ai.funkel/funkel

Est-ce que ai.funkel/funkel est sûr ?

Au dernier audit MCP Hub, le serveur MCP « ai.funkel/funkel » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 51 outils

• approve_leads≈ 412 tokens

  Approve or reject one or more discovered leads. Two-phase: first call returns a confirmation token + preview; the user reviews an inline card and confirms; second call (with confirmation_token) commits the status flip. action='approve' requires campaign_id (the campaign the leads will be associated with); action='reject' does not. The tool stamps each lead's status + reviewed_at + campaign_id; downstream campaign-engine pipelines ingest approved leads through their normal path. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Paramètres, retour & exemple (6)

  Paramètres

  • count · integer · optionnel
    Number of leads in the batch (used in the confirm preview; mirrors len(lead_ids))
  • action · string · requis · approve | reject
    Decision applied to every lead in lead_ids
  • lead_ids · array · requis
    Discovered lead ids (from a prior find_leads result)
  • campaign_id · string · optionnel
    Required for action=approve; omitted for action=reject (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • campaign_name · string · optionnel
    Campaign name (used in the confirm preview)
  • confirmation_token · string · optionnel
    Phase-2 token (omit on phase-1)

  Exemple d'appel

  {"name": "approve_leads", "arguments": {"action": "approve", "lead_ids": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• configure_agent_source≈ 520 tokens

  Configure X or Hacker News searches for one owned agent and set source listening. First call get_agent_sources. If no source exists, propose 1-10 precise searches from the user's request and saved ICP; do not invent a broad search without showing it. If a source exists, show its current searches and only replace them when the user asks to change them. This tool previews the exact searches, enabled state, and LinkedIn resolution choice, then requires explicit approval. It does not activate a draft or paused agent. For an already configured source whose searches need no change, use set_agent_source_listening instead. X needs a connected X account for collection. Hacker News uses its public search provider. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Paramètres, retour & exemple (8)

  Paramètres

  • app_id · string · optionnel
    Product ID; required for MCP accounts with multiple products (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • source · string · requis · x | hackernews
    Source to configure
  • enabled · boolean · requis
    Whether source listening should be enabled after approval
  • queries · array · requis
    Exact search phrases to save, 1-10
  • agent_id · string · requis
    Owned agent ID (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • confirmation_token · string · optionnel
    One-use approval token; omit before approval
  • expected_updated_at · string · optionnel
    Version from get_agent_sources; optional on first call
  • auto_resolve_linkedin · boolean · optionnel
    Hacker News only; automatically resolve high-confidence leads through LinkedIn, which may use credits

  Exemple d'appel

  {"name": "configure_agent_source", "arguments": {"source": "x", "enabled": true, "queries": [], "agent_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• control_operator_task≈ 305 tokens

  Pause, resume, cancel, or retry a durable Operator task after exact approval. Supply its current version. Retry also requires one failed idempotent local-read step; completed effects cannot replay. A pause may not stop an already executing provider call. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Paramètres, retour & exemple (5)

  Paramètres

  • step_id · string · optionnel
    Required failed step id for retry (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • task_id · string · requis
    Task id (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • operation · string · requis · pause | resume | cancel | retry
    Task transition
  • expected_version · integer · requis
    Current task version
  • confirmation_token · string · optionnel
    One-use approval token; omit on first call

  Exemple d'appel

  {"name": "control_operator_task", "arguments": {"task_id": "texte", "operation": "pause", "expected_version": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• create_agent≈ 988 tokens

  Create a new draft agent under the request's scoped app. Two-phase: first call previews every setting; second call after user confirmation creates it. The agent's ICP starts from the app's saved ICP; icp_filters keys you supply override only those keys, every other saved field (job_titles, mandatory_keywords, excluded_companies, company_sizes, ...) is kept as-is. Do not restate the full ICP from memory for a vague request like "set it up" — omit icp_filters entirely to inherit the saved ICP untouched, and only pass the specific keys the user actually asked to change. To deliberately clear a list field, pass it as an empty array. excluded_companies stores exact current employer names. If supplied a LinkedIn company URL, Operator saves its slug name there and retains the URL separately for competitor signals; ask the user to verify the name in the approval. Supply signals only when the user selects exact agent discovery signals; each signal must include its supported platform, category, key, label, enabled state, and config. An explicit empty signals array creates no signals. Without signals, defaults seed from the merged ICP filters. A requested keyword such as product launch can be a keyword_tracking_product_launch signal with config.keyword='product launch'. Ask for missing signal details; never claim a requested setting was saved if this schema cannot represent it. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Paramètres, retour & exemple (9)

