Agent Passport System — Cryptographic Identity for AI Agents
NPM · AGENT-PASSPORT-SYSTEM-MCP · 2 COMPONENTS
Cryptographic identity, delegation, governance, and commerce for AI agents. 154 tools.
Available components
Last scanned (21 hours ago)
Scores higher than 72% of npm servers
Category Crypto and Web3
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security56
- No malware found by supply-chain analysis.Pass
- Known CVEs could not be checked: the version this server declares is not published in its registry.Unverified
- Declares code that runs automatically (postinstall) and that we could not recognise. It may be perfectly ordinary, but we have not established what it does. View diagnostics → Partial
- Dependency health could not be checked: the version this server declares is not published in its registry.Unverified
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to agent-passport-system/agent-passport-mcp). View diagnostics → Pass
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 0 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability82
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 15534 tokens (~100/item across 154 items; 154 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management99
- Stability check failed: the tool surface changed between 6.1.2 and 8.1.1: 0 tool removals, 3 breaking changes, 2 additions. See how to fix → Fail
Tool Coverage89
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 67% of tool parameters carry a description.Partial
Tool Safety89
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 5 of 9 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "execute_with_context" implies "execute" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Partial
- An AI judge read all 154 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 4 Nov 26 −6
- Known CVEs: fail → unverified ▼ security
- Dependency health: 1.00 → unverified ▼ functional
- Package version: 8.1.0 → 8.1.1 functional
- 2 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 96 to 99.
- 31 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 89 to 92.
- 28 Oct 26 +1
- GHSA-f897-62hf-6gxq affects this package: high ▼ security
- 26 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 72 to 76.
- 24 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 66 to 69.
- 22 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 59 to 62.
- 21 Oct 26 −5
- CVE-2026-111771 affects this package: high ▼ security
- CVE-2026-111770 affects this package: high ▼ security
- CVE-2026-111768 affects this package: high ▼ security
- Known CVEs: pass → fail ▼ security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 4 Nov 2026 · Analysed npm/agent-passport-system-mcp@8.1.1
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | agent-passport-system/agent-passport-mcp |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/agent-passport-system/agent-passport-mcp/.github/workflows/release.yml@refs/tags/v8.1.1 |
| Rekor log index | 3686579620 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:69def867768627dcf389cf0368c711623c8f1ef18f667d7cd8d4321c643d097c3f6e4c13ed9a0e5fc913c5473fd944e4dd52caa11e3eb95e458780896 |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| postinstall | unreviewed | echo '\n🔑 Agent Passport MCP installed! Run: npx agent-passport-system-mcp setup\n Or for zero-install remote: npx agent-passport-system-mcp setup --remote\n' |
Background: Why install scripts are a supply-chain risk →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
accept_assignment Accept Task Assignment ~36
[ANY ROLE] Accept your task assignment. Confirms you're ready to work.
| Name | Type | Req | Description |
|---|---|---|---|
| task_id | string | yes | Task ID to accept |
No output schema declared.
No examples provided.
activate_emergency Activate Emergency Pathway ~58
Activate a pre-authorized emergency pathway with evidence.
| Name | Type | Req | Description |
|---|---|---|---|
| pathway_id | string | yes | – |
| trigger_evidence | string | yes | Evidence that trigger conditions are met |
| trust_epoch | number | – | – |
| valid_until | string | yes | – |
No output schema declared.
No examples provided.
add_approval_signature Add Approval Signature ~60
Add a signature to an approval request.
| Name | Type | Req | Description |
|---|---|---|---|
| key_class | string | – | – |
| office_id | string | – | – |
| request_id | string | yes | – |
| signer_private_key | string | yes | – |
| signer_public_key | string | yes | – |
No output schema declared.
No examples provided.
add_principal_report Add Principal Outcome Report ~58
Add principal's perspective to an outcome record. Enables three-way divergence reporting.
| Name | Type | Req | Description |
|---|---|---|---|
| divergence_score | number | yes | – |
| observed_outcome | string | yes | – |
| outcome_class | string | yes | – |
| outcome_id | string | yes | – |
No output schema declared.
