# Trust Gate

> Post-quantum, tamper-evident receipts for agent actions. Ed25519 + ML-DSA-65, offline verify.

- name: io.github.CWNApps/trust-gate-mcp
- version: 0.2.0
- connection class: R0 (autonomous)
- trust: 90/100
- quality: 63/100 (needs work)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.CWNApps%2Ftrust-gate-mcp
- tools: https://api.protogrid.dev/v1/servers/io.github.CWNApps%2Ftrust-gate-mcp/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "trust-gate-mcp": {
      "type": "http",
      "url": "https://trust-gate-mcp.onrender.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 65
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-100% ~updated-117d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 63/100 (needs work)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: audit_my_agent_inventory (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); verify_receipt (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); mint_receipt_for_record_change (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 1,493 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 25 (weight 15)

- warn `stability.changes`: 7 tool changes in 30 days
- fail `stability.rug_pull`: 2 tools kept their name but changed most of their description in 30 days; review before trusting them

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 7, about 1,493 tokens to load them all
- tool set hash: cb2ff71139cbb343fae35c100dbf7214
- tools last changed: 2026-10-02T09:56:17.513Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.CWNApps/trust-gate-mcp.svg)](https://protogrid.dev/servers/io.github.CWNApps/trust-gate-mcp)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-02 `run_exit_drill` added
  - Vendor exit readiness drill. Checks local signing key, local model access (Ollama). Returns step-by-step results and a tamper-evident receipt. Informational; it signs one receipt, which creates the signing key on a host that has none yet.
- 2026-10-02 `check_egress` added
  - Egress classification check. Scans a data sample for a finite list of sensitivity markers and classifies as NO_MARKERS_FOUND / INTERNAL / CONFIDENTIAL / RESTRICTED. RESTRICTED sets blocked=true; this tool cannot block anything itself, and NO_MARKERS_FOUND is not clearance to send. Returns classification, retention info, and a tamper-evident receipt.
- 2026-10-02 `gate_decision` added
  - Two-phase decision gate with a real verdict. PREVIEW returns ALLOW, DENY or ESCALATE with the risk tier and reasons, plus a preview_id, without acting. COMMIT re-evaluates the same inputs and mints a signed receipt for the verdict. Only ALLOW returns a GRANTED permit; DENY returns DENIED; ESCALATE returns WITHHELD_PENDING_HUMAN and a human must decide outside this tool. Applies only to actions the caller routes through it: it does not observe or block what an agent does. Verb-tier heuristic on the action name and resource, not a proof. Stateless. Optional attestation: triggered_by_type, triggered_by_source, decision_model.
- 2026-10-02 `verify_receipt` changed (description, inputSchema) **meaning changed**
  - before: Verify a Trust Gate receipt from the certificate alone (offline). require_pq=True (default via OAO_REQUIRE_PQ) FAILS if the ML-DSA-65 or SLH-DSA legs are missing -- defends against signature-stripping downgrade attacks.
  - after: Verify a Trust Gate receipt from the certificate alone (offline). ok=true means unchanged since signing, signed, kid consistent with the embedded key, and (require_pq default on) at least one post-quantum leg verified; unsigned receipts fail. It does not prove who signed: pass expected_kid to pin the signer's Ed25519 key; a pin counts only when that key's own signature verifies (see signer_pinned). The post-quantum keys in a receipt are not covered by the kid.
- 2026-10-02 `mint_action_receipt` changed (description, inputSchema) **meaning changed**
  - before: Mint a post-quantum receipt for an arbitrary consequential agent action.
  - after: Mint a signed receipt (Ed25519, plus ML-DSA-65 when the post-quantum backend is available) for an arbitrary consequential agent action. Optional attestation: triggered_by_type (human/agent/script), triggered_by_source (api/cli/cron), decision_model (the LLM model used). Attestation values are caller claims: allowlisted to safe characters, signed, not verified. Decisions that contain a gate verdict word are reserved for gate_decision.
- 2026-10-02 `audit_my_agent_inventory` changed (description)
  - before: Rank a CALLER-PROVIDED list of MCP tools by worst-regret if they act, with a signed receipt. Cannot auto-discover the inventory -- MCP does not allow that; the caller must pass it in.
  - after: Rank a CALLER-PROVIDED list of MCP tools by worst-regret if they act (a name-based heuristic that weights a name's first word most). Read-only: it mints no receipt. Cannot auto-discover the inventory -- MCP does not allow that; the caller must pass it in.
- 2026-10-02 `mint_receipt_for_record_change` changed (description)
  - before: Mint a post-quantum receipt for one CRM record change. Old/new values are carried as SHA-256 hashes. Works with any CRM (Relaticle, hosted CRMs, custom).
  - after: Mint a signed receipt (Ed25519, plus ML-DSA-65 when the post-quantum backend is available) for one CRM record change. Old/new values are carried as SHA-256 hashes. Works with any CRM (Relaticle, hosted CRMs, custom).