  Paramètres

  • name · string · requis
    Display name for the new agent (1-100 chars)
  • type · string · optionnel · signal | lookalike
    Agent type (default 'signal')
  • signals · array · optionnel
    Exact agent discovery signals. Omit to seed from ICP; use [] for none.
  • app_name · string · optionnel
    App name (used in the confirm preview)
  • icp_filters · object · optionnel
    Optional structured ICP filters. Use job_titles, industries, regions, company_sizes, excluded_keywords, and exclude_service_providers. excluded_companies accepts exact employer names or LinkedIn company URLs. URLs become slug names and remain separately in competitor_urls. Ask the user to verify the employer name. Do not use unsupported excluded_industries.
  • max_signals · integer · optionnel
    Cap on enabled signals (default 15)
  • icp_description · string · optionnel
    Free-text ICP description for the new agent
  • confirmation_token · string · optionnel
    Phase-2 token (omit on phase-1)
  • linkedin_account_ids · array · optionnel
    Local UUIDs of the workspace LinkedIn accounts selected for searches. Use [] for none.

  Exemple d'appel

  {"name": "create_agent", "arguments": {"name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• create_campaign_draft≈ 643 tokens

  Create a draft campaign in the selected product. First show the exact campaign, agent, destination list, and any agent retargeting for approval. With agent_id and no list_id, use the agent's destination list; if absent, assign the product default list to both. An explicit different list retargets a draft agent only after approval. Never activate, discover, enroll, or send. If workflow_steps are omitted, create the standard 4-step flow. For custom steps ask about type, delay, message mode, template, and final step. In message_template use only {FirstName}, {LastName}, and {Company}. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Paramètres, retour & exemple (7)

  Paramètres

  • name · string · requis
    Campaign name (1-100 chars)
  • list_id · string · optionnel
    Optional owned lead list id. With an agent, omitted means its destination list. Otherwise the product default list is used or created. (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • agent_id · string · optionnel
    Optional agent id (from a prior list_agents) that supplies leads to this campaign (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • app_name · string · optionnel
    App name (used in the confirm preview)
  • workflow_steps · array · optionnel
    Optional custom workflow steps
  • cold_outreach_mode · string · optionnel · invite | inmail | email
    Cold outreach mode (default 'invite')
  • confirmation_token · string · optionnel
    Phase-2 token (omit on phase-1)

  Exemple d'appel

  {"name": "create_campaign_draft", "arguments": {"name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• create_list≈ 206 tokens

  Create a new lead list scoped to the request's app. Use this when the user wants to organise leads into a named bucket (e.g. 'Q4 Targets', 'Hot Founders'). The new list starts empty; populate it later via approve_leads with action='approve' and the new list_id, or by editing the list manually. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Paramètres, retour & exemple (2)

  Paramètres

  • name · string · requis
    Display name for the list (1-100 chars)
  • description · string · optionnel
    Optional one-sentence description of what the list is for

  Exemple d'appel

  {"name": "create_list", "arguments": {"name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• create_note≈ 280 tokens

  Create a scoped note or reminder after an explicit confirmation of the exact lead, body, and due date. One request_key can be applied only once; a changed intent with the same key fails. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Paramètres, retour & exemple (6)

  Paramètres

  • body · string · requis
    Note or reminder text (max 5000 chars)
  • lead_id · string · requis
    Lead id (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • reminder_at · string · optionnel
    Optional RFC3339 reminder due date
  • request_key · string · requis
    Stable unique request identity (8-128 chars)
  • reminder_body · string · optionnel
    Required when reminder_at is set
  • confirmation_token · string · optionnel
    One-use approval token; omit on first call

  Exemple d'appel

  {"name": "create_note", "arguments": {"body": "texte", "lead_id": "texte", "request_key": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• create_reminder≈ 262 tokens

  Create a scoped note or reminder after an explicit confirmation of the exact lead, body, and due date. One request_key can be applied only once; a changed intent with the same key fails. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Paramètres, retour & exemple (5)