No examples provided.
apply_reputation_downgrade Apply Reputation Downgrade ~95
Apply import policy downgrade to a foreign vouched reputation.
| Name | Type | Req | Description |
|---|---|---|---|
| accept_from | array | yes | Gateway IDs accepted by import policy |
| agent_id | string | yes | – |
| attested_diversity_score | number | yes | – |
| attested_tier | number | yes | – |
| downgrade_ratio | number | – | – |
| foreign_default_tier | number | – | – |
| origin_gateway_id | string | yes | – |
No output schema declared.
No examples provided.
aps_aggregate_settlement Aggregate Settlement Record ~161
Aggregate a batch of Attribution Primitives over a half-open settlement period [t0, t1) into a signed SettlementRecord. Each axis (D, P, G, C) produces a per-contributor total with a balanced-Merkle commitment. Residual buckets pool sub-threshold contributors. Output is a fully signed record ready for third-party verification.
| Name | Type | Req | Description |
|---|---|---|---|
| gateway_did | string | yes | Gateway DID that signs the record |
| gateway_private_key | string | yes | Ed25519 gateway private key (hex) |
| issued_at | string | – | Override issued_at (canonical ISO-8601 UTC ms + Z); defaults to now |
| period | object | yes | – |
| receipts | array | yes | Array of AttributionPrimitives to aggregate |
No output schema declared.
No examples provided.
aps_attribution_receipt_id Compute Attribution Receipt ID ~52
Representation boundary helper: compute the canonical sha256 id of an AttributionReceipt's unsigned core. Verifiers use this to detect id tampering.
| Name | Type | Req | Description |
|---|---|---|---|
| receipt | – | yes | AttributionReceipt JSON (signatures ignored) |
No output schema declared.
No examples provided.
aps_build_contributor_query Build Contributor Query Response ~138
Build a contributor-query response: given a signed SettlementRecord and a contributor DID, return per-axis (total_weight, contribution_count, merkle_path, axis_root) plus the full signed record so a third party can verify the contributor's share end-to-end without trusting the gateway beyond its public key. Returns null if the contributor has no share in the period.
| Name | Type | Req | Description |
|---|---|---|---|
| contributor_did | string | yes | Contributor DID (data source, compute provider, governance signer, or protocol module identifier) |
| gateway_jwks | string | – | Advisory JWKS URL; not part of the signed material |
| record | – | yes | A signed SettlementRecord |
No output schema declared.
No examples provided.
aps_capability_evaluate_authority Build Authority Evaluation Request ~161
v0.1 capability-token authority evaluation request (M2). Subject signs a request carrying the sink's M1, the delegation chain, and a revealed authority-token preimage. The gateway consumes this to decide permit/deny. Search keywords: capability token, authority evaluation, M2.
| Name | Type | Req | Description |
|---|---|---|---|
| authority_token | object | yes | – |
| challenge | – | yes | SinkChallenge object from M1 |
| delegation_chain | array | yes | v2.x delegation envelopes |
| delegation_chain_root | string | – | Override; otherwise computed from chain |
| freshness_beacon | object | yes | – |
| subject_private_key | string | yes | Subject Ed25519 private key (hex) |
| subject_public_key | string | yes | Subject Ed25519 public key (hex) |
No output schema declared.
No examples provided.
aps_capability_issue_challenge Issue Capability Sink Challenge ~166
v0.1 capability-token sink challenge (M1). Sink issues a signed canonical action statement. Returns the SinkChallenge and its challenge_hash. Used to bind the gateway's later policy evaluation to a specific action the sink authored. Search keywords: capability token, sink challenge, M1.
| Name | Type | Req | Description |
|---|---|---|---|
| action | object | yes | Canonical action statement |
| required_policy_freshness | object | – | – |
| sink_id | string | yes | DID of the sink issuing the challenge |
| sink_private_key | string | yes | Sink Ed25519 private key (hex) |
| sink_public_key | string | yes | Sink Ed25519 public key (hex) |
| subject_id | string | yes | DID of the subject the challenge is addressed to |
| validity_seconds | integer | – | – |
No output schema declared.
