com.agentery/agentery

Est-ce que com.agentery/agentery est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.agentery/agentery » 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 23 outils

• compare_providers≈ 728 tokens

  Use to compare 2–6 shortlisted listings side by side — plan-level prices (e.g. the Pro tier), capabilities, deployment, licence and how to connect — or to check a quote against alternatives. Inputs resolve to real listings by exact handle, then exact name, never a silent fuzzy swap: unknown inputs come back in unresolved_inputs with suggested_matches and a corrected_call; if only one input is real it is compared with its nearest market peers (comparison_status says so); if none resolve, comparison_status is insufficient_valid_providers. Mixed delivery types are flagged: a hosted agent and an MCP server are not directly equivalent, so compare hosted prices with hosted prices. Over-budget or weak matches get suggested_alternatives. Returns a concise decision view by default (fit, observed plans and prices with source and date, job cost, requirement verdicts, unknowns); pass detail:"full" for every field. Accepts `provider_ids` (aliases: handles, ids, or a comma-separated string).

  Paramètres, retour & exemple (7)

  Paramètres

  • task · string · optionnel
    Optional. The buyer's job in plain words; used as the service_view heading.
  • detail · string · optionnel · concise | full
    Optional. concise (default): the decision view. full: the complete comparison (all plan lines, evidence checks, deployment, licence, how to connect, requirement evidence excerpts).
  • service · string · optionnel · supplier-verification | contract-review | developer-capabilities | cheaper-alternatives
    Optional. A service recipe whose fixed requirements and evidence fields are applied (see service_view.requirements).
  • optional · array · optionnel
    Optional preferences: reported in service_view but never gating.
  • request_ref · string · optionnel
    Optional task reference (rq_ + 12 hex) from an earlier answer. Continues that task: its remembered facts (quantities, budget, requirements, benchmark selection) apply to this call, and the answer keeps the same request_ref.
  • provider_ids · array · requis
    2-6 provider handles from search_providers/market_gaps, e.g. ["openhands","lexaclaw"]
  • requirements · array · optionnel
    Optional. Mandatory requirements as plain phrases (e.g. "sanctions screening", "documented MCP interface"). Adds an ADDITIVE service_view: per-provider evidence matrix from stored first-party page text — supported / not_supported / unknown with the excerpt and observation date; unknown never means unsupported.

  Exemple d'appel

  {"name": "compare_providers", "arguments": {"provider_ids": []}}

  Exemple de retour

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

• create_custom_benchmark≈ 448 tokens

  Use when someone wants to keep watching the prices of products they choose (e.g. five named writing tools). Creates a PRIVATE custom benchmark (a saved, calculated peer cohort) over Agentery's data — no account needed. Two modes: (A) explicit members: pass `members` (a list of exact handles; product names/domains resolve where unambiguous). (B) fork a market: pass `base_niche` (its slug) plus optional `remove`/`add`. Returns a one-time secret `benchmark_id` (cb_… token) — store it; it's your only key. Use it later in get/update/delete and in market_report/get_price_index/get_price_index_history. Ambiguous names are returned as candidates, never silently resolved; unresolved inputs block creation unless allow_partial:true. All prices/history are computed from Agentery's immutable observations; canonical market data is never changed.

  Paramètres, retour & exemple (6)

  Paramètres

  • add · array · optionnel
    members to add
  • name · string · optionnel
    Optional private label
  • remove · array · optionnel
    Mode B: members to drop from the forked market
  • members · array · optionnel
    Mode A: exact handles (preferred), product names or domains
  • base_niche · string · optionnel
    Mode B: slug of the canonical market to fork
  • allow_partial · boolean · optionnel
    Create with only the resolved members when some inputs don't resolve (default false)

  Exemple d'appel

  {"name": "create_custom_benchmark", "arguments": {"add": [], "name": "texte", "remove": [], "members": [], "base_niche": "texte", "allow_partial": true}}

  Exemple de retour

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

• delete_custom_benchmark≈ 130 tokens

  Disable access to a custom benchmark. Keeps only a minimal audit record; no underlying Agentery data is touched. Pass `benchmark_id`.