  Paramètres

  • body · string · requis
    Note or reminder text (max 5000 chars)
  • lead_id · string · requis
    Lead id (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • reminder_at · string · requis
    Required RFC3339 reminder due date
  • request_key · string · requis
    Stable unique request identity (8-128 chars)
  • confirmation_token · string · optionnel
    One-use approval token; omit on first call

  Exemple d'appel

  {"name": "create_reminder", "arguments": {"body": "texte", "lead_id": "texte", "reminder_at": "texte", "request_key": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• draft_icp_edit≈ 273 tokens

  Stage a proposed ICP edit for one agent. Returns a diff envelope (current vs proposed, fields_changed) so the user can review the change inline before applying it. Does NOT write — to actually apply the edit, call update_icp (confirm-tier) with the same agent_id and proposed fields. Use this when the user describes a change in plain language ('target Series A founders in EU' etc.); never call update_icp directly without first staging here so the user sees the before/after.

  Paramètres, retour & exemple (3)

  Paramètres

  • agent_id · string · requis
    Agent id (from a prior list_agents) (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • proposed_icp_filters · string · optionnel
    Optional structured filters JSON (job_titles, industries, regions, etc.)
  • proposed_icp_description · string · optionnel
    Free-text description of the new ICP

  Exemple d'appel

  {"name": "draft_icp_edit", "arguments": {"agent_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• draft_message≈ 272 tokens

  Generate a personalised draft for one lead. Reads the lead's profile (industry, role, headline, optional reference hook) and returns a single message body. Does NOT send. After the user reviews and approves, call send_message to actually deliver. ALWAYS call get_lead first to inspect reply_state — refuse to draft for opted-out / replied / rejected leads. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Paramètres, retour & exemple (3)

  Paramètres

  • tone · string · optionnel · warm | professional | direct
    Voice register
  • lead_id · string · requis
    Lead id (from a prior find_leads / get_lead) (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • reference · string · optionnel
    Optional specific hook (recent post, role transition, milestone) the user wants referenced

  Exemple d'appel

  {"name": "draft_message", "arguments": {"lead_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• enable_agent≈ 252 tokens

  Enable (activate) a paused or draft agent so it begins discovering leads on its schedule. Two-phase: first call returns a confirmation token + preview; the user reviews and confirms; second call (with confirmation_token) commits. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Paramètres, retour & exemple (4)

  Paramètres

  • agent_id · string · requis
    Agent id (from a prior list_agents) (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • app_name · string · requis
    App name (used in the confirm preview)
  • agent_name · string · requis
    Agent name (used in the confirm preview)
  • confirmation_token · string · optionnel
    Phase-2 token (omit on phase-1)

  Exemple d'appel

  {"name": "enable_agent", "arguments": {"agent_id": "texte", "app_name": "texte", "agent_name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• enable_campaign≈ 307 tokens

  Enable (resume) a paused or draft campaign. The campaign engine starts scheduling actions per the campaign's workflow. Two-phase: first call returns a confirmation token + preview; the user reviews and confirms; second call (with confirmation_token) commits. Activation pre-conditions (workflow steps, connected accounts) are validated by the underlying campaign service — the tool surfaces any failure as a structured error. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Paramètres, retour & exemple (4)

  Paramètres

  • app_name · string · requis
    App name (used in the confirm preview)
  • campaign_id · string · requis
    Campaign id (from a prior list_campaigns) (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • campaign_name · string · requis
    Campaign name (used in the confirm preview)
  • confirmation_token · string · optionnel
    Phase-2 token (omit on phase-1)

  Exemple d'appel

  {"name": "enable_campaign", "arguments": {"app_name": "texte", "campaign_id": "texte", "campaign_name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• find_leads≈ 299 tokens

  Search leads in the app the request is scoped to. Returns bounded named summaries and IDs, never full rows. Use get_lead to load full detail for a specific id. Default source is 'discovered' (agent-found, awaiting approval); pass source='approved' to search leads already in campaigns. Optional 'search' keyword runs an ILIKE across name/company/headline; optional 'status' narrows by lead status. If results are thin, surface the count and ASK the user before broadening the filters — do not silently relax constraints.