No examples provided.
aps_capability_mint_receipt Mint Capability Challenge Receipt ~140
v0.1 capability-token gateway receipt (M3). Gateway signs a permit or deny over the sink's exact challenge_hash. Echoes the M2 delegation_chain_root so the sink can verify the gateway saw the same chain the subject committed to. Search keywords: capability token, challenge receipt, gateway receipt, M3.
| Name | Type | Req | Description |
|---|---|---|---|
| decision | string | yes | – |
| deny_reason | string | – | – |
| gateway_private_key | string | yes | – |
| gateway_public_key | string | yes | – |
| policy_digest | string | yes | SHA-256 of the policy bundle used in evaluation |
| request | – | yes | AuthorityEvaluationRequest from M2 |
No output schema declared.
No examples provided.
aps_capability_sign_effect Sign Capability Effect Receipt ~200
v0.1 capability-token sink effect receipt (M4). The sink verifies the gateway's M3, consumes the token preimage (rejecting a replayed nullifier), and signs an EffectReceipt binding the consumed token to the action result the caller supplies. This tool does not execute the action. The (M1, M3, M4) tuple is the full attestation record. Search keywords: capability token, effect receipt, M4, sink attestation.
| Name | Type | Req | Description |
|---|---|---|---|
| challenge | – | yes | Original SinkChallenge from M1 (for binding verification) |
| challenge_receipt | – | yes | ChallengeReceipt from M3 |
| effect | object | yes | – |
| expected_delegation_chain_root | string | – | If omitted, falls back to the receipt's own root |
| gateway_public_key | string | yes | Used to verify M3 before consuming the token |
| sink_private_key | string | yes | – |
| sink_public_key | string | yes | – |
No output schema declared.
No examples provided.
aps_check_artifact_citations Check Artifact Citations ~156
Representation boundary: gate a binding artifact's citations. Each citation must resolve to a provided, signed, unexpired receipt whose content + principal match, with per-artifact replay protection, and each receipt must bind its parties to the keys beside them. What a valid result establishes: every citation is backed by a receipt the cited principal consented to. What it does not establish: authority to act on the artifact. Receipts whose parties are named by identifiers that do not self-certify stop passing this gate.
| Name | Type | Req | Description |
|---|---|---|---|
| artifact | – | yes | CitingArtifact with optional citations[] array |
| binding_context | string | – | Require receipts to be scoped to this binding context |
| receipts | array | yes | AttributionReceipts backing each citation |
No output schema declared.
No examples provided.
aps_check_escalation_required Check Escalation Required ~122
Escalation boundary: check whether an action on a v2 delegation requires owner confirmation before execution. Returns {required, requirement?, reason?}. Use aps_record_owner_confirmation to clear the flag when required.
| Name | Type | Req | Description |
|---|---|---|---|
| action_class | string | yes | Action class (e.g. 'org_creation', 'spend_above_threshold') |
| action_details | – | – | Structured details; hashed for audit |
| delegation | – | yes | V2Delegation with optional scope.escalation_requirements |
| session_id | string | – | Session id (required for per_session scope) |
No output schema declared.
No examples provided.
aps_check_projection_consistency Check Projection Consistency ~96
Cross-projection consistency check: given two projections, confirm they originate from the same signed receipt. Returns {same_receipt: true} or {same_receipt: false, reason: 'DIFFERENT_ACTIONS'|'DIFFERENT_RECEIPTS'|'DIFFERENT_SIGNATURES'|'METADATA_MISMATCH'}.
| Name | Type | Req | Description |
|---|---|---|---|
| projection_a | – | yes | First AttributionProjection |
| projection_b | – | yes | Second AttributionProjection |
No output schema declared.
No examples provided.
aps_compute_attribution_action_ref Compute Attribution Action Ref ~85
Derive the action_ref (hex sha256) for an action tuple. action_ref is the content-addressed anchor that all four axis projections bind to. Useful for indexing primitives by action without constructing the full primitive.
| Name | Type | Req | Description |
|---|---|---|---|
| actionType | string | yes | – |
| agentId | string | yes | – |
| nonce | string | yes | – |
| params | object | yes | – |
No output schema declared.