  Paramètres, retour & exemple (1)

  Paramètres

  • benchmark_id · string · requis
    Your cb_ token

  Exemple d'appel

  {"name": "delete_custom_benchmark", "arguments": {"benchmark_id": "texte"}}

  Exemple de retour

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

• demand_signals≈ 251 tokens

  Inspect searches by external callers in the last 90 days that found no provider or only weak matches (best relevance below 0.62), shown as generalised job labels and ranked by distinct callers. Most entries come from a single caller: treat those as leads. These are limited coverage signals from Agentery's own callers — not proof that a product does not exist, and not proof that a market has paying demand. Not a prerequisite for choosing a product. Empty args ({}) return the current list; an empty response means there is insufficient qualifying evidence (status insufficient_evidence + next_step) — it is never filled from search popularity, page views or trending queries.

  Paramètres, retour & exemple (1)

  Paramètres

  • limit · number · optionnel
    Max signals (1-50, default 20)

  Exemple d'appel

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

  Exemple de retour

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

• find_market≈ 307 tokens

  Use when someone asks what a kind of product typically costs or who competes in a space, e.g. 'what should I charge for lead-generation automation' or 'tools that monitor competitor pricing'. Maps the task to its market (the nearest providers by meaning, no fixed categories) and returns the market label, provider and priced counts, the nearest providers with observed prices, and pricing_by_tier (median, p25/p75, range and n per buyer tier). When nothing is close it returns no_match or thin_coverage and withholds pricing rather than invent a market. For market plus shortlist in one call use research_capability.

  Paramètres, retour & exemple (2)

  Paramètres

  • task · string · requis
    REQUIRED. A natural-language task, capability or service in plain words, e.g. 'reconcile supplier invoices'. Call as {"task": "…"}; an empty call returns status needs_input with an example and searches nothing.
  • query · string · optionnel
    Alias for task (back-compat only) — prefer task

  Exemple d'appel

  {"name": "find_market", "arguments": {"task": "texte"}}

  Exemple de retour

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

• get_custom_benchmark≈ 280 tokens

  Get a private custom benchmark's current report: members, current stats (headline median/quartiles only when ≥3 comparable priced members — monthly, per-seat and per-call prices are never blended), buyer-tier / provider-type / pricing-unit cohorts, historical index, and data coverage. Pass `benchmark_id` (your cb_ token) as an ARGUMENT.

  Paramètres, retour & exemple (4)

  Paramètres

  • as_of · string · optionnel
    Optional YYYY-MM-DD — reproduce the exact stats + index as they were on that date, using this version's fixed membership
  • version · number · optionnel
    Optional benchmark version (default latest)
  • benchmark_id · string · requis
    Your cb_ token (bearer secret; passed as an argument, never a URL)
  • response_mode · string · optionnel · summary | full
    full includes the index series

  Exemple d'appel

  {"name": "get_custom_benchmark", "arguments": {"benchmark_id": "texte"}}

  Exemple de retour

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

• get_group_fair_price≈ 307 tokens

  Use to check what a product of a given kind typically costs: give a task or product type (or a group_id from the group price league) and get its product group's fair price for each buyer tier (individual, pro, team / small business, enterprise) — the median entry monthly price in that tier with its typical range — plus which payment models the group typically uses (free, subscription, usage, one-time, contact sales), usage and one-time medians where at least 3 listings publish them, and the group's price-index change over 90 days. Groups are built from what products do, not from price. Medians of current published prices only; individual listings are not returned — use search_providers for candidates.

  Paramètres, retour & exemple (2)

  Paramètres

  • query · string · optionnel
    The task or product type, e.g. 'AI meeting notes for sales teams'.
  • group_id · number · optionnel
    Optional: a group id from agentery.com/aepi/groups or from get_provider_profile's product_group.

