What are the risks of connecting to npm:agentlookup-mcp?

References sensitive file paths / environment secrets. Overall trust grade D (65/100).

When was npm:agentlookup-mcp last audited?

Last checked 2026-06-03; wmcp.sh re-checks it on a schedule for tool drift and rug-pulls.

npm:agentlookup-mcp

Item: npm:agentlookup-mcp
Rating: 65
Author: wmcp.sh

https://www.npmjs.com/package/agentlookup-mcp

65/100 · MCP Trust Grade · checked 1mo ago · MCP 1.0.1

Is the npm:agentlookup-mcp MCP server safe to use?

Independent trust grade D (65/100). References sensitive file paths / environment secrets. wmcp.sh continuously watches npm:agentlookup-mcp for tool drift and rug-pulls. The grade is free and identical whether or not the operator pays.

What it offers — 4 tools · Search

discover_agents

Browse new, active, and popular agents in the registry. Use when exploring what

heartbeat

Send a heartbeat to keep a registered agent

lookup_agent

Get full details for a specific agent by ID. Use when an agent_id is known from search results, from a .well-known/agents.json file, or from a user pr

register_agent

Register a new agent in the public registry. Use when the user wants to make their agent discoverable, or when an autonomous agent decides to register

Spec / packaging20%100

✓ depends on an MCP SDK
✓ declares a bin entry (runnable server)
✓ 4 tool(s) detected in source

Security (OWASP MCP)30%25

⚠ references sensitive file paths / env secrets
scanned 6 source files

Maintenance / popularity20%75

last published ~3mo ago
2 published versions

Tool hygiene15%95

✓ ships TypeScript types
2 runtime deps

Transparency / provenance15%55

no repository link
✓ MIT license
15 weekly downloads

Findings

WARNMCP08 References sensitive file paths / environment secrets.

INFO Static analysis of npm package agentlookup-mcp@1.0.1 (stdio server — no remote endpoint). Reliability/behavioral signals require running it; not measured.

Grade another server

We re-grade npm:agentlookup-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:agentlookup-mcp grade D

Share on X Open card image

https://wmcp.sh/mcp/grade/npm%3Aagentlookup-mcp

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.

Markdown (for your README)

[![MCP Trust Grade D](https://wmcp.sh/mcp/grade/npm%3Aagentlookup-mcp/badge.svg)](https://wmcp.sh/mcp/grade/npm%3Aagentlookup-mcp)

HTML

<a href="https://wmcp.sh/mcp/grade/npm%3Aagentlookup-mcp"><img src="https://wmcp.sh/mcp/grade/npm%3Aagentlookup-mcp/badge.svg" alt="MCP Trust Grade D · 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.