No examples provided.
aps_compute_compute_axis_weights Compute Compute Axis Weights ~128
Compute the C-axis fractional weight vector from a list of inference billing records (prompt_tokens, completion_tokens). Returns canonical ComputeAxisEntry[] with 6-digit decimal compute_share strings that sum to ~1.0 and feed directly into aps_construct_attribution_primitive. Weights = prompt_tokens + completion_tokens × COMPLETION_MULTIPLIER (default 3.0), then normalized. Parameter names match the SDK: `providers`, optional `profile`.
| Name | Type | Req | Description |
|---|---|---|---|
| profile | – | – | Optional WeightProfile override; defaults to DEFAULT_WEIGHT_PROFILE |
| providers | array | yes | Per-provider billing records |
No output schema declared.
No examples provided.
aps_compute_data_axis_weights Compute Data Axis Weights ~163
Compute the D-axis fractional weight vector from a list of AccessReceipt records with role, timestamp, and content length. Returns canonical DataAxisEntry[] with 6-digit decimal contribution_weight strings that sum to ~1.0 and feed directly into aps_construct_attribution_primitive. Empty input returns an empty array, and all-zero raw weights return an error. Weights = role × recency_decay × length_weight, then normalized. Parameter names match the SDK: `sources`, `action_timestamp`, optional `profile`.
| Name | Type | Req | Description |
|---|---|---|---|
| action_timestamp | string | yes | ISO-8601 UTC ms when the action ran (t_action) |
| profile | – | – | Optional WeightProfile override; defaults to DEFAULT_WEIGHT_PROFILE |
| sources | array | yes | Per-source records with retrieval metadata |
No output schema declared.
No examples provided.
aps_construct_attribution_primitive Construct Attribution Primitive ~159
Build and sign a four-axis AttributionPrimitive for an action. Axes: D (data sources), P (protocol modules), G (delegation chain), C (compute providers). Returns the complete signed object.
| Name | Type | Req | Description |
|---|---|---|---|
| action | object | yes | Action identity tuple; the action_ref is derived as sha256(canonical(this)) |
| axes | object | yes | Four-axis content. See spec §1.2 for entry shapes per axis. |
| issuer | string | yes | Issuer DID (gateway or agent producing the receipt) |
| issuer_private_key | string | yes | Ed25519 private key hex that signs the envelope |
| timestamp | string | – | ISO-8601 UTC with ms precision + Z (§2.5). Defaults to now(). |
No output schema declared.
No examples provided.
aps_create_attribution_receipt Create Attribution Receipt ~309
Representation boundary: build a citer-signed AttributionReceipt attributing a claim to a third-party principal. Each party is named by a self-certifying DID that commits to the key beside it, so a receipt naming a party by a bare public key or by a did:web style identifier will not verify. The receipt is not yet valid: the cited principal must sign consent via aps_sign_attribution_consent before checkArtifactCitations accepts it.
| Name | Type | Req | Description |
|---|---|---|---|
| binding_context | string | yes | ID of the binding artifact this citation is scoped to |
| citation_content | string | yes | The quoted or paraphrased claim |
| cited_principal | string | yes | Self-certifying DID of the cited principal, from the SDK createDID (multibase did:aps). It must commit to cited_principal_public_key. |
| cited_principal_public_key | string | yes | Hex public key of cited principal |
| citer | string | yes | Self-certifying DID of the citing agent, from the SDK createDID (multibase did:aps). A bare public key or the hex did:aps form from createDIDHex does not self-certify and will not verify. |
| citer_private_key | string | yes | Hex private key of citer |
| citer_public_key | string | yes | Hex public key of citer |
| gateway_id | string | – | Gateway id for timestamping (default: 'mcp') |
| ttl_ms | number | – | Receipt TTL in ms (default: 24h) |
No output schema declared.
No examples provided.
aps_create_provisional Create Provisional Statement ~156
Commitment boundary: emit a provisional statement for agent-to-agent negotiation. Default is non-binding until a PromotionEvent satisfies a PromotionPolicy. Dead-man expiry auto-withdraws.
| Name | Type | Req | Description |
|---|---|---|---|
| author | string | yes | AgentDID/public key of the emitting agent |
| author_principal | string | yes | PrincipalDID behind the author |
| author_private_key | string | yes | Hex private key of author for signing |
| content | string | yes | Statement content (offer, position, claim) |
| dead_man_ms | number | – | Dead-man expiry relative to now (ms). If elapsed without promotion/withdrawal, statement auto-withdraws. |
| gateway_id | string | – | Gateway id for timestamping (default: 'mcp') |
No output schema declared.
