com.bidda/bidda-compliance

Est-ce que com.bidda/bidda-compliance est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.bidda/bidda-compliance » 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 25 outils

• browse_topics≈ 160 tokens

  Browse the registry by cross-cutting compliance TOPIC (for example data breach notification, AI transparency, AML and KYC). Returns each topic with how many rules carry it and across how many pillars and jurisdictions. Topics sit on top of the 39 pillars without replacing them. Free, no key required. Pass a topic string to drill into one.

  Paramètres, retour & exemple (1)

  Paramètres

  • topic · string · optionnel
    Optional topic name to filter or drill into.

  Exemple d'appel

  {"name": "browse_topics", "arguments": {"topic": "texte"}}

  Exemple de retour

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

• check_action_compliance≈ 241 tokens

  Pre-flight regulatory check. Agent describes an intended action in natural language ("process EU resident biometric data", "transfer health records to a third-party AI vendor", "deploy autonomous trading model in Singapore") and receives a ranked list of regulations that may apply, plus a risk indicator (LOW/MODERATE/HIGH). The primary tool for runtime compliance gating in autonomous agent workflows.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
    Max matches to return. Default 10. Max 25.
  • action · string · requis
    Natural-language description of the intended action.
  • jurisdiction · string · optionnel
    Optional jurisdiction filter (eu, us, uk, etc.).

  Exemple d'appel

  {"name": "check_action_compliance", "arguments": {"action": "texte"}}

  Exemple de retour

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

• compare_jurisdictions≈ 244 tokens

  Compare how different jurisdictions address a compliance topic, side by side, including where their numeric thresholds differ (for example a breach-notification deadline of 72 hours versus 30 days). It surfaces the real rules and numbers and does not rank which jurisdiction is stricter. Requires an active Bidda subscription: pass your key as api_key.

  Paramètres, retour & exemple (2)

  Paramètres

  • topic · string · requis
    Topic to compare, for example "data breach notification".
  • api_key · string · optionnel
    Optional. Your Bidda subscription key. Prefer sending it as the x-bidda-api-key header (or Authorization: Bearer), which is what the auth settings in your MCP client configure; the header takes precedence over this argument. A free trial counts.

  Exemple d'appel

  {"name": "compare_jurisdictions", "arguments": {"topic": "texte"}}

  Exemple de retour

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

• consult_node≈ 456 tokens

  The one-call governed turn: fetch the full vault node (this consumes one call on your key, exactly like unlocking a node) AND record a verified node_consulted entry for it on an open run, in a single step. The entry pins the node to its current version + integrity hash, so the run receipt proves what the agent actually consulted. Use this instead of get_node when you are inside a run. Requires an active Bidda subscription: pass api_key.

  Paramètres, retour & exemple (9)

  Paramètres

  • model · string · optionnel
    Optional: the model id/version making the decision.
  • action · string · optionnel
    Optional: an action the agent took or checked.
  • run_id · string · requis
    The open run to record into (from open_run).
  • api_key · string · optionnel
    Optional. Your Bidda subscription key. Prefer sending it as the x-bidda-api-key header (or Authorization: Bearer), which is what the auth settings in your MCP client configure; the header takes precedence over this argument. A free trial counts.
  • node_id · string · requis
    The rule to fetch and record.
  • decision · string · optionnel
    Optional: what the agent decided using this node.
  • input_hash · string · optionnel
    Optional: a sha256:... hash of the user's message instead of the text.
  • user_input · string · optionnel
    Optional: the end user's message as text.
  • subject_hash · string · optionnel
    Optional: a sha256:... hash of an end-user identifier. Hash only.

  Exemple d'appel

  {"name": "consult_node", "arguments": {"run_id": "texte", "node_id": "texte"}}

  Exemple de retour

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

• create_attestation≈ 330 tokens

  Create a signed, time-stamped record of which Bidda rules a person or AI agent relied on for a decision. Returns a record ID and a public verify URL so anyone can later confirm the record has not been changed. Useful for agents that must keep an audit trail of what they checked. Requires an active Bidda subscription: pass api_key.

  Paramètres, retour & exemple (5)

  Paramètres

  • agent · string · requis
    The system or AI agent that made the decision.
  • nodes · array · requis
    node_ids that were checked (max 50).
  • action · string · optionnel
    Optional: what the agent did.
  • api_key · string · optionnel
    Optional. Your Bidda subscription key. Prefer sending it as the x-bidda-api-key header (or Authorization: Bearer), which is what the auth settings in your MCP client configure; the header takes precedence over this argument. A free trial counts.
  • workflow_steps_followed · array · optionnel
    Optional: steps the agent followed.