  Exemple d'appel

  {"name": "get_group_fair_price", "arguments": {"query": "texte", "group_id": 1}}

  Exemple de retour

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

• get_price_index≈ 481 tokens

  Use when asked whether prices of AI agents, tools or MCP servers are rising or falling overall. Returns the current Agent Economy Price Index (AEPI), a like-for-like index of observed agent and MCP pricing (base 100 = 29 Jun 2026; an index level, not a price), with 1-, 7- and 30-day change, plus the same for the four buyer tiers (Individual, Pro, Team/SME, Enterprise). provider_type=agent|mcp gives the standalone index for that delivery type; tier narrows to one tier. For the trend over time use get_price_index_history; for what a particular kind of product costs use get_group_fair_price or price_benchmark.

  Paramètres, retour & exemple (4)

  Paramètres

  • tier · string · optionnel · all | individual | pro | team | enterprise
    Filter to one buyer tier ('team' = Team/SME). Default 'all'.
  • benchmark_id · string · optionnel
    Optional: a private custom benchmark token (cb_…) from create_custom_benchmark — returns that cohort's current index instead of the economy index. Cannot be combined with niche.
  • provider_type · string · optionnel · all | agent | mcp | subscription | hybrid | one_off | payg
    'all' (default) = the combined whole-economy index; 'agent' or 'mcp' = the standalone index over just that delivery type (own base 100); 'payg' = the standalone pay-as-you-go sub-index (usage rates purchasable without a subscription, engine v2). Agents and MCPs price and move differently, so an MCP buyer should read the 'mcp' index and an agent buyer the 'agent' index.
  • response_mode · string · optionnel · summary | full
    'summary' (default) or 'full' (adds exact sub-0.01% moves and repricing counts).

  Exemple d'appel

  {"name": "get_price_index", "arguments": {"tier": "all", "benchmark_id": "texte", "provider_type": "all", "response_mode": "summary"}}

  Exemple de retour

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

• get_price_index_history≈ 610 tokens

  Use to show how AI agent and MCP prices have moved over time: the dated Agent Economy Price Index series, the same chained like-for-like series agentery.com/aepi charts. Points are index levels (base 100), never prices. Whole-economy series by default; `tier` for one buyer tier; provider_type agent|mcp for one delivery type (own base 100); `period` 30d (default) / 90d / all; response_mode summary (default) or full (adds gap flags). Thin data returns insufficient_history, never an invented series. For what one capability costs use price_benchmark or market_report. Also reads a private custom benchmark's history via benchmark_id.

  Paramètres, retour & exemple (6)

  Paramètres

  • tier · string · optionnel · all | individual | pro | team | enterprise
    Return one buyer tier's series ('team' = Team/SME). Default 'all' = the headline series.
  • since · string · optionnel
    Optional, for providers that poll: the `cursor` (or `next_cursor`) from your previous call, or an ISO timestamp of your last check. Returns only what changed since then: new_points (newly published days), corrected_points (earlier days whose published level changed, with previous_level) and withdrawn_points, plus next_cursor for the next call. status 'no_changes' when nothing changed. Omit for the full history.
  • period · string · optionnel · 30d | 90d | all
    History window. Default '30d'.
  • benchmark_id · string · optionnel
    Optional: a private custom benchmark token (cb_…) — returns that cohort's dated series instead of the economy series. Cannot be combined with niche.
  • provider_type · string · optionnel · all | agent | mcp | subscription | hybrid | one_off | payg
    'all' (default) = the combined whole-economy series, or the standalone 'agent' / 'mcp' / 'subscription' / 'hybrid' / 'one_off' / 'payg' = the billing-LENS series (they cut across provider/mcp; a rate sits in one delivery type AND one lens; own base 100) — 'payg' (pay-as-you-go, engine v2) series (own base 100).
  • response_mode · string · optionnel · summary | full
    'summary' (default, compact) or 'full'.