  Paramètres, retour & exemple (4)

  Paramètres

  • limit · integer · requis
    Max number of leads to return (1..50)
  • search · string · optionnel
    Optional keyword (matches name, company, or headline)
  • source · string · optionnel · discovered | approved
    Lead source. Default 'discovered'.
  • status · string · optionnel
    Optional status filter (e.g. 'pending', 'approved', 'rejected')

  Exemple d'appel

  {"name": "find_leads", "arguments": {"limit": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_access≈ 121 tokens

  Read current account access for Operator and campaign actions in the selected product. Operator requires active paid or lifetime entitlement; campaign actions also accept active beta. Feature flags are account-wide. This snapshot is not an action authorization or credit quote.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_access", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_agent_sources≈ 246 tokens

  Read X and Hacker News listening settings for one owned agent, including sources not configured yet. Use list_agents to identify the agent. If configured is false, use configure_agent_source to propose exact searches and enable listening after approval. If configured is true and searches exist, use set_agent_source_listening to toggle without changing searches. A draft or paused agent does not collect until activated. LinkedIn signal groups are separate.

  Paramètres, retour & exemple (2)

  Paramètres

  • app_id · string · optionnel
    Product ID; required for MCP accounts with multiple products (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • agent_id · string · requis
    Owned agent ID (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)

  Exemple d'appel

  {"name": "get_agent_sources", "arguments": {"agent_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_analytics≈ 214 tokens

  Return product- or campaign-scoped activity in a UTC lookback interval. Completed actions and invitations use executed_at; connections and recorded replies use lead event timestamps. These are separate event counts, not one conversion cohort. Default 7 days, max 90.

  Paramètres, retour & exemple (3)

  Paramètres

  • scope · string · optionnel · campaign | app
    Aggregation level. Default 'app'.
  • days_back · integer · optionnel
    Lookback window in days (default 7)
  • campaign_id · string · optionnel
    Campaign id (required when scope='campaign') (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)

  Exemple d'appel

  {"name": "get_analytics", "arguments": {"scope": "campaign", "days_back": 1, "campaign_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_campaign≈ 162 tokens

  Read one campaign in the selected product. Returns updated_at for exact approved settings changes, plus workflow, sender assignments, schedule, review mode, observed action state, and readiness blockers. Empty templates are not claimed as generated messages. No sending or activation occurs.

  Paramètres, retour & exemple (1)

  Paramètres

  • campaign_id · string · requis
    Campaign id (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)

  Exemple d'appel

  {"name": "get_campaign", "arguments": {"campaign_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_conversation_context≈ 257 tokens

  Return bounded conversation context for one lead or conversation in the request scope: lead profile, product/campaign context, last real messages, recent notes, open reminders, and Reply Assistant follow-up suggestions. Use this before meeting prep, reply planning, or questions about what happened with a lead. Read-only; does not draft or send messages.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
    Number of recent messages to return (default 12, max 20)
  • lead_id · string · optionnel
    Lead id from find_leads/get_lead or a follow-up result (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • conversation_id · string · optionnel
    Conversation id from inbox/follow-up context (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)

  Exemple d'appel

  {"name": "get_conversation_context", "arguments": {"limit": 1, "lead_id": "texte", "conversation_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_daily_priorities≈ 110 tokens

  Rank up to four live operational starting points with source IDs and links. Connected senders and insights count across the account; leads, actions, campaigns, and unread messages count within the selected product. Read only.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_daily_priorities", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_inbox_queue≈ 186 tokens

  List reply-needed conversations or due follow-ups in the selected product. One predicate determines both the total and page. AI drafts are not counted as sent replies. Limit 50; use offset for later pages.

  Paramètres, retour & exemple (3)

  Paramètres

  • mode · string · requis · reply_needed | due_follow_up
    Queue type
  • limit · integer · optionnel
    Maximum rows (default 20, max 50)
  • offset · integer · optionnel
    Pagination offset (default 0)

  Exemple d'appel

  {"name": "get_inbox_queue", "arguments": {"mode": "reply_needed"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_insight≈ 124 tokens

  Read one insight and its evidence for the selected product, or an explicitly account-scoped insight. Read-only; proposed changes never run here.