  Exemple d'appel

  {"name": "create_attestation", "arguments": {"agent": "texte", "nodes": []}}

  Exemple de retour

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

• create_control_attestation≈ 478 tokens

  Sign a tamper-evident record of one of YOUR OWN controls or policies and the Bidda obligation nodes it maps to. Each obligation is pinned to its current version + integrity hash at signing time, so the record shows what the control was mapped against on that date. This is the design-side evidence ('we operate this control, mapped to these obligations'); run receipts are the operating-side evidence. Requires an active Bidda subscription: pass api_key.

  Paramètres, retour & exemple (9)

  Paramètres

  • nodes · array · requis
    Obligation node_ids the control maps to (max 50).
  • api_key · string · optionnel
    Optional. Your Bidda subscription key. Prefer sending it as the x-bidda-api-key header (or Authorization: Bearer), which is what the auth settings in your MCP client configure; the header takes precedence over this argument. A free trial counts.
  • control · string · requis
    The name of your control or policy.
  • framework · string · optionnel
    Optional: the framework you are mapping to (e.g. "EU AI Act").
  • statement · string · requis
    What the control does or asserts (plain text).
  • evidence_ref · string · optionnel
    Optional: a reference/URL/hash to your own evidence (kept by you).
  • control_owner · string · optionnel
    Optional: the role or team that owns the control.
  • control_status · string · optionnel
    Optional: implemented | planned | in-progress.
  • effective_date · string · optionnel
    Optional: YYYY-MM-DD the control took effect.

  Exemple d'appel

  {"name": "create_control_attestation", "arguments": {"nodes": [], "control": "texte", "statement": "texte"}}

  Exemple de retour

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

• drift_check≈ 327 tokens

  Check whether the compliance rules an agent has cached in its own memory are still current. Submit the node_id and the integrity hash you stored when you last grounded on each rule; get back, per rule, whether it is fresh, has drifted (content changed), or was withdrawn (instrument repealed) - so the agent re-grounds before acting on stale law. Included with every API tier; the per-call batch size scales with your plan. Pass api_key.

  Paramètres, retour & exemple (2)

  Paramètres

  • anchors · array · requis
    The cached rules to check.
  • api_key · string · optionnel
    Optional. Your Bidda subscription key. Prefer sending it as the x-bidda-api-key header (or Authorization: Bearer), which is what the auth settings in your MCP client configure; the header takes precedence over this argument. A free trial counts.

  Exemple d'appel

  {"name": "drift_check", "arguments": {"anchors": []}}

  Exemple de retour

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

• gap_check≈ 280 tokens

  Given the compliance rules a team says it covers, return the prerequisite rules Bidda's dependency graph links to them that were NOT listed - the 'you missed the prerequisite obligation' gaps - plus any covered rule the registry marks withdrawn. A coverage aid for a qualified reviewer; it does not rank or determine compliance. Requires an active Bidda subscription: pass api_key.

  Paramètres, retour & exemple (3)

  Paramètres

  • depth · number · optionnel
    Optional: how many dependency hops to walk (1-3, default 1).
  • nodes · array · requis
    The node_ids you cover (max 200).
  • api_key · string · optionnel
    Optional. Your Bidda subscription key. Prefer sending it as the x-bidda-api-key header (or Authorization: Bearer), which is what the auth settings in your MCP client configure; the header takes precedence over this argument. A free trial counts.

  Exemple d'appel

  {"name": "gap_check", "arguments": {"nodes": []}}

  Exemple de retour

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

• get_audit_pack≈ 206 tokens

  Export a run as a governance evidence pack: the signed receipt, every entry, a roll-up of the nodes consulted (with pinned versions/hashes), an independent hash-chain + Merkle integrity self-check, and a coversheet mapping the receipt to the record-keeping obligations it supports (EU AI Act Art. 12/26, ISO/IEC 42001, NIST AI RMF). A sealed run is readable by id; a still-open run's draft pack needs your api_key.

  Paramètres, retour & exemple (2)

  Paramètres

  • run_id · string · requis
    The run to export.
  • api_key · string · optionnel
    Optional: your Bidda key, required for a still-open (unsealed) run.