No examples provided.
aps_project_attribution Project Attribution Axis ~92
Extract a single-axis projection from an AttributionPrimitive. The projection carries the axis content plus a two-hop Merkle path that lets a downstream verifier reconstruct the signed root without seeing the other three axes. axis: 'D' | 'P' | 'G' | 'C'.
| Name | Type | Req | Description |
|---|---|---|---|
| axis | string | yes | Axis to project |
| primitive | – | yes | An AttributionPrimitive (from aps_construct_attribution_primitive) |
No output schema declared.
No examples provided.
aps_promote_statement Promote Provisional Statement ~109
Commitment boundary: promote a provisional statement to binding by attaching a PromotionEvent that satisfies the PromotionPolicy (m-of-n principal signatures). dead_man_elapsed cannot promote, because the dead-man path auto-withdraws the statement.
| Name | Type | Req | Description |
|---|---|---|---|
| policy | – | yes | PromotionPolicy {id, required_signers, threshold, max_time_to_promote} |
| promotion_event | – | yes | PromotionEvent with kind, promoted_at, promoter, promoter_signature, policy_reference |
| statement | – | yes | ProvisionalStatement from aps_create_provisional |
No output schema declared.
No examples provided.
aps_record_owner_confirmation Record Owner Confirmation ~140
Escalation boundary: owner signs an OwnerConfirmation authorizing a flagged action. Builds the ConfirmationRequest and signs it in a single call. The confirmation is bound to action_details via hash and scoped (per_action / per_session / time_window).
| Name | Type | Req | Description |
|---|---|---|---|
| action_class | string | yes | Action class being confirmed |
| action_details | – | yes | Structured action details — hashed and bound to the confirmation |
| delegation | – | yes | V2Delegation with escalation_requirements for this action class |
| owner_private_key | string | yes | Hex private key of the delegation's owner (delegator) |
| session_id | string | – | Session id (required for per_session scope) |
No output schema declared.
No examples provided.
aps_sign_attribution_consent Sign Attribution Consent ~103
Representation boundary: the cited principal adds their consent signature to an AttributionReceipt. Without this signature, verifyAttributionConsent and checkArtifactCitations reject the receipt. The signature is checked against the key the receipt carries for that party, and that key must be the one the party DID commits to.
| Name | Type | Req | Description |
|---|---|---|---|
| cited_principal_private_key | string | yes | Hex private key of cited principal |
| receipt | – | yes | AttributionReceipt JSON from aps_create_attribution_receipt |
No output schema declared.
No examples provided.
aps_verify_attribution_consent Verify Attribution Consent ~143
Representation boundary: verify an AttributionReceipt end-to-end (id, citer signature, consent signature, expiry) and bind each named party to the key beside it. What a valid result establishes: the receipt is intact, unexpired, and signed by the keys its party DIDs commit to. What it does not establish: that either party is authorized for your relying-party decision, or who they are outside the protocol. A party named by an identifier that does not self-certify is refused as unresolved rather than assumed. Returns {valid, reason?}.
| Name | Type | Req | Description |
|---|---|---|---|
| now | – | – | Optional HybridTimestamp to pin the evaluation moment |
| receipt | – | yes | AttributionReceipt JSON |
No output schema declared.
No examples provided.
aps_verify_attribution_primitive Verify Attribution Primitive ~76
End-to-end verify of a full AttributionPrimitive: constructs projections for all four axes and verifies each one. Useful as a post-construction sanity check or for verifying a primitive received from a peer.
| Name | Type | Req | Description |
|---|---|---|---|
| issuer_public_key | string | yes | Issuer Ed25519 public key hex |
| primitive | – | yes | An AttributionPrimitive |
No output schema declared.