  Exemple d'appel

  {"name": "get_price_index_history", "arguments": {"tier": "all", "since": "texte", "period": "30d", "benchmark_id": "texte", "provider_type": "all", "response_mode": "summary"}}

  Exemple de retour

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

• get_provider≈ 175 tokens

  For buying decisions prefer get_provider_profile (prices, deployment, evidence); use this only for the short public directory card of one provider by handle or registration number: bio, source URLs, X-verification status, entity type, community rating and structured profile when available.

  Paramètres, retour & exemple (2)

  Paramètres

  • handle · string · optionnel
    Provider handle, e.g. 'openhands'
  • regNum · number · optionnel
    Registration number, e.g. 2432

  Exemple d'appel

  {"name": "get_provider", "arguments": {"handle": "texte", "regNum": 1}}

  Exemple de retour

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

• get_provider_profile≈ 294 tokens

  Use to check one specific listing before recommending or connecting it: plans and prices with billing units, what it does, integrations, deployment (hosted / self_hosted / both / unknown, with evidence), licence (named licence only), liveness and how to connect (website, docs, MCP endpoint with a copy-paste config_snippet, A2A agent card, API, install). Fields are null when the vendor publishes nothing; nothing is guessed. price_applies_to flags a stored price that belongs to the vendor's platform rather than this connector. product_group names the listing's product group with its fair price per buyer tier and 90-day price-index change. reported_success stays null until 5+ distinct reporters in 90 days; after actually using a listing, call report_outcome.

  Paramètres, retour & exemple (1)

  Paramètres

  • provider_id · string · requis
    The provider_id/handle returned by search_providers or compare_providers

  Exemple d'appel

  {"name": "get_provider_profile", "arguments": {"provider_id": "texte"}}

  Exemple de retour

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

• get_research≈ 246 tokens

  Status and result of a research job created by request_research. status: queued / running / answered / partly_answered / still_unknown / failed; phase: queued | running | retry_scheduled | completed_answer | completed_unknown | failed. Poll no more often than poll_after_seconds — polling is free and never repeats the work. result: answer (yes/no/partly/unknown), short_answer, evidence per claim (quote, URL, observed date; file path and revision for repositories; element for pricing-page buttons), facts assessed separately (e.g. Dockerfile vs published image vs Helm chart), conflicts and what remains unresolved.

  Paramètres, retour & exemple (1)

  Paramètres

  • job_id · string · requis
    The job_id from request_research (rj_ + 12 hex).

  Exemple d'appel

  {"name": "get_research", "arguments": {"job_id": "texte"}}

  Exemple de retour

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

• market_gaps≈ 306 tokens

  Use when a seller or investor asks which tasks people look for that few paid products serve. Clusters requests seen on this MCP server by meaning and returns those far from any paid provider: the request phrasing, distinct_callers, raw_requests, the nearest paid provider and its similarity (low = under-served). headline = jobs asked by two or more callers; weak_leads = one caller; information_requests = questions about a named product. These are research leads from limited traffic, not buyer counts or proof of a market-wide gap; few or none is normal while volume is low. Marked test traffic is excluded. No arguments needed.

  Paramètres, retour & exemple (3)

  Paramètres

  • rank · string · optionnel · gaps | hot
    gaps (default): whitespace with money, crowded excluded. hot: most active by market pulse, crowding ignored.
  • limit · number · optionnel
    Max gaps (1-50, default 15)
  • sector · string · optionnel
    Optional sector filter, e.g. 'legal', 'healthcare'

  Exemple d'appel

  {"name": "market_gaps", "arguments": {"rank": "gaps", "limit": 1, "sector": "texte"}}

  Exemple de retour

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

• market_report≈ 545 tokens

  Deep-dive ONE market before building or investing — the market is the semantic neighbourhood of your natural-language query (nearest providers by text embedding, NO fixed category). Every field is MEASURED: the observed-pricing benchmark separated by provider type and buyer tier (median, mean, stdev, p25/p75, min–max range and n via the canonical pricing engine), how many providers are in the neighbourhood and how many are priced, and the top providers already competing there with their observed price and relevance. Pass `query` (a natural-language capability or market, e.g. 'customer support chatbot'). For market + pricing + a ready shortlist in one call, use research_capability.