Full history: https://api.protogrid.dev/v1/servers/io.github.CWNApps%2Ftrust-gate-mcp/changes

## Remotes

- https://trust-gate-mcp.onrender.com/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (7)

- `audit_my_agent_inventory`: Rank a CALLER-PROVIDED list of MCP tools by worst-regret if they act (a name-based heuristic that weights a name's first word most). Read-only: it mints no receipt. Cannot auto-discover the inventory -- MCP does not allow that; the caller must pass it in.
- `check_egress`: Egress classification check. Scans a data sample for a finite list of sensitivity markers and classifies as NO_MARKERS_FOUND / INTERNAL / CONFIDENTIAL / RESTRICTED. RESTRICTED sets blocked=true; this tool cannot block anything itself, and NO_MARKERS_FOUND is not clearance to send. Returns classification, retention info, and a tamper-evident receipt.
- `gate_decision`: Two-phase decision gate with a real verdict. PREVIEW returns ALLOW, DENY or ESCALATE with the risk tier and reasons, plus a preview_id, without acting. COMMIT re-evaluates the same inputs and mints a signed receipt for the verdict. Only ALLOW returns a GRANTED permit; DENY returns DENIED; ESCALATE returns WITHHELD_PENDING_HUMAN and a human must decide outside this tool. Applies only to actions the caller routes through it: it does not observe or block what an agent does. Verb-tier heuristic on the action name and resource, not a proof. Stateless. Optional attestation: triggered_by_type, triggered_by_source, decision_model.
- `mint_action_receipt`: Mint a signed receipt (Ed25519, plus ML-DSA-65 when the post-quantum backend is available) for an arbitrary consequential agent action. Optional attestation: triggered_by_type (human/agent/script), triggered_by_source (api/cli/cron), decision_model (the LLM model used). Attestation values are caller claims: allowlisted to safe characters, signed, not verified. Decisions that contain a gate verdict word are reserved for gate_decision.
- `mint_receipt_for_record_change`: Mint a signed receipt (Ed25519, plus ML-DSA-65 when the post-quantum backend is available) for one CRM record change. Old/new values are carried as SHA-256 hashes. Works with any CRM (Relaticle, hosted CRMs, custom).
- `run_exit_drill`: Vendor exit readiness drill. Checks local signing key, local model access (Ollama). Returns step-by-step results and a tamper-evident receipt. Informational; it signs one receipt, which creates the signing key on a host that has none yet.
- `verify_receipt`: Verify a Trust Gate receipt from the certificate alone (offline). ok=true means unchanged since signing, signed, kid consistent with the embedded key, and (require_pq default on) at least one post-quantum leg verified; unsigned receipts fail. It does not prove who signed: pass expected_kid to pin the signer's Ed25519 key; a pin counts only when that key's own signature verifies (see signer_pinned). The post-quantum keys in a receipt are not covered by the kid.