No examples provided.
aps_verify_attribution_projection Verify Attribution Projection ~107
Verify a single-axis AttributionProjection under the issuer's Ed25519 public key. Returns {valid: true} or {valid: false, reason: 'INVALID_AXIS_TAG'|'MERKLE_MISMATCH'|'SIGNATURE_INVALID'|'MALFORMED'}. Verification is purely local and needs no other axes.
| Name | Type | Req | Description |
|---|---|---|---|
| issuer_public_key | string | yes | Issuer Ed25519 public key hex |
| projection | – | yes | An AttributionProjection (from aps_project_attribution) |
No output schema declared.
No examples provided.
aps_verify_promotion Verify Statement Promotion ~75
Commitment boundary: verify that a promoted statement's PromotionEvent cryptographically satisfies the PromotionPolicy (policy_reference match, promoter in required_signers, threshold, signature, max_time_to_promote, author-signature tamper check).
| Name | Type | Req | Description |
|---|---|---|---|
| policy | – | yes | PromotionPolicy to check against |
| statement | – | yes | Promoted ProvisionalStatement |
No output schema declared.
No examples provided.
aps_verify_settlement Verify Settlement Record ~154
Verify a signed SettlementRecord under S1-S5 (signature, Merkle roots, conservation, residual shape, optional input-receipts cross-check). S3 conservation is the strongest invariant: a gateway cannot inflate or suppress any contributor's share without breaking it. Returns {valid: true} or {valid: false, reason, detail}. Pass inputReceipts to also recompute input_receipts_hash.
| Name | Type | Req | Description |
|---|---|---|---|
| gateway_public_key | string | yes | Gateway Ed25519 public key hex |
| input_receipts | array | – | Optional — the input Attribution Primitives that fed the settlement. When supplied, S5 cross-checks input_receipts_hash and verifies each receipt individually. |
| record | – | yes | A signed SettlementRecord |
No output schema declared.
No examples provided.
aps_withdraw_provisional Withdraw Provisional Statement ~110
Commitment boundary: author withdraws their own provisional statement. Already-promoted statements cannot be withdrawn. Caller must supply the author's signature over the withdrawal payload (canonicalize({action:'withdraw', statement_id})).
| Name | Type | Req | Description |
|---|---|---|---|
| author_private_key | string | – | If provided, tool signs the withdrawal payload with this key. |
| author_signature | string | – | Hex Ed25519 signature. If omitted, provide author_private_key and the tool will sign for you. |
| statement | – | yes | ProvisionalStatement to withdraw |
No output schema declared.
No examples provided.
assign_agent Assign Agent to Task Role ~93
[OPERATOR] Assign an agent to a role in a task. Creates a delegation automatically.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | Agent ID |
| agent_public_key | string | yes | Agent's Ed25519 public key |
| role | string | yes | Role to assign |
| scope | array | yes | Delegation scopes |
| spend_limit | number | – | Max spend |
| task_id | string | yes | Task ID |
No output schema declared.
No examples provided.
attest_to_floor Attest to Values Floor ~48
Attest that your agent agrees to abide by the loaded Values Floor.
| Name | Type | Req | Description |
|---|---|---|---|
| extensions | array | – | Optional additional extensions |
| floor_version | string | yes | Version of the floor to attest to |
No output schema declared.
No examples provided.
broadcast Broadcast Agent Message ~79
Send a signed message to all agents via comms/broadcast.json.
| Name | Type | Req | Description |
|---|---|---|---|
| data | object | – | Structured data payload |
| message | string | yes | Message body |
| priority | string | – | Priority: low, normal, high, critical |
| subject | string | yes | Message subject |
| type | string | – | Message type (default: 'broadcast') |
No output schema declared.
No examples provided.
check_aggregate_constraints Check Aggregate Constraints ~100
Check if a data access would violate aggregate rate limits.
| Name | Type | Req | Description |
|---|---|---|---|
| agentId | string | yes | – |
| burstLimit | number | – | – |
| currentAccessCount | number | yes | – |
| currentRecordCount | number | yes | – |
| lastAccessMs | number | yes | – |
| maxAccessesPerWindow | number | – | – |
| sourceId | string | yes | – |
| windowMs | number | – | – |
| windowStartMs | number | yes | – |
No output schema declared.