  Paramètres, retour & exemple (1)

  Paramètres

  • insight_id · string · requis
    Insight id (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)

  Exemple d'appel

  {"name": "get_insight", "arguments": {"insight_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_lead≈ 224 tokens

  Return full detail for a single lead by id, INCLUDING the derived reply_state and opt_out flags. Always call this before drafting or sending a message — a lead whose reply_state is 'replied', 'rejected', or 'opted_out', or whose opt_out is true, must NEVER be drafted to or messaged. Use source='approved' for leads in active campaigns; default 'discovered' is for agent-found leads awaiting approval.

  Paramètres, retour & exemple (2)

  Paramètres

  • source · string · optionnel · discovered | approved
    Lead source. Default 'discovered'.
  • lead_id · string · requis
    Lead id (from a prior find_leads result) (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)

  Exemple d'appel

  {"name": "get_lead", "arguments": {"lead_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_list≈ 117 tokens

  Read one unarchived list in the selected product and its exact member count. Does not return contacts; use list_list_contacts.

  Paramètres, retour & exemple (1)

  Paramètres

  • list_id · string · requis
    List id (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)

  Exemple d'appel

  {"name": "get_list", "arguments": {"list_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_operator_task≈ 136 tokens

  Read one durable Operator task in the selected product with its step states, action states, safe summaries, version, and progress. Does not return executable arguments or raw provider errors.

  Paramètres, retour & exemple (1)

  Paramètres

  • task_id · string · requis
    Task id (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)

  Exemple d'appel

  {"name": "get_operator_task", "arguments": {"task_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_product_context≈ 102 tokens

  Read the selected product's name, site, description, ICP summary, language, Product Brain availability, and dashboard link. No provider credentials or raw unbounded configuration are returned.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_product_context", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_reply_attempt≈ 155 tokens

  Read one reply attempt by its stable request_key in the selected product. Returns actual delivery evidence and next_action. Uncertain delivery requires manual provider review unless an exact outgoing provider message is confirmed. Never retries or sends.

  Paramètres, retour & exemple (1)

  Paramètres

  • request_key · string · requis
    Stable request identity from send_conversation_reply, 8-128 characters

  Exemple d'appel

  {"name": "get_reply_attempt", "arguments": {"request_key": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_schedule≈ 181 tokens

  List pending, approved, or failed scheduled actions in the selected product, optionally for one campaign. Returns one bounded page and its exact total. Completed actions are not included.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
    Page size (default 20; max 50)
  • offset · integer · optionnel
    Page offset (default 0)
  • campaign_id · string · optionnel
    Optional campaign id (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)

  Exemple d'appel

  {"name": "get_schedule", "arguments": {"limit": 1, "offset": 1, "campaign_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_scheduled_action≈ 132 tokens

  Read one action in the selected product: campaign, lead, type, state, scheduled and executed timestamps. Does not return provider metadata or a message body.

  Paramètres, retour & exemple (1)

  Paramètres

  • action_id · string · requis
    Scheduled action id (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)

  Exemple d'appel

  {"name": "get_scheduled_action", "arguments": {"action_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_sender_health≈ 100 tokens

  Show account-wide connected sender health and separate readiness for campaign assignments in the selected product. An account-wide connection does not prove a campaign has a usable sender.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_sender_health", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• import_search_leads_to_list≈ 408 tokens

  Import lead rows from a prior search_external_leads session into a lead list. Two-phase: first call returns a confirmation token + preview; the user reviews an inline card and confirms; second call with confirmation_token commits. provider_ids omitted means import every lead in the search session. Supply list_id for an existing list, or list_name to create a new list during the confirmed commit. After a committed result returns list_id, use that exact list_id when creating a campaign from the imported search leads. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Paramètres, retour & exemple (5)

  Paramètres

  • list_id · string · optionnel
    Existing lead list id to import into (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • list_name · string · optionnel
    Name for a new list to create during the confirmed import when list_id is omitted
  • session_id · string · requis
    Lead search session id returned by search_external_leads (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • provider_ids · array · optionnel
    Optional selected provider ids from the search result. Omit to import all search results.
  • confirmation_token · string · optionnel
    Phase-2 token (omit on phase-1)

  Exemple d'appel

  {"name": "import_search_leads_to_list", "arguments": {"session_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_agents≈ 172 tokens

  List the specialist agents in the product/app the request is scoped to. Returns a summary (count, brief one-liner, and a list of {id, name, status, type, role, one-line icp_summary}). Internal agent types are mapped to product-facing roles such as lead_finder. Full ICP filters / config are collapsed to a one-liner — call get_agent (later) to load full detail. Use this to ground questions like 'how many specialist agents do I have?' or 'which Lead Finder agents are active?'.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_agents", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_apps≈ 156 tokens

