MCP.Market

Heimdall MCP server

by caglarbozkurt·io.github.caglarbozkurt/heimdall·v0.5.1
No reviews yet

Scan an MCP server or agent config for injection, exfiltration, and risky capabilities.

A88/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A88/100

full report

Adoption
New

0 stars36 downloads/wk

Reviews

Write one

Nobody has reviewed Heimdall yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Heimdall tools (1)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • scan_mcp_server

    Statically vet an MCP server (or a whole MCP client config) BEFORE trusting or installing it.

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

no findings
  • Code scan59 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 82 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 88/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Heimdall compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
88/100
higher than 80% of 4,460 AI and agents servers
Tools
1
the typical AI and agents server has 6
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
36
more than 27% of 1,538 AI and agents servers with a package

What its tools let an agent do: 1 read

Install Heimdall in Claude Code, Cursor or VS Code

Runs npx -y mcp-heimdall-scan on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add heimdall -- npx -y mcp-heimdall-scan
Add to Cursor

What the publisher says

From the Heimdall repository's README, as published. We do not edit it. Read it on GitHub

Heimdall

The watchman at your agent's gate.

A local, pre-flight security scanner for Model Context Protocol (MCP) servers — vet a server, or a whole agent config, before your agent trusts it. No account, no backend, and it never runs the server by default.

MCP servers are unvetted code with a natural-language attack surface: their tool descriptions go straight to your model, and the server runs with your machine's access. Heimdall scores what a server can actually do — not what it claims — and cites the exact evidence. It runs entirely on your machine, needs no account, and never executes the server by default, so you can vet a package before you install it and gate it in CI.

Quickstart

npx mcp-heimdall-scan firecrawl-mcp                   # scan a published server
npx mcp-heimdall-scan ./claude_desktop_config.json    # audit your whole agent config
npx mcp-heimdall-scan firecrawl-mcp --online          # + check its deps for known CVEs (OSV.dev)
npx mcp-heimdall-scan ./my-server --policy strict     # gate it in CI

No install, runs locally, nothing leaves your machine.

Or try it in your browser: caglarbozkurt.github.io/mcp-heimdall — the full scanner runs 100% client-side (npm packages are fetched via jsDelivr; or paste a tools.json / MCP config). No backend, nothing uploaded. Local paths and --handshake need the CLI.

What it checks

Every finding cites file:line or tool:name. Capability ≠ risk: raw power is shown as an informational profile and never fails the scan — only hard gates and real anomalies do.

What makes it different

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Heimdall: common questions

Is Heimdall MCP server safe?
Yes, by our scan: it is graded A (88/100). Read the Heimdall safety report
How do I install Heimdall?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Heimdall need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Heimdall maintained?
The last commit was 121 days ago (2026-07-06). The latest release is v0.5.1.
What can I use instead of Heimdall?
Servers from other publishers that do the same job: Agent Security Scanner MCP server, Godot MCP server and Skillsmith MCP server.
How does Heimdall compare with other AI and agents MCP servers?
safety score 88/100 (higher than 80% of 4,460 AI and agents servers); tools 1 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Heimdall

Same job from other publishers: the closest match first, then the best rated.

  • Agent Security Scanner
    Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.
    C
  • Godot MCP
    Agent-driven Godot playtesting: editor control, input injection, game-time stepping, live state.
    A
  • Skillsmith
    Share agent skills across your team, scan them for risk, and track what's actually used.
    B
  • Shellward
    AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.
    A