No examples provided.
check_authority_delegation Check Authority Delegation ~152
Verify a root AuthorityDelegationV1 issued by this server's key, with the SDK chain verifier: shape, delegation_id, signature, time window and revocation status from this process's in-memory revocation store. Returns the verifier's state (valid, invalid, indeterminate or unsupported) and its failure codes, for example REVOKED or EXPIRED. A delegation this server did not issue, including one signed by this key under another issuer name, resolves no key and is not valid here. A delegation issued before a restart has revocation status unknown, because the store is in memory.
| Name | Type | Req | Description |
|---|---|---|---|
| delegation | – | yes | The AuthorityDelegationV1 to check, as a JSON string or object. |
No output schema declared.
No examples provided.
check_combination_permitted Check Data Combination Permitted ~89
Check if combining data from two sources is permitted. Prevents prohibited inferences (HIPAA, COPPA, GDPR Art 9).
| Name | Type | Req | Description |
|---|---|---|---|
| forbiddenSourceClasses | array | – | – |
| forbiddenSourceIds | array | – | – |
| otherSourceClasses | array | – | – |
| otherSourceId | string | yes | – |
| reason | string | yes | – |
| regulatoryBasis | string | – | – |
No output schema declared.
No examples provided.
check_jurisdiction_transfer Check Jurisdiction Transfer ~98
Check if a data transfer is permitted under jurisdiction constraints (EU_ONLY, GDPR_ADEQUATE_ONLY, NO_CROSS_BORDER).
| Name | Type | Req | Description |
|---|---|---|---|
| processingRestrictions | array | – | – |
| purpose | string | yes | – |
| sourceJurisdiction | string | yes | ISO 3166-1 alpha-2 code |
| targetJurisdiction | string | yes | ISO 3166-1 alpha-2 code |
| transferConstraints | array | – | – |
No output schema declared.
No examples provided.
check_messages Check Agent Messages ~61
Check messages addressed to you. Reads from comms/to-{your-agent-name}.json.
| Name | Type | Req | Description |
|---|---|---|---|
| mark_read | boolean | – | Mark returned messages as processed (default: false) |
| unprocessed_only | boolean | – | Only show unprocessed messages (default: true) |
No output schema declared.
No examples provided.
check_purpose_permitted Check Purpose Permitted ~68
Check if a purpose is permitted under source terms. Supports wildcards (research:*) and hierarchical matching.
| Name | Type | Req | Description |
|---|---|---|---|
| allowedPurposes | array | yes | Purposes allowed by the source terms |
| purpose | string | yes | Purpose to check (e.g. research:academic, training:model) |
No output schema declared.
No examples provided.
check_retention_expired Check Retention Expired ~64
Check if data retention has expired based on TTL policy.
| Name | Type | Req | Description |
|---|---|---|---|
| accessType | string | – | – |
| accessedAt | string | yes | ISO timestamp of when data was accessed |
| maxRetentionMs | number|null | yes | Max retention in ms (null = no limit) |
No output schema declared.
No examples provided.
check_tier Check Tier Permits Action ~110
Check if an agent's earned tier permits an action at a given autonomy level and spend amount. Returns null if permitted, or escalation details if tier is insufficient.
| Name | Type | Req | Description |
|---|---|---|---|
| agentId | string | yes | Agent ID |
| principalId | string | yes | Principal ID |
| requestedAutonomy | number | – | Requested autonomy level (1-5) |
| requestedDepth | number | – | Requested delegation depth |
| requestedSpend | number | – | Requested spend amount in dollars |
| scope | string | yes | Reputation scope |
No output schema declared.
No examples provided.
check_usage_permitted Check Usage Permitted ~43
Check if a specific usage type is permitted under a governance block's terms.
| Name | Type | Req | Description |
|---|---|---|---|
| block | string | yes | Governance block JSON string |
| usage | string | yes | – |
No output schema declared.
No examples provided.
classify_evidence_quality Classify Evidence Quality ~90
Classify attestation evidence quality (none / issuer_vouched / infrastructure / principal_bound) and return the corresponding grade (0-3).
| Name | Type | Req | Description |
|---|---|---|---|
| evidence | object | – | Evidence object (checked for known infrastructure keys) |
| has_issuer_signature | boolean | – | – |
| has_principal_binding | boolean | – | – |
| method | string | – | Attestation method (e.g. 'spiffe') |
No output schema declared.