  List the products/apps owned by the request scope's user. Returns a summary (count, brief one-liner, and a list of {id, name, description, url}) with no timestamps or internal flags. Use this for product inventory or explicit product-switch/disambiguation questions. A normal product-scoped request already carries an app_id in Scope; do not call this just to discover which product to use for product-aware actions.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_apps", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_campaigns≈ 134 tokens

  List the campaigns in the app the request is scoped to (excludes archived). Returns a summary (count, brief one-liner, and a list of {id, name, status, agent_id, list_id}). Settings JSON is intentionally omitted; call get_campaign for current workflow, sender, and action detail. Status values: 'draft', 'active', 'paused'.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_campaigns", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_insights≈ 144 tokens

  List account-scoped and selected-product-scoped open insights. Each item labels its actual scope; account insights are not product-only. Exact total and bounded pages.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
    Page size (default 20; max 50)
  • offset · integer · optionnel
    Page offset (default 0)

  Exemple d'appel

  {"name": "list_insights", "arguments": {"limit": 1, "offset": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_list_contacts≈ 174 tokens

  List contacts in one unarchived list in the selected product. Returns exact total and bounded pages. Does not expose email or provider identifiers.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
    Page size (default 20; max 50)
  • offset · integer · optionnel
    Page offset (default 0)
  • list_id · string · requis
    List id (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)

  Exemple d'appel

  {"name": "list_list_contacts", "arguments": {"list_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_lists≈ 137 tokens

  List unarchived lead lists in the selected product. Returns exact total and bounded pages. A list's cached lead count is not used for the total.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
    Page size (default 20; max 50)
  • offset · integer · optionnel
    Page offset (default 0)

  Exemple d'appel

  {"name": "list_lists", "arguments": {"limit": 1, "offset": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_operator_files≈ 114 tokens

  List up to 20 files uploaded to any of your Operator threads in the selected product. Returns file IDs and metadata only, never bytes or extracted text. A file can be used for a same-product LinkedIn reply, not another product or email reply.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_operator_files", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_operator_tasks≈ 136 tokens

  List durable Operator tasks in the selected product. Returns bounded pages, exact total, task status, version, and links. Read-only.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
    Page size (default 20; max 50)
  • offset · integer · optionnel
    Page offset (default 0)

  Exemple d'appel

  {"name": "list_operator_tasks", "arguments": {"limit": 1, "offset": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_preferences≈ 120 tokens

  List up to 20 saved Operator preferences for the user and product in the request scope. Values are bounded, labeled customer data, and never override user instructions or system rules. Returns key, value, and source only. No provider credentials or tokens are returned.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_preferences", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_reminders≈ 162 tokens

  List open or done lead reminders in the selected product with exact total and bounded pages. Default is open. This read does not complete a reminder.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
    Page size (default 20; max 50)
  • offset · integer · optionnel
    Page offset (default 0)
  • status · string · optionnel · open | done
    Reminder state

  Exemple d'appel

  {"name": "list_reminders", "arguments": {"limit": 1, "offset": 1, "status": "open"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• pause_agent≈ 282 tokens

  Pause an active agent so it stops discovering new leads. The agent's existing leads remain in the list. Two-phase: first call returns a confirmation token + preview; the user reviews an inline card and confirms or cancels; second call (with confirmation_token) commits the pause. Always include agent_name + app_name so the preview is human-readable. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Paramètres, retour & exemple (4)

  Paramètres

  • agent_id · string · requis
    Agent id (from a prior list_agents) (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • app_name · string · requis
    App name (used in the confirm preview)
  • agent_name · string · requis
    Agent name (used in the confirm preview)
  • confirmation_token · string · optionnel
    Phase-2 token (omit on phase-1)

  Exemple d'appel

  {"name": "pause_agent", "arguments": {"agent_id": "texte", "app_name": "texte", "agent_name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• pause_campaign≈ 280 tokens

  Pause an active campaign. The campaign engine stops scheduling actions. Two-phase: first call returns a confirmation token + preview; the user reviews an inline card and confirms or cancels; second call (with confirmation_token) commits the pause. Always include campaign_name + app_name so the preview is human-readable. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Paramètres, retour & exemple (4)

