# Odile Gate Oversight (remote · gate.odilelabs.com)

Watch Odile Gate: runs, held actions, audit log with signed export, metrics and refusal reasons.

- Trust score: 69/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `gate.odilelabs.com`: 69/100 (this document), [markdown](https://verifymcp.io/servers/com-odilelabs-gate-oversight/mcp-oversight.md), [page](https://verifymcp.io/servers/com-odilelabs-gate-oversight/mcp-oversight)

## Channel facts

- Endpoint: `https://gate.odilelabs.com/mcp/oversight`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 66/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (gate_revoke_run).
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 64/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2921 tokens (~194/item across 15 items; 15 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 97/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 91% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Odile Gate Oversight MCP server?

Odile Gate Oversight is a hosted endpoint at https://gate.odilelabs.com/mcp/oversight, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-odilelabs-gate-oversight 'https://gate.odilelabs.com/mcp/oversight'
```

### Cursor

```json
{
  "mcpServers": {
    "com-odilelabs-gate-oversight": {
      "url": "https://gate.odilelabs.com/mcp/oversight"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-odilelabs-gate-oversight": {
      "type": "http",
      "url": "https://gate.odilelabs.com/mcp/oversight"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-odilelabs-gate-oversight]
url = "https://gate.odilelabs.com/mcp/oversight"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-odilelabs-gate-oversight": {
      "type": "remote",
      "url": "https://gate.odilelabs.com/mcp/oversight",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-odilelabs-gate-oversight --url 'https://gate.odilelabs.com/mcp/oversight' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-odilelabs-gate-oversight:
    url: "https://gate.odilelabs.com/mcp/oversight"
```

### Netclaw

```json
{
  "McpServers": {
    "com-odilelabs-gate-oversight": {
      "Transport": "http",
      "Url": "https://gate.odilelabs.com/mcp/oversight"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-odilelabs-gate-oversight -t streamable-http -u 'https://gate.odilelabs.com/mcp/oversight'
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-21 (score 69, +1)

- [security] Tool “gate_export_audit_proof” rewrote its description, which is the text the model reads
- [security] Tool “gate_learn_suggestions” rewrote its description, which is the text the model reads
- [security] Tool “gate_list_actions” rewrote its description, which is the text the model reads
- [security] Tool “gate_export_audit_proof” is now declared destructive
- [security] Tool “gate_learn_suggestions” is now declared destructive
- [security] Tool “gate_list_actions” is now declared destructive

### 2026-11-18 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-16 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-15 (score 66, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-14 (score 66)

First indexed and scored.

## MCP tools (15)

### `gate_list_apps` (~109 tokens)

List apps

Read the project's apps, allowed calls, limits, state, idle flags and anomaly-guard settings. Use it to select an app id. Create or revoke apps on the setup endpoint, /mcp/setup.

Input parameters:

- `admin_key` (string, required): The project admin key (ga_...). Read it from the .env; never print it.
- `project_id` (string, required): The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3...

### `gate_list_approvers` (~143 tokens)

List approver keys

Approvers are people who decide held actions. List active and revoked dedicated approvers with ids, names and creation times; never returns keys or hashes. Team members with the approver role are a separate list. Requires the project owner key or an active member key. Create or revoke dedicated keys and inspect team roles on the setup endpoint, /mcp/setup.

Input parameters:

- `admin_key` (string, required): The project owner key (ga_...) or an active member key (gm_...). Never print it.
- `project_id` (string, required): The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3...

### `gate_create_run` (~350 tokens)

Grant one agent run

Gate Actions: give one agent session narrow, expiring permission. Actions are rules with {placeholders} bound by scope (e.g. "PATCH /customers/{customer}/tickets/:id" with scope {"customer":"A"}), each with an optional max and approval. Check gate_list_approvers for an active human approver before granting approval:true actions; create one on the setup endpoint, /mcp/setup if needed; without an active approver the grant is refused. Returns a run token (shown once) the agent sends as x-odile-run with its app key. Writes in a run need an Idempotency-Key. Give a write a check ("GET /bookings?idempotency_key={key}") and the agent can settle a lost answer with POST /g/<id>/_gate/recover.

Input parameters:

- `actions` (array, required): Rules, or {rule, max, approval, check}
- `admin_key` (string, required): The project admin key (ga_...). Read it from the .env; never print it.
- `app` (string, required): The app id (app_...) this run is for
- `label` (string): Optional: what the run is for, e.g. "triage ticket 4411"
- `max_calls` (integer): Optional: calls allowed in the whole run
- `project_id` (string, required): The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3...
- `scope` (object): Values for the {placeholders}, e.g. {"customer":"A"}
- `ttl_seconds` (integer): How long the run lasts (default 3600)

### `gate_delegate_run` (~162 tokens)

Delegate a narrower run

Hand a narrower run to another active app in the same project. Uses the parent app key and run token, never the admin key. Scope, expiry, approvals and ancestor budgets stay enforced; maximum depth five.