No examples provided.
commerce_preflight Commerce Preflight (Moved to Gateway) ~139
[moved to gateway in SDK 3.3.0] The 6-gate commerce preflight orchestration moved out of the SDK and MCP into the AEOESS gateway. This tool no longer runs the pipeline locally. It returns a machine-readable deprecation notice pointing to the gateway commerce endpoint. Compose the pure gate predicates from the SDK yourself, or call the gateway.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | Agent making the purchase |
| amount | number | yes | Purchase amount |
| currency | string | – | Currency code |
| delegation_id | string | yes | Commerce delegation ID |
| merchant_name | string | yes | Merchant to purchase from |
No output schema declared.
No examples provided.
compare_timestamps Compare Hybrid Timestamps ~31
Compare two hybrid timestamps to determine ordering.
| Name | Type | Req | Description |
|---|---|---|---|
| a | object | yes | – |
| b | object | yes | – |
No output schema declared.
No examples provided.
complete_action Complete Action (Deprecated) ~82
[deprecated in v3.0.0, use the gateway.aeoess.com REST API] Complete a permitted action and get the full 3-signature proof chain.
| Name | Type | Req | Description |
|---|---|---|---|
| intent_id | string | yes | Intent ID from execute_with_context result |
| status | string | yes | Outcome of the action |
| summary | string | yes | Brief description of what was accomplished |
No output schema declared.
No examples provided.
complete_task Complete Task ~63
[OPERATOR] Close the task unit with final status and retrospective. A later call replaces the stored completion record.
| Name | Type | Req | Description |
|---|---|---|---|
| retrospective | string | – | What went well, what didn't |
| status | string | yes | Final status |
| task_id | string | yes | Task ID |
No output schema declared.
No examples provided.
compute_action_ref Compute Action Reference ~112
Compute content-addressed request identity (SHA-256 of agentId + actionType + scope + normalized timestamp). Two receipts with the same action_ref describe the same request.
| Name | Type | Req | Description |
|---|---|---|---|
| action_type | string | yes | – |
| agent_id | string | yes | – |
| scope_required | array | yes | – |
| timestamp | string | – | RFC 3339 timestamp carrying an explicit offset or Z; defaults to now. A zone-less value is refused, because it names no instant and would produce a different action_ref on every machine. |
No output schema declared.
No examples provided.
compute_governance_taint Compute Governance Taint ~52
Compute governance taint level for an artifact based on its derivation chain and revoked sources.
| Name | Type | Req | Description |
|---|---|---|---|
| artifactId | string | yes | – |
| revokedSources | array | – | Source IDs that have been revoked |
No output schema declared.
No examples provided.
How do I install the Agent Passport System — Cryptographic Identity for AI Agents MCP server?
Agent Passport System — Cryptographic Identity for AI Agents runs locally as an npm package, launched with npx -y agent-passport-system-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · agent-passport-system-mcp
claude mcp add agent-passport-system-agent-passport-mcp -- npx -y agent-passport-system-mcp
What is the Agent Passport System — Cryptographic Identity for AI Agents MCP server?
Agent Passport System — Cryptographic Identity for AI Agents is an MCP server listed in the public MCP registry as io.github.agent-passport-system/agent-passport-mcp. Cryptographic identity, delegation, governance, and commerce for AI agents. 154 tools. This page covers its npm package (agent-passport-system-mcp).
Is the Agent Passport System — Cryptographic Identity for AI Agents MCP server safe to use?
Agent Passport System — Cryptographic Identity for AI Agents scores 82 out of 100 on VerifyMCP. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Agent Passport System — Cryptographic Identity for AI Agents MCP server expose?
Agent Passport System — Cryptographic Identity for AI Agents exposes 154 tools: list_profiles, list_tools_for_scope, identify, generate_keys, issue_passport, and 149 more. Their descriptions and schemas cost roughly 15,534 tokens of context every time the server is loaded.
Is the Agent Passport System — Cryptographic Identity for AI Agents MCP server still maintained?
Agent Passport System — Cryptographic Identity for AI Agents is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Agent Passport System — Cryptographic Identity for AI Agents MCP server under?
Agent Passport System — Cryptographic Identity for AI Agents declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.