  Paramètres

  • app_name · string · requis
    App name (used in the confirm preview)
  • campaign_id · string · requis
    Campaign id (from a prior list_campaigns) (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • campaign_name · string · requis
    Campaign name (used in the confirm preview)
  • confirmation_token · string · optionnel
    Phase-2 token (omit on phase-1)

  Exemple d'appel

  {"name": "pause_campaign", "arguments": {"app_name": "texte", "campaign_id": "texte", "campaign_name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• prepare_conversation_reply≈ 238 tokens

  Prepare one exact local inbound reply. Returns recipient, sender, channel, inbound revision, final signed body, and optional owned file identity. Never sends. Files are available only for supported connected LinkedIn conversations in the selected product.

  Paramètres, retour & exemple (3)

  Paramètres

  • body · string · requis
    Full proposed body. A configured booking link is tracked in the final preview
  • attachment_id · string · optionnel
    Optional file ID from list_operator_files. LinkedIn replies only (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • conversation_id · string · requis
    Local conversation id (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)

  Exemple d'appel

  {"name": "prepare_conversation_reply", "arguments": {"body": "texte", "conversation_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• rename_list≈ 239 tokens

  Rename one unarchived list in the selected product after explicit approval. Supply its current name to reject stale changes; include the full new description. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Paramètres, retour & exemple (5)

  Paramètres

  • name · string · requis
    New name (1-100 chars)
  • list_id · string · requis
    List id (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • description · string · requis
    New full description
  • expected_name · string · requis
    Current list name
  • confirmation_token · string · optionnel
    Approval token; omit on first call

  Exemple d'appel

  {"name": "rename_list", "arguments": {"name": "texte", "list_id": "texte", "description": "texte", "expected_name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• save_preference≈ 221 tokens

  Save one selected-product Operator preference after explicit approval. The value is bounded JSON data, not a system instruction. Existing keys update. No provider credentials or tokens are accepted. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Paramètres, retour & exemple (4)

  Paramètres

  • key · string · requis
    Preference key (1-100 chars; no secret names)
  • value · string · requis
    JSON value (max 600 bytes)
  • reason · string · optionnel
    Why this preference should be saved
  • confirmation_token · string · optionnel
    Approval token; omit on first call

  Exemple d'appel

  {"name": "save_preference", "arguments": {"key": "texte", "value": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• search_external_leads≈ 271 tokens

  Search LinkedIn for fresh people leads from the request user's connected account. Use this when the user describes leads to find by words, roles, companies, or market terms, rather than asking to search existing saved leads. Returns a server-owned session_id and up to 10 lead previews. To import the results, call import_search_leads_to_list with that session_id after the user asks to import all or selected leads. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Paramètres, retour & exemple (3)

  Paramètres

  • role · string · optionnel
    Optional job-title filter, e.g. 'Founder OR CEO'
  • limit · integer · optionnel
    Max results to return (1..10). Default 10.
  • query · string · requis
    Free-text people search, e.g. 'YC founders building AI devtools'

  Exemple d'appel

  {"name": "search_external_leads", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• send_conversation_reply≈ 318 tokens

  Send one exact prepared reply to the latest inbound message after explicit human approval. Provide the complete prepare_conversation_reply result, its attachment_id when present, and a stable request_key. A timeout is uncertain and cannot be retried automatically. LinkedIn files are supported; email files are unavailable. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Paramètres, retour & exemple (5)

  Paramètres

  • prepared · object · requis
    Exact prepare_conversation_reply result; all fields required by server validation
  • request_key · string · requis
    Stable unique request identity, 8-128 chars
  • attachment_id · string · optionnel
    Exact prepared file ID when present (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • confirmation_token · string · optionnel
    One-use approval token; omit on first call
  • reply_as_confirmed · boolean · optionnel
    Explicitly confirm using another rep's sender

  Exemple d'appel

  {"name": "send_conversation_reply", "arguments": {"prepared": {}, "request_key": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• set_agent_source_listening≈ 348 tokens

  Pause or resume only an existing X or Hacker News source on an agent. First read get_agent_sources. If configured is false or searches are empty, use configure_agent_source instead. The first call shows exact approval; a second user-approved call commits. Saved searches, budgets, LinkedIn resolution and other sources stay unchanged. A draft or paused agent does not collect until activated. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Paramètres, retour & exemple (6)