Input parameters:

- `actions` (array, required)
- `app` (string, required): The destination app id
- `app_key` (string, required): The parent app key (gk_...)
- `label` (string): A short label for the delegated job
- `max_calls` (integer)
- `project_id` (string, required): The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3...
- `run_token` (string, required): The parent run token (gr_...)
- `ttl_seconds` (integer)

### `gate_revoke_run` (~140 tokens)

End an agent run

End one run granted with gate_create_run: its token stops working at once (403 run_revoked) while the app itself keeps working. Use it to stop an agent mid-job; grant a new run with gate_create_run if the work should continue.

Input parameters:

- `admin_key` (string, required): The project admin key (ga_...). Read it from the .env; never print it.
- `project_id` (string, required): The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3...
- `run_id` (string, required): The run id: run.run_id in gate_create_run's result

### `gate_list_actions` (~162 tokens)

List held actions

Which actions are waiting for a human decision? Read held actions (pending by default, or another requested state) and their exact calls; this tool cannot decide or resubmit them. This also expires overdue held actions in the project and clears their stored request paths and bodies. Approving or rejecting a held action is done by a person with an approver key in the dashboard, by design. No MCP tool can approve actions.

Input parameters:

- `admin_key` (string, required): The project admin key (ga_...). Read it from the .env; never print it.
- `project_id` (string, required): The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3...
- `state` (string): Default: pending

### `gate_read_audit` (~233 tokens)

Read the audit log

Which gateway calls happened recently? Returns recent gateway calls (time, app, matched route, status, reason, duration); use it to investigate individual calls across the project rather than gate_get_metrics aggregates or a single gate_get_run_timeline. Newest first, with totals by status and refusal reason for the returned calls. This view never returns bodies, query values or headers. For 24-hour totals and anomaly scores use gate_get_metrics; for a signed export an auditor can check, gate_export_audit_proof; for one run's history, gate_get_run_timeline.

Input parameters:

- `admin_key` (string, required): The project admin key (ga_...). Read it from the .env; never print it.
- `app` (string): Optional: only this app id (app_...)
- `limit` (integer): How many calls (default 20)
- `project_id` (string, required): The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3...
- `status` (string): Optional: only this HTTP status, e.g. "403"

### `gate_export_audit_proof` (~249 tokens)

Export a signed audit proof

Which signed audit records can I export for verification? Returns chained audit rows, decided-action feature snapshots and signed anchors; use it for a portable tamper-evident export instead of gate_read_audit's recent-call view, then check it with gate_verify_audit_proof. No sealed paths/bodies, notes, keys or IPs in the action labels. Legacy actions lack snapshots and are excluded. store_audit=false has no chain. Follow next_from for audit rows and next_actions_after as actions_after for labels (10,000 each). Use API/SDK to verify exports above the MCP request size limit. The signature is HMAC-SHA256. This also expires overdue held actions in the project and clears their stored request paths and bodies.

Input parameters:

- `actions_after` (string): Action cursor from next_actions_after
- `admin_key` (string, required): The project admin key (ga_...). Read it from the .env; never print it.
- `from` (integer)
- `project_id` (string, required): The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3...
- `to` (integer)

### `gate_verify_audit_proof` (~150 tokens)

Verify a signed audit export

Is this signed audit export intact? Returns intact or broken_at for a supplied signed export; use it to check a gate_export_audit_proof export rather than retrieve audit rows. Recomputes the chain and project signature; broken_at is a one-based row position. Does not approve actions or change permissions.

Input parameters:

- `admin_key` (string, required): The project admin key (ga_...). Read it from the .env; never print it.
- `project_id` (string, required): The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3...
- `proof` (object, required): The full signed export from gate_export_audit_proof

### `gate_get_metrics` (~279 tokens)

Read Gate operational metrics

What are the project call trends and current usage? Returns project-wide 24-hour call aggregates, anomaly scores, idle apps and current-month usage; use it for operational trends rather than individual calls in gate_read_audit or one run in gate_get_run_timeline. Includes stored call counts by HTTP status and reason, measured duration through response headers (including upstream wait), per-app anomaly scores and 24-hour anomaly counts, idle apps (active apps whose key made no allowed call in the project's idle_days, default 14; a flag only, never a revoke), and separate current-month gateway usage: plan, used, allowed, plus upgrade URL and checkout path on Free at 80% or above. Only POST the checkout path when the admin asks to upgrade; reading metrics never starts checkout. Requires the project owner key or an active member key. Audit may be partial: invalid-key sampling and audit-off periods are disclosed. No upstream requests, quota use or policy changes; not a health certificate or performance guarantee. For individual calls use gate_read_audit.