  Exemple d'appel

  {"name": "get_audit_pack", "arguments": {"run_id": "texte"}}

  Exemple de retour

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

• get_crosswalk≈ 145 tokens

  Return the cross-framework mapping dimensions for a node: which other regulations, standards, or jurisdictions this rule maps to (e.g. GDPR Article 17 → CCPA right-to-delete → POPIA Section 24). Discovery returns the available dimensions; full mapping values are vault-gated.

  Paramètres, retour & exemple (1)

  Paramètres

  • node_id · string · requis
    Node ID to inspect crosswalks for.

  Exemple d'appel

  {"name": "get_crosswalk", "arguments": {"node_id": "texte"}}

  Exemple de retour

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

• get_dependency_chain≈ 184 tokens

  Walk the prerequisite chain for a compliance node. Given one node, returns its full dependency tree (the prior obligations an agent must satisfy before this one applies). Use this to plan a complete compliance posture: unlocking one node usually requires understanding 3-8 upstream nodes. Defaults to depth 2; max 4.

  Paramètres, retour & exemple (2)

  Paramètres

  • node_id · string · requis
    Root node ID to expand from.
  • max_depth · integer · optionnel
    How many hops to walk (1-4). Default 2.

  Exemple d'appel

  {"name": "get_dependency_chain", "arguments": {"node_id": "texte"}}

  Exemple de retour

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

• get_jurisdiction_bundle≈ 192 tokens

  Return all compliance nodes that apply in a specific jurisdiction (EU, US, UK, Australia, Singapore, India, Canada, China, South Africa, Japan, Brazil and others). Use when an agent enters a new market and needs the full regulatory surface for that geography.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
    Max nodes to return. Default 25. Max 100.
  • jurisdiction · string · requis
    Jurisdiction code or name: eu, us, uk, au, sg, india, canada, china, south-africa, japan, brazil.

  Exemple d'appel

  {"name": "get_jurisdiction_bundle", "arguments": {"jurisdiction": "texte"}}

  Exemple de retour

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

• get_latest_changes≈ 178 tokens

  List the most recently updated compliance nodes: the regulatory change feed. Use to monitor incoming amendments, new guidance, or freshly added rules. Filter by pillar to focus on a domain. Agents should call this on a schedule to keep compliance posture current.

  Paramètres, retour & exemple (2)

  Paramètres

  • days · integer · optionnel
    Look back N days. Default 30. Max 180.
  • pillar · string · optionnel
    Optional pillar filter, e.g. "AI Governance" or "Cybersecurity".

  Exemple d'appel

  {"name": "get_latest_changes", "arguments": {"days": 1, "pillar": "texte"}}

  Exemple de retour

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

• get_mitre_mapping≈ 269 tokens

  The MITRE Rosetta Stone. Given a MITRE technique ID across 5 frameworks (ATT&CK Enterprise, ATT&CK Mobile, ATT&CK ICS, D3FEND, ATLAS), return the Bidda node for that technique plus its mapped compliance obligations: NIST 800-53 controls, ISO 27001 Annex A clauses, PCI DSS requirements, NIS2 articles, HIPAA Security Rule, DORA articles, NERC CIP, IEC 62443. The bridge between how SOC teams think (technique IDs) and how compliance teams think (control families). Free.

  Paramètres, retour & exemple (1)

  Paramètres

  • technique_id · string · requis
    MITRE technique ID. ATT&CK Enterprise (T1566, T1486, T1078, T1003.001, T1547.001); ATT&CK Mobile (T1474, T1521, T1471, T1430, T1417); ATT&CK ICS (T0883, T0809, T0879, T0886, T0814); D3FEND (D3-FIM, D3-MFA, D3-NTA, D3-NI, D3-AI, D3-CH); CAPEC (CAPEC-66, CAPEC-63, CAPEC-98, CAPEC-94, CAPEC-49); or ATLAS (AML.T0020).

  Exemple d'appel

  {"name": "get_mitre_mapping", "arguments": {"technique_id": "texte"}}

  Exemple de retour

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

• get_node≈ 166 tokens

  Get a specific compliance node by its ID. Returns the node summary: title, compliance pillar, version, last updated, and BLUF. The full node (machine-executable deterministic workflow, actionable schema, primary legal citations, dependency chain) is available at bidda.com.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    Node ID, e.g. "basel-iii-capital", "gdpr-article-5-principles", "fatf-40-recommendations-2023-consolidated", "us-hipaa-privacy-rule"

  Exemple d'appel

  {"name": "get_node", "arguments": {"id": "texte"}}

  Exemple de retour

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

• get_run≈ 143 tokens

  Fetch a run and its entries. The owner can read an open or sealed run (pass api_key); a sealed run is also publicly readable by id and reports whether its signature is valid.