  Paramètres, retour & exemple (6)

  Paramètres

  • limit · number · optionnel
    full mode: members per page (1–150, default 50).
  • query · string · requis
    Natural-language capability or market, e.g. 'customer support chatbot' or 'ai phishing detection'.
  • offset · number · optionnel
    full mode: paging offset over members (default 0).
  • cohort_ref · string · optionnel
    Optional (1.17.0): reuse the exact set of comparable providers selected by an earlier price_benchmark / market_report / research_capability call (its cohort_ref), instead of re-selecting the market from new wording.
  • request_ref · string · optionnel
    Optional task reference (rq_ + 12 hex) from an earlier answer. Continues that task: its remembered facts (quantities, budget, requirements, benchmark selection) apply to this call, and the answer keeps the same request_ref.
  • response_mode · string · optionnel · summary | full
    'summary' (DEFAULT): neighbourhood counts, per-type/per-tier price cohorts and the top 12 providers. 'full' (1.17.0): EVERY member of the neighbourhood, paged with offset / limit, each with its price reading (plan, unit, currency, source, observed date).

  Exemple d'appel

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

  Exemple de retour

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

• price_benchmark≈ 1070 tokens

  Use to judge whether a price is fair or what a capability typically costs, e.g. 'Is $49/month reasonable for an AI SDR for a small team?'. Pass the capability as `query` (aliases: task, niche). Returns observed prices of comparable products — median, p25/p75, range, mean, stdev and n — split by delivery type (agent | mcp) and buyer tier (individual / pro / team_sme / enterprise), never blended across incompatible pricing units. Comparables are the products closest in what they do (no fixed categories). A benchmark describes an observed sample; it is not a quote and not evidence of willingness to pay. Set provider_type and buyer_tier when known. If nothing priced is close it returns resolved:false with a note, never an invented figure.

  Paramètres, retour & exemple (15)

  Paramètres

  • task · string · optionnel
    Alias of `query` (same text).
  • limit · number · optionnel
    Observations per page in full mode (1–100, default 50).
  • niche · string · optionnel
    Legacy alias of `query`, kept for older clients — prefer `query`.
  • query · string · optionnel
    The capability to benchmark, in natural language, e.g. 'AI code review' or 'supplier invoice reconciliation'. Preferred input.
  • offset · number · optionnel
    Paging offset over the selected observations in full mode.
  • sector · string · optionnel
    Sector name, e.g. 'legal' (ignored if a query is given)
  • currency · string · optionnel
    Currency of proposed_price (ISO code, default USD).
  • buyer_tier · string · optionnel · individual | pro | team_sme | enterprise | all
    Buyer tier being priced. Set when the user describes who is buying (an individual, a professional, a team/SME, or an enterprise). An individual licence must never be represented by the SME or enterprise price.
  • cohort_ref · string · optionnel
    Optional (1.17.0): reuse the exact set of comparable providers selected by an earlier price_benchmark / market_report / research_capability call (its cohort_ref), instead of re-selecting the market from new wording.
  • commitment · string · optionnel · monthly | annual
    Billing commitment of proposed_price (default monthly).
  • request_ref · string · optionnel
    Optional task reference (rq_ + 12 hex) from an earlier answer. Continues that task: its remembered facts (quantities, budget, requirements, benchmark selection) apply to this call, and the answer keeps the same request_ref.
  • pricing_unit · string · optionnel · flat | per_seat | per_agent | per_call | per_ticket | per_conversation | per_resolution | per_transaction
    Billing unit the benchmark is FOR (1.17.0: honoured). Selects the comparable observations; units are never converted into one another, and a thin unit returns its observations and the gap — never a flat-monthly substitute. A query such as 'cost per support ticket' sets it when omitted.
  • provider_type · string · optionnel · agent | mcp | api | all
    Delivery type being priced. Set when the user says provider, MCP or API. Omit (or 'all') to get the per-type matrix instead of a blended figure. 'api' is recognised but not yet a separate commercial cohort (folded into provider).
  • response_mode · string · optionnel · summary | full
    'summary' (default): the selected benchmark with its top observations. 'full': every included observation (paged), with plan, native price, unit, commitment, source and observed date.
  • proposed_price · number · optionnel
    Optional (sellers): a proposed price to position against the selected comparable offers (same unit; currency below). Returns where it sits in the observed range; a percentile only with ≥5 comparable providers. A market reference, not an optimal price.

