Agent teams, swarms, memory and hooks for Claude Code and Codex, served over MCP.
Odile Gate Oversight is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Watch Odile Gate: runs, held actions, audit log with signed export, metrics and refusal reasons.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http odile-gate-oversight-mcp https://gate.odilelabs.com/mcp/oversight
# 2 — ask your agent for something these tools do
# gate_list_apps, gate_list_approvers, gate_create_run and 12 more
Odile Gate Oversight costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http odile-gate-oversight-mcp https://gate.odilelabs.com/mcp/oversightReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
15 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3... |
| admin_key | string | yes | The project admin key (ga_...). Read it from the .env; never print it. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3... |
| admin_key | string | yes | The project owner key (ga_...) or an active member key (gm_...). Never print it. |
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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3... |
| admin_key | string | yes | The project admin key (ga_...). Read it from the .env; never print it. |
| app | string | yes | The app id (app_...) this run is for |
| label | string | no | Optional: what the run is for, e.g. "triage ticket 4411" |
| scope | object | no | Values for the {placeholders}, e.g. {"customer":"A"} |
| actions | array | yes | Rules, or {rule, max, approval, check} |
| ttl_seconds | integer | no | How long the run lasts (default 3600) |
| max_calls | integer | no | Optional: calls allowed in the whole 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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3... |
| app_key | string | yes | The parent app key (gk_...) |
| run_token | string | yes | The parent run token (gr_...) |
| app | string | yes | The destination app id |
| actions | array | yes | — |
| ttl_seconds | integer | no | — |
| max_calls | integer | no | — |
| label | string | no | A short label for the delegated job |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3... |
| admin_key | string | yes | The project admin key (ga_...). Read it from the .env; never print it. |
| run_id | string | yes | The run id: run.run_id in gate_create_run's result |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3... |
| admin_key | string | yes | The project admin key (ga_...). Read it from the .env; never print it. |
| state | string | no | Default: pending |
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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3... |
| admin_key | string | yes | The project admin key (ga_...). Read it from the .env; never print it. |
| app | string | no | Optional: only this app id (app_...) |
| status | string | no | Optional: only this HTTP status, e.g. "403" |
| limit | integer | no | How many calls (default 20) |
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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3... |
| admin_key | string | yes | The project admin key (ga_...). Read it from the .env; never print it. |
| from | integer | no | — |
| to | integer | no | — |
| actions_after | string | no | Action cursor from next_actions_after |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3... |
| admin_key | string | yes | The project admin key (ga_...). Read it from the .env; never print it. |
| proof | object | yes | The full signed export from gate_export_audit_proof |
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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3... |
| admin_key | string | yes | The project admin key (ga_...). Read it from the .env; never print it. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3... |
| admin_key | string | yes | The project admin key (ga_...). Read it from the .env; never print it. |
| run_id | string | yes | The run id |
| before | integer | no | Older audit events (timeline pages have at most 500 events) |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3... |
| admin_key | string | yes | The project admin key (ga_...). Read it from the .env; never print it. |
| run_id | string | yes | The run id |
What a Gate refusal means and how to fix it, from the x-gate-refused header value (e.g. route_not_allowed).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| reason | string | yes | The x-gate-refused value |
| recoverable | boolean | no | Whether the write was granted with a recovery check |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3... |
| admin_key | string | yes | The project admin key (ga_...). Read it from the .env; never print it. |
| app | string | yes | The app id |
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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3... |
| admin_key | string | yes | The project owner key (ga_...) or an accepted admin member key (gm_...). Read it from the .env; never print it. |
| app | string | yes | The app id (app_...) with stored learning suggestions |
| confirm | boolean | yes | Explicit confirmation to apply the reviewed learning suggestions |
| mode | string | no | Extend existing routes (default), or replace them with learned routes; both set the suggested rate limit |
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Odile Gate Oversight or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| gate_list_apps | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| gate_list_approvers | no tags | |
| gate_create_run | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| gate_delegate_run | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| gate_revoke_run | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| gate_list_actions | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| gate_read_audit | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| gate_export_audit_proof | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| gate_verify_audit_proof | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| gate_get_metrics | no tags | |
| gate_get_run_timeline | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| gate_get_run_tree | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| gate_explain_refusal | no tags | |
| gate_learn_suggestions | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| gate_update_app | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.1.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish Odile Gate Oversight can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.