Input parameters:

- `admin_key` (string, required): The project admin key (ga_...). Read it from the .env; never print it.
- `project_id` (string, required): The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3...

### `gate_get_run_timeline` (~169 tokens)

Read run timeline

What happened during this run? Returns one run's call metadata, approvals and approver names, recovery outcomes and delegated children; use it to reconstruct that session instead of gate_read_audit's project-wide calls or gate_get_run_tree's permission state. No bodies or query values. One run only; the project-wide log is gate_read_audit.

Input parameters:

- `admin_key` (string, required): The project admin key (ga_...). Read it from the .env; never print it.
- `before` (integer): Older audit events (timeline pages have at most 500 events)
- `project_id` (string, required): The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3...
- `run_id` (string, required): The run id

### `gate_get_run_tree` (~130 tokens)

Read run tree

Which permissions and delegated descendants does this run have? Returns one run and its delegated descendants without tokens; use it to inspect delegation and permission state instead of gate_get_run_timeline events. One run only; the project-wide log is gate_read_audit.

Input parameters:

- `admin_key` (string, required): The project admin key (ga_...). Read it from the .env; never print it.
- `project_id` (string, required): The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3...
- `run_id` (string, required): The run id

### `gate_explain_refusal` (~70 tokens)

Explain a refused call

What a Gate refusal means and how to fix it, from the x-gate-refused header value (e.g. route_not_allowed).

Input parameters:

- `reason` (string, required): The x-gate-refused value
- `recoverable` (boolean): Whether the write was granted with a recovery check

### `gate_learn_suggestions` (~148 tokens)

Read learning suggestions

Read normalized routes and a suggested per-minute limit from an admin-enabled, time-boxed learning session. Records only method, normalized path templates and counts per minute; no query values, raw ids, headers or bodies. Never enables learning or applies rules. This also deletes learning sessions, route templates and minute counts past their retention deadline across the project.

Input parameters:

- `admin_key` (string, required): The project admin key (ga_...). Read it from the .env; never print it.
- `app` (string, required): The app id
- `project_id` (string, required): The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3...

### `gate_update_app` (~238 tokens)

Apply learned app routes and rate limit

Apply stored learning suggestions to an existing app and return the applied routes, suggested per-minute limit and learning-session metadata. Review gate_learn_suggestions first, then explicitly confirm; requires the project owner key or an admin member key. mode="extend" adds learned routes (default); "replace" removes existing routes before applying them. Both modes set the learned rate limit and keep the app key. Only learned suggestions can be applied: arbitrary routes or rate limits are not accepted, and this tool never starts learning.

Input parameters:

- `admin_key` (string, required): The project owner key (ga_...) or an accepted admin member key (gm_...). Read it from the .env; never print it.
- `app` (string, required): The app id (app_...) with stored learning suggestions
- `confirm` (boolean, required): Explicit confirmation to apply the reviewed learning suggestions
- `mode` (string): Extend existing routes (default), or replace them with learned routes; both set the suggested rate limit
- `project_id` (string, required): The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3...

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-odilelabs-gate-oversight/mcp-oversight#diagnostics

## Score history

- 2026-11-21: 69
- 2026-11-20: 68
- 2026-11-19: 68
- 2026-11-18: 68
- 2026-11-17: 67
- 2026-11-16: 67
- 2026-11-15: 66
- 2026-11-14: 66

## Common questions

### What is the Odile Gate Oversight MCP server?

Odile Gate Oversight is an MCP server listed in the public MCP registry as com.odilelabs/gate-oversight. Watch Odile Gate: runs, held actions, audit log with signed export, metrics and refusal reasons. This page covers its hosted endpoint (https://gate.odilelabs.com/mcp/oversight).

### Is the Odile Gate Oversight MCP server safe to use?

Odile Gate Oversight scores 69 out of 100 on VerifyMCP. 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 Odile Gate Oversight MCP server expose?

Odile Gate Oversight exposes 15 tools: gate_list_apps, gate_list_approvers, gate_create_run, gate_delegate_run, gate_revoke_run, and 10 more. Their descriptions and schemas cost roughly 2,732 tokens of context every time the server is loaded.

### Does the Odile Gate Oversight MCP server require authentication?

No. We connected to Odile Gate Oversight without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Odile Gate Oversight MCP server still maintained?

Odile Gate Oversight is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Odile Gate Oversight MCP server?

VerifyMCP ran 13 checks on Odile Gate Oversight, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://gate.odilelabs.com/mcp/oversight
- Website: https://gate.odilelabs.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-odilelabs-gate-oversight/mcp-oversight.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-odilelabs-gate-oversight/mcp-oversight/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-odilelabs-gate-oversight/mcp-oversight.json
- HTML version of this page: https://verifymcp.io/servers/com-odilelabs-gate-oversight/mcp-oversight