  Exemple d'appel

  {"name": "price_benchmark", "arguments": {"task": "texte", "limit": 1, "niche": "texte", "query": "texte", "offset": 1, "sector": "texte"}}

  Exemple de retour

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

• refine_results≈ 428 tokens

  Use when an earlier search_providers or research_capability answer missed what was meant: pass its request_ref and the correction in plain words (e.g. 'must integrate with Slack', 'budget is $20/month', 'data must stay in the EU'). Agentery re-runs the search with the changed constraints (the others are kept) and returns the new answer plus what changed. source: 'human' (the user's words), 'agent' (your assessment, default) or 'follow_up'. Agentery sees only the request and correction you send, never your wider conversation. Task answers (search_providers, compare_providers, research_capability, price_benchmark, market_report) carry ONE request_ref plus a 'conversation' block: the facts remembered for the task, any optional clarification questions (at most two, one round) and the exact refine_results call to continue. Answer with plain words, 'unknown' or 'skip'; source is one of human, agent, follow_up. Pass the same request_ref to another task tool to continue the task there. References expire 24 h after the last turn.

  Paramètres, retour & exemple (3)

  Paramètres

  • source · string · optionnel · human | agent | follow_up
    Where the correction came from. Default 'agent'.
  • correction · string · requis
    What was missing or wrong, in plain words.
  • request_ref · string · requis
    The request_ref from the earlier answer (rq_ + 12 hex characters).

  Exemple d'appel

  {"name": "refine_results", "arguments": {"correction": "texte", "request_ref": "texte"}}

  Exemple de retour

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

• report_outcome≈ 488 tokens

  Report the result of ACTUALLY USING a listed provider for a task. Testing Agentery's connection or retrieval does not establish that the listed provider worked — do not report those. Reports are self-reported evidence subject to eligibility checks: they are correlated with your recent retrievals, improve ranking accuracy, and unlock higher rate limits for contributors. Only reports we can match to one of YOUR retrievals (search_providers / get_provider_profile / compare_providers / suggest_alternatives naming that provider, last 48h) carry weight; unmatched reports are stored but unweighted. Aggregates surface as `reported_success` on profile/comparison cards once 5+ distinct reporters exist (90-day window). Callers with 5+ correlated reports in 30 days get a doubled per-minute rate limit. Send an x-agentery-key header to keep one reporter identity across IPs (it is stored only as a hash).

  Paramètres, retour & exemple (6)

  Paramètres

  • note · string · optionnel
    Optional free-text detail (capped at 300 chars)
  • outcome · string · requis · worked | failed | partial
    Did the provider accomplish the task you hired it for?
  • agent_id · string · requis
    Handle of the provider you used, as returned by search_providers/get_provider_profile/compare_providers
  • task_type · string · optionnel
    Optional short task label, e.g. 'code-review', 'lead-enrichment'
  • latency_ms · number · optionnel
    Optional end-to-end latency of the provider in milliseconds
  • error_class · string · optionnel
    Optional failure class, e.g. 'timeout', 'auth', 'wrong-output', 'endpoint-down'

  Exemple d'appel

  {"name": "report_outcome", "arguments": {"outcome": "worked", "agent_id": "texte"}}

  Exemple de retour

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

• request_research≈ 356 tokens

  Use when a buying decision hinges on one specific fact about one listing that its profile does not settle, e.g. {"provider_id":"flux_operator","requirement":"Is there a Helm chart for Kubernetes?"} or 'Does the Business plan go to checkout or to contact sales?'. Agentery reads the vendor's own pages, its code repository (read, never run) and the pricing page's buttons, and answers yes / no / partly / unknown with quotes, URLs and observation dates. Usually answered in this response within about 15 s; otherwise call get_research with the job_id after poll_after_seconds. Identical questions share one job. A found statement is the vendor's own claim, not independent verification.