  Paramètres, retour & exemple (2)

  Paramètres

  • run_id · string · requis
    The run_id to fetch.
  • api_key · string · optionnel
    Optional: your Bidda key, required to read your own still-open run.

  Exemple d'appel

  {"name": "get_run", "arguments": {"run_id": "texte"}}

  Exemple de retour

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

• list_pillars≈ 155 tokens

  List all compliance pillars in the Bidda Sovereign Intelligence registry with node counts. Use this first to discover available compliance domains before searching. Bidda has 10,099 cryptographically-verified nodes across 39 pillars, including a MITRE layer spanning 6 frameworks (ATT&CK Enterprise/Mobile/ICS, D3FEND, ATLAS, CAPEC) plus Banking, AI Governance, Cybersecurity, Healthcare, Legal, ESG and more.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_pillars", "arguments": {}}

  Exemple de retour

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

• obligation_deltas≈ 315 tokens

  The obligation-level change feed: primary sources whose content changed (or whose node was withdrawn), mapped to the Bidda obligation nodes they affect, filterable by time, pillar, or specific nodes. Use it to answer 'what obligations changed since I last reviewed?'. Requires an active Bidda subscription: pass api_key.

  Paramètres, retour & exemple (5)

  Paramètres

  • limit · number · optionnel
    Optional: max deltas to return (default 100, max 500).
  • nodes · array · optionnel
    Optional: restrict to deltas affecting these node_ids.
  • since · string · optionnel
    Optional: ISO timestamp; only deltas newer than this are returned.
  • pillar · string · optionnel
    Optional: restrict to one pillar.
  • api_key · string · optionnel
    Optional. Your Bidda subscription key. Prefer sending it as the x-bidda-api-key header (or Authorization: Bearer), which is what the auth settings in your MCP client configure; the header takes precedence over this argument. A free trial counts.

  Exemple d'appel

  {"name": "obligation_deltas", "arguments": {"limit": 1, "nodes": [], "since": "texte", "pillar": "texte", "api_key": "texte"}}

  Exemple de retour

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

• open_run≈ 266 tokens

  Open a run ledger: a signed, tamper-evident log of what an agent does across a whole task or conversation (for example a support-bot chat). Returns a run_id. Record one entry per turn with record_run_entry, then seal_run to get a single signed Run Receipt. Requires an active Bidda subscription: pass api_key.

  Paramètres, retour & exemple (3)

  Paramètres

  • agent · string · requis
    The system or agent running the task or conversation.
  • label · string · optionnel
    Optional human label, for example the chat or ticket id.
  • api_key · string · optionnel
    Optional. Your Bidda subscription key. Prefer sending it as the x-bidda-api-key header (or Authorization: Bearer), which is what the auth settings in your MCP client configure; the header takes precedence over this argument. A free trial counts.

  Exemple d'appel

  {"name": "open_run", "arguments": {"agent": "texte"}}

  Exemple de retour

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

• oscal_assessment_results≈ 206 tokens

  Export a governed run's evidence as a NIST OSCAL assessment-results document (the machine-readable format GRC and audit tooling consumes): reviewed-controls (the obligation nodes consulted), observations (each pinned to its version + integrity hash), and props recording the independent integrity self-check. A sealed run is readable by id; a still-open run needs your api_key.

  Paramètres, retour & exemple (2)

  Paramètres

  • run_id · string · requis
    The run to export as OSCAL assessment-results.
  • api_key · string · optionnel
    Optional: your Bidda key, required for a still-open (unsealed) run.

  Exemple d'appel

  {"name": "oscal_assessment_results", "arguments": {"run_id": "texte"}}

  Exemple de retour

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

• point_in_time≈ 251 tokens

  Get a signed record of which committed version of a rule was authoritative at a specific past date, anchored to the public history chain. Useful when an agent must show what a rule said at the moment it acted. Requires an active Bidda subscription: pass api_key.

  Paramètres, retour & exemple (3)

  Paramètres

  • as_of · string · optionnel
    ISO date or time, or epoch milliseconds. Defaults to now.
  • api_key · string · optionnel
    Optional. Your Bidda subscription key. Prefer sending it as the x-bidda-api-key header (or Authorization: Bearer), which is what the auth settings in your MCP client configure; the header takes precedence over this argument. A free trial counts.
  • node_id · string · requis
    The rule (node_id).

