C

npm:openrouter-admin-mcp

https://www.npmjs.com/package/openrouter-admin-mcp
75/100 · MCP Trust Grade · checked 2h ago · MCP 0.7.3

What it offers — 14 tools · AI & ML

or_activity

Show OpenRouter usage grouped by endpoint for the last 30 UTC days. Optional filters: date (YYYY-MM-DD), api_key_hash, user_id.

or_credits

Show OpenRouter balance: total purchased, total used, remaining.

or_current_key

Show metadata of the Provisioning key the server is using (label, type, limits, usage).

or_generation

Get details of a single inference call by its generation_id (returned by OpenRouter in completion responses, e.g.

or_guardrails_list

List all OpenRouter guardrails (account-wide spending limits and provider/model allowlists).

or_guardrail_get

Get details of one guardrail by id: limit_usd, reset_interval, allowed/ignored providers/models, enforce_zdr.

or_guardrails_assignments

One-shot view of all guardrail assignments: which keys and which org members are bound to which guardrail. Combines /guardrails/key-assignments and /g

or_guardrail_create

Create a new guardrail. Combine spend limit (limit_usd + reset_interval) with provider/model allowlists. Destructive — confirm before running.

or_guardrail_update

Update an existing guardrail. Pass null to clear nullable fields. Destructive — confirm before running.

or_guardrail_delete

Permanently delete a guardrail. Existing assignments will detach. Destructive — confirm before running.

or_guardrail_assign_keys

Bulk-assign a guardrail to a set of inference keys (by hash). Destructive — confirm.

or_guardrail_unassign_keys

Bulk-unassign a guardrail from a set of inference keys (by hash). Destructive — confirm.

or_guardrail_assign_members

Bulk-assign a guardrail to a set of organization members (by user_id). Destructive — confirm.

or_guardrail_unassign_members

Bulk-unassign a guardrail from organization members (by user_id). Destructive — confirm.

Spec / packaging20%100
Security (OWASP MCP)30%25
Maintenance / popularity20%100
Tool hygiene15%95
Transparency / provenance15%90

Findings

WARNMCP08 References sensitive file paths / environment secrets.
INFO Static analysis of npm package openrouter-admin-mcp@0.7.3 (stdio server — no remote endpoint). Reliability/behavioral signals require running it; not measured.
Grade another server

We re-grade npm:openrouter-admin-mcp on a schedule and alert your Slack/webhook the moment its tools change or its grade drops — rug-pull insurance for the connection.

Share this report card

A 1200×630 card with the grade + audit — drop it in a post, Slack, or your repo.

MCP Trust report card — npm:openrouter-admin-mcp grade C
Share on X Open card image

Embed this grade

A live badge — it re-verifies itself and shows current stability. Static scorecards can't. Paste it in your README or site to show users you're independently audited.

MCP Trust Grade C · wmcp.sh
[![MCP Trust Grade C](https://wmcp.sh/mcp/grade/npm%3Aopenrouter-admin-mcp/badge.svg)](https://wmcp.sh/mcp/grade/npm%3Aopenrouter-admin-mcp)
<a href="https://wmcp.sh/mcp/grade/npm%3Aopenrouter-admin-mcp"><img src="https://wmcp.sh/mcp/grade/npm%3Aopenrouter-admin-mcp/badge.svg" alt="MCP Trust Grade C · wmcp.sh"></a>

Agents: check this before connecting

Add the wmcp.sh trust oracle as an MCP server and call grade_mcp_server / check_mcp_drift in your agent's pre-connection gate:

https://wmcp.sh/mcp/trust
How this grade is computed. An open, independent rubric — Spec conformance (20%), Security mapped to the OWASP MCP Top 10 (30%), Reliability (20%), Tool hygiene (15%), Transparency (15%) — run by connecting to the server and inspecting its real MCP surface. The grade is free and identical whether or not the operator pays. v1 uses static + spec signals from a single connection; continuous uptime, real latency, and annotation-truthing (declared readOnly vs observed behavior) layer on via the wmcp.sh proxy.