# Odile Gate Oversight

> Odile Gate Oversight is a freemium MCP server for security. Read-only MCP view of Odile Gate runs, held actions, audit log and metrics. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Platforms:** API, Web
- **Website:** https://gate.odilelabs.com
- **MCP Registry name:** com.odilelabs/gate-oversight
- **Categories:** security, developer tools
- **Listing updated:** 2026-11-14

## About

This is the oversight side of Odile Gate, a proxy that sits in front of a database API so each AI-built app gets its own key, an allow-list of calls and a per-minute limit. The MCP endpoint at gate.odilelabs.com/mcp/oversight lets an agent or its human look at what Gate has been doing: runs, actions held for approval, the audit log with signed export, metrics and refusal reasons.

The site describes several things Gate enforces. Refused calls get a 401, 403 or 429 answer from Gate itself. A run grants an agent session a few named actions, bound to one customer, with limits and an expiry; actions marked for approval are held with a 202 until a named approver accepts them in the dashboard. Writes carry an idempotency key, and after a timeout Gate answers outcome_unknown instead of resending.

Tools mentioned for the wider product include gate_metrics, a read-only view of the last 24 hours of calls by status and reason, gate_check_setup, which reports observation mode, wildcard grants and missing JWT setup without changing settings, and gate_set_response for field redaction. Which of these this oversight endpoint exposes is not spelled out.

## Features

- **Audit log with export:** Call metadata is recorded in an exportable audit log; invalid-key rows are limited to 20 per hour.
- **Held-action review:** Calls marked for approval are held until an approver accepts or rejects the exact call.
- **Refusal reasons:** Gate answers refused calls itself, with distinct codes for missing key, no matching rule and rate limits.
- **Operational metrics:** Shows the last 24 hours of stored calls by HTTP status and reason, with duration.
- **Idle app flags:** Apps with no allowed call for a chosen 1 to 90 days are flagged, with an optional webhook.
- **Setup check:** A separate check reports observation mode, wildcard grants and approval separation gaps.

## Good for

- Review which agent actions are waiting for human approval
- Export a signed audit log for a security review
- Find out why an AI-built app's calls were refused
- Spot apps that have stopped making calls

## Install

### Claude Code (Terminal)

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

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://gate.odilelabs.com/mcp/oversight
```

### Cursor (~/.cursor/mcp.json)

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

### VS Code (.vscode/mcp.json)

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

### Windsurf (~/.codeium/windsurf/mcp_config.json)

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

### Other clients (your client's MCP settings (most use this shape))

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

## Tools

- `gate_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.
- `gate_list_approvers`: 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.
- `gate_create_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 ac
- `gate_delegate_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.
- `gate_revoke_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.
- `gate_list_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. 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.
- `gate_read_audit`: 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-ho
- `gate_export_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=f
- `gate_verify_audit_proof`: 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.
- `gate_get_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 ano
- `gate_get_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.
- `gate_get_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.
- `gate_explain_refusal`: What a Gate refusal means and how to fix it, from the x-gate-refused header value (e.g. route_not_allowed).
- `gate_learn_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.
- `gate_update_app`: 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 an

## FAQ

### What does Gate do?

It sits in front of your database API and gives each AI-built app a key, an allow-list of calls, a rate limit and an audit log.

### Does the oversight server change anything?

The registry describes it as a way to watch runs, held actions, the audit log and metrics, which suggests viewing rather than changing.

### Can Gate limit access to one customer's data?

Yes. A run can be bound to one customer, and per-user rules check a login token so a call must name that user.

### Is there a free plan?

The site refers to Free and Pro tiers; prices are not shown in the text.

### Is Odile Gate Oversight free?

Odile Gate Oversight has a free plan, with paid plans for more usage or features.

### How do I add Odile Gate Oversight to Claude Code?

Run this command in your terminal: claude mcp add --transport http gate-oversight https://gate.odilelabs.com/mcp/oversight

### What are the best alternatives to Odile Gate Oversight?

The closest alternatives to Odile Gate Oversight are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

## Alternatives

- [REA](https://ai-powered.com/mcp/rea): REA is an open-source MCP server for developer tools.
- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [GitHub](https://ai-powered.com/mcp/github-2): GitHub is an open-source MCP server for developer tools.
- [Serena MCP: the IDE for your agent](https://ai-powered.com/mcp/serena-mcp-the-ide-for-your-agent): Serena MCP: the IDE for your agent is an open-source MCP server for developer tools.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [Ouroboros](https://ai-powered.com/mcp/ouroboros): Ouroboros is an open-source MCP server for developer tools.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [Concord MCP](https://ai-powered.com/mcp/concord-mcp): Concord MCP is a freemium MCP server for developer tools.

---
Source: https://ai-powered.com/mcp/odile-gate-oversight