  Exemple d'appel

  {"name": "point_in_time", "arguments": {"node_id": "texte"}}

  Exemple de retour

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

• record_run_entry≈ 537 tokens

  Append one entry to an open run: which Bidda rules the agent consulted, what it decided, and the end user's input (as text via note, or privately as input_hash). Each entry is hash-chained to the previous one. Requires an active Bidda subscription: pass api_key.

  Paramètres, retour & exemple (12)

  Paramètres

  • note · string · optionnel
    Optional: the end user's message as text.
  • model · string · optionnel
    Optional: the model id/version that produced this decision (e.g. gpt-4o-2024-08-06).
  • nodes · array · optionnel
    Optional node_ids the agent consulted (max 50).
  • action · string · optionnel
    Optional: an action the agent took or checked.
  • run_id · string · requis
    The run_id returned by open_run.
  • api_key · string · optionnel
    Optional. Your Bidda subscription key. Prefer sending it as the x-bidda-api-key header (or Authorization: Bearer), which is what the auth settings in your MCP client configure; the header takes precedence over this argument. A free trial counts.
  • decision · string · optionnel
    Optional: what the agent decided or did this turn.
  • entry_type · string · optionnel
    Optional: node_consulted | action_checked | decision | note. Defaults to note.
  • input_hash · string · optionnel
    Optional: a sha256:... hash of the user's message instead of the text.
  • output_hash · string · optionnel
    Optional: a sha256:... hash of the agent's output.
  • subject_hash · string · optionnel
    Optional: a sha256:... hash of an end-user identifier for per-subject traceability. Hash only, never plaintext.
  • verify_nodes · boolean · optionnel
    Optional: pin each node in "nodes" to its current version + integrity hash (proof, not just a claim). No extra call charge.

  Exemple d'appel

  {"name": "record_run_entry", "arguments": {"run_id": "texte"}}

  Exemple de retour

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

• seal_run≈ 212 tokens

  Seal an open run into one signed Run Receipt covering every entry, with a public verify URL. Idempotent: sealing an already-sealed run returns the same receipt. Requires an active Bidda subscription: pass api_key.

  Paramètres, retour & exemple (2)

  Paramètres

  • run_id · string · requis
    The run_id to seal.
  • api_key · string · optionnel
    Optional. Your Bidda subscription key. Prefer sending it as the x-bidda-api-key header (or Authorization: Bearer), which is what the auth settings in your MCP client configure; the header takes precedence over this argument. A free trial counts.

  Exemple d'appel

  {"name": "seal_run", "arguments": {"run_id": "texte"}}

  Exemple de retour

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

• search_nodes≈ 249 tokens

  Search Bidda compliance nodes by keyword. Returns matching node summaries including a one-sentence BLUF (Bottom Line Up Front): the exact compliance obligation in plain language. Every node traces to a primary legal source (no hallucination). Examples: "Basel III capital", "GDPR data breach", "AML transaction monitoring", "SOC 2 Type II".

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · number · optionnel
    Max results (default 10, max 25)
  • query · string · requis
    Search terms, e.g. "Basel III capital requirements", "GDPR data breach notification 72 hours", "FATF travel rule"
  • pillar · string · optionnel
    Optional: filter by pillar name, e.g. "Banking & Global Finance", "Cybersecurity", "AI Governance & Law", "Medical & Healthcare"

  Exemple d'appel

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

  Exemple de retour

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

• watch_changes≈ 320 tokens

  Subscribe to regulatory change alerts: watch specific rules and/or whole pillars and get notified by email or webhook when their primary source changes. Requires an active Bidda subscription: pass api_key.

  Paramètres, retour & exemple (6)

  Paramètres

  • label · string · optionnel
    Optional name for the alert.
  • nodes · array · optionnel
    node_ids to watch.
  • api_key · string · optionnel
    Optional. Your Bidda subscription key. Prefer sending it as the x-bidda-api-key header (or Authorization: Bearer), which is what the auth settings in your MCP client configure; the header takes precedence over this argument. A free trial counts.
  • pillars · array · optionnel
    Pillar names to watch.
  • channels · object · optionnel
    Delivery channels, for example { "email": true, "webhook": false }. Defaults to email.
  • webhook_url · string · optionnel
    Required if the webhook channel is enabled.

  Exemple d'appel

  {"name": "watch_changes", "arguments": {"label": "texte", "nodes": [], "api_key": "texte", "pillars": [], "channels": {}, "webhook_url": "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://bidda.com/mcp