  Paramètres, retour & exemple (3)

  Paramètres

  • provider_id · string · requis
    The listing (provider_id from search_providers).
  • request_ref · string · optionnel
    Optional: the request_ref of the answer that raised the question.
  • requirement · string · requis
    The requirement in plain words, e.g. 'EU data residency', 'integrates with Slack', 'SOC 2 Type II', 'commercial use permitted'.

  Exemple d'appel

  {"name": "request_research", "arguments": {"provider_id": "texte", "requirement": "texte"}}

  Exemple de retour

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

• research_capability≈ 765 tokens

  Use for a quick first overview of a buying task in one call: the closest-matching listings (matched on what they do, no fixed categories), the price range and median for comparable products (with n), and a shortlist with observed prices, market_position (below / in line / above market) and handles in compare_ready for compare_providers. Also returns suggested_alternatives. It does not run the comparison. For careful selection prefer search_providers → get_provider_profile → compare_providers. Accepts `task` (aliases: query, q).

  Paramètres, retour & exemple (10)

  Paramètres

  • sort · string · optionnel · match | price_asc
    Shortlist ordering. Default 'match'.
  • task · string · requis
    Required — the natural-language capability/task, e.g. 'reconcile supplier invoices' or 'litigation-analysis provider'. Aliases: query, q.
  • limit · number · optionnel
    Shortlist size (1-12, default 5).
  • buyer_tier · string · optionnel · individual | pro | team | enterprise
    Optional buyer tier to price against ('team' = Team/SME).
  • cohort_ref · string · optionnel
    Optional (1.17.0): reuse the exact set of comparable providers selected by an earlier price_benchmark / market_report / research_capability call.
  • request_ref · string · optionnel
    Optional task reference (rq_ + 12 hex) from an earlier answer. Continues that task: its remembered facts (quantities, budget, requirements, benchmark selection) apply to this call, and the answer keeps the same request_ref.
  • integrations · array · optionnel
    Optional required integrations, e.g. ["zendesk","slack"] — soft preference; integration status is reported per provider.
  • provider_type · string · optionnel · auto | agent | mcp | api | any
    Preferred delivery type. 'auto' (default) infers from the task; note 'AI agent' phrasing is treated as generic (neutral), not an agent-only filter. When a type is explicit (mcp/api/agent) matching providers are SOFT-RANKED to the top and the rest are kept as clearly-labelled cross_type_alternative entries — never hard-filtered (no zero-result cliff), and the functional match is never changed. Every provider is labelled with provider_type (public values: agent | mcp | api | unknown) + type_match_score; provider_type{type_rank_boost_applied, boosted_provider_type, result_counts_by_type} is returned.
  • response_mode · string · optionnel · summary | full
    'summary' (default) or 'full' (adds tier cohorts, coverage and raw results).
  • max_monthly_usd · number · optionnel
    Optional budget ceiling in USD/month — filters the shortlist and drives suggested_alternatives.

  Exemple d'appel

  {"name": "research_capability", "arguments": {"task": "texte"}}

  Exemple de retour

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

• search_providers≈ 874 tokens

  Use when someone wants to find or shortlist AI products, AI agents, MCP servers or APIs for a task, e.g. 'AI tool that transcribes sales calls' or 'MCP server to reply to Zendesk tickets'. Returns ranked candidates with what each does, a fit label (match / partial / weak, naming any mismatch), delivery type, price status (known / free / contact_sales / unknown; unknown is never free) and links. Requirements in the wording are checked per result; unverified ones are marked unknown. Results are candidates to check: open strong ones with get_provider_profile and compare finalists with compare_providers. Thin coverage returns no_match, never padding.