  Paramètres

  • app_id · string · optionnel
    Product ID; required for MCP accounts with multiple products (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • source · string · requis · x | hackernews
    One source
  • enabled · boolean · requis
  • agent_id · string · requis
    Owned agent ID (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • confirmation_token · string · optionnel
    One-use approval token, omit before approval
  • expected_updated_at · string · optionnel
    Version from get_agent_sources; optional on first call

  Exemple d'appel

  {"name": "set_agent_source_listening", "arguments": {"source": "x", "enabled": true, "agent_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• update_campaign_settings≈ 574 tokens

  Change a campaign's manual review, send window, or sender assignments in the selected product. Read get_campaign first and copy its updated_at as expected_updated_at. Omitted settings remain unchanged. Explicit null sender clears one platform. First call returns an exact approval preview; approved execution saves all changes atomically. It never activates, enrolls, or sends. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Paramètres, retour & exemple (6)

  Paramètres

  • schedule · object · optionnel
    Full send window; all fields required when supplied
  • campaign_id · string · requis
    Owned campaign id from get_campaign (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • review_mode · boolean · optionnel
    Require manual review before outreach
  • confirmation_token · string · optionnel
    One-use approval token; omit on first call
  • account_assignments · object · optionnel
    Only supplied platforms change
  • expected_updated_at · string · optionnel
    Exact updated_at from get_campaign; may be omitted for a server-filled first preview

  Exemple d'appel

  {"name": "update_campaign_settings", "arguments": {"campaign_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• update_campaign_workflow≈ 601 tokens

  Update message content on existing steps in a draft or paused campaign. Prefer one-based message_order, which counts only message-bearing steps and automatically skips invite/follow steps: message_order 1, 2, 3 targets the first, second, and third messages even when raw workflow step 1 is an invite. step_order remains available only when an exact raw workflow order is already known. Provide exactly one selector plus the exact message_template for every item. In message_template use only {FirstName}, {LastName}, and {Company} personalization variables. This is a two-phase confirmed action: first call without confirmation_token returns a confirmation card; approved execution applies the exact stored workflow_messages through the campaign service. It never launches or sends. Always include campaign_name and app_name for a human-readable preview. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Paramètres, retour & exemple (5)

  Paramètres

  • app_name · string · requis
    App name used in the confirmation preview
  • campaign_id · string · requis
    Campaign id from a prior list_campaigns result (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • campaign_name · string · requis
    Campaign name used in the confirmation preview
  • workflow_messages · array · requis
    Exact message content to persist; prefer message_order 1..N for ordinary campaign copy
  • confirmation_token · string · optionnel
    Phase-2 token (omit on phase-1)

  Exemple d'appel

  {"name": "update_campaign_workflow", "arguments": {"app_name": "texte", "campaign_id": "texte", "campaign_name": "texte", "workflow_messages": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• update_icp≈ 458 tokens

  Apply an ICP edit (description and/or filters JSON) to one agent. Two-phase: first call returns a confirmation token + preview; the user reviews the diff inline and confirms; second call (with confirmation_token) commits. ALWAYS call draft_icp_edit first so the user sees a before/after; never call update_icp directly without staging a diff. Pre-populate agent_name in the schema args so the preview is human-readable. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Paramètres, retour & exemple (6)

  Paramètres

  • agent_id · string · requis
    Agent id (from a prior list_agents) (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • agent_name · string · optionnel
    Agent name (used in the confirm preview)
  • icp_filters · object · optionnel
    New structured filters object. Use company_sizes and exclude_service_providers. excluded_companies accepts exact employer names or LinkedIn company URLs. URLs become slug names and remain separately in competitor_urls. Ask the user to verify the employer name. Omit to leave unchanged.
  • icp_description · string · optionnel
    New free-text ICP description (omit to leave unchanged)
  • industry_inputs · array · optionnel
    Explicit raw industry intent from draft_icp_edit ready_to_execute_args. Omit for canonical-only edits. Nested old metadata cannot restore removed raw intent.
  • confirmation_token · string · optionnel
    Phase-2 token (omit on phase-1)

  Exemple d'appel

  {"name": "update_icp", "arguments": {"agent_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://api.funkel.ai/mcp