  Paramètres, retour & exemple (10)

  Paramètres

  • sort · string · optionnel · match | price_asc
    match (default) or price_asc (cheapest observed price first; unpriced providers last)
  • limit · number · optionnel
    Max results (1-50, default 20)
  • query · string · requis
    REQUIRED. Free-text description of the product job you are buying, e.g. 'customer support provider with Zendesk integration' or 'supplier invoice reconciliation'. Not for questions about Agentery itself (upvotes, endpoints): those return status unsupported_request.
  • billing · array · optionnel
    Only providers with one of these observed billing models, e.g. ["free","freemium","subscription","usage"]
  • filters · object · optionnel
    Optional: industry_fit[], integrations_available[], entity_type[] (agent|tool|infrastructure|service|marketplace|content-community), autonomy_level[] (assistant|workflow automation|agentic|infrastructure), minimum_evidence_quality (low|medium|high)
  • deployment · string · optionnel · hosted | self_hosted | both | unknown
    Optional (1.10.0). Keep only providers whose EVIDENCED deployment model matches: hosted = a vendor-published MCP endpoint exists (connect, nothing to install); self_hosted = a published install line (npx/uvx/docker/pip/git clone) and no vendor endpoint; both = both are documented; unknown = no evidence held. 'both' listings satisfy hosted and self_hosted. Evidence comes from the vendor's own pages and source directories (Glama/MCP registry attributes) — never guessed from a repository's existence.
  • request_ref · string · optionnel
    Optional task reference (rq_ + 12 hex) from an earlier answer. Continues that task: its remembered facts (quantities, budget, requirements, benchmark selection) apply to this call, and the answer keeps the same request_ref.
  • provider_type · string · optionnel · agent | mcp | api | platform | infrastructure
    Filter to one provider type — the audited classification dimension (same as the website type chips and AEPI facets); result labels always match this filter. Omit for all types.
  • max_monthly_usd · number · optionnel
    Drop providers whose observed lowest paid tier exceeds this (USD/month). Providers with no observed public price still pass unless require_public_price is true.
  • require_public_price · boolean · optionnel
    Only return providers with an observed public price (default false)

  Exemple d'appel

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

  Exemple de retour

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

• stop_research_updates≈ 104 tokens

  Stop watching a research job (the result stays retrievable with get_research).

  Paramètres, retour & exemple (1)

  Paramètres

  • job_id · string · requis

  Exemple d'appel

  {"name": "stop_research_updates", "arguments": {"job_id": "texte"}}

  Exemple de retour

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

• suggest_alternatives≈ 362 tokens

  Find related alternatives to a known provider, ranked by text-embedding nearness to that provider's OWN profile (NO category lookup), each with observed price, endpoint liveness, community upvotes and how_to_connect (website, docs, mcp endpoint). For cheaper_only, inspect whether the reference price and candidate prices support a valid comparison: an empty response may reflect a missing or incompatible reference price rather than the absence of alternatives (the response says which). Accepts `agent_id` (aliases: handle, id). These substitutes are also surfaced inside research_capability and compare_providers. Each alternative also carries `deployment` (evidenced model) and how_to_connect.install / repository (1.10.0).

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · number · optionnel
    Max alternatives (1-10, default 5)
  • agent_id · string · requis
    Handle of the provider to find substitutes for, e.g. 'openhands'
  • cheaper_only · boolean · optionnel
    Only keep alternatives priced below the subject's lowest monthly price. Free/freemium providers always qualify; providers with no observed price are excluded. Default false.

  Exemple d'appel

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

  Exemple de retour

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

• update_custom_benchmark≈ 187 tokens

  Add/remove members or rename a custom benchmark. Creates a NEW immutable version (the previous version stays fully reproducible) and returns the exact change-impact on the median/quartiles/index. Pass `benchmark_id`.

  Paramètres, retour & exemple (4)

  Paramètres

  • add · array · optionnel
  • remove · array · optionnel
  • rename · string · optionnel
  • benchmark_id · string · requis
    Your cb_ token

  Exemple d'appel

  {"name": "update_custom_benchmark", "arguments": {"benchmark_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://agentery.com/api/mcp