Hound MCP server

by tiluckdave·io.github.tiluckdave/hound·v0.2.1·17 stars

No reviews yet

The dependency bloodhound for AI coding agents. Zero API keys, zero config.

A92/100grade A

Write a review Install

What users say

No reviews yet

Be the first

Safety scan

A92/100

full report

Adoption

Growing

17 stars59 downloads/wk

Reviews

Write one

Nobody has reviewed Hound yet.

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

Hound tools (12)

write = sends, deletes, buys or posts

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

hound_advisories
Get full details for a security advisory by ID (GHSA, CVE, or OSV ID). Returns title, severity, affected versions, fix versions, and references.
hound_audit
Scan a project's lockfile for dependency risks. Parses package-lock.json, yarn.lock, pnpm-lock.yaml, requirements.txt, Cargo.lock, or go.sum and batch-queries OSV for vulnerabilities across all dependencies.
hound_compare
Side-by-side comparison of two packages: vulnerabilities, OpenSSF Scorecard, GitHub stars, release recency, and license. Returns a recommendation.
hound_inspect
Get a comprehensive profile of a package version: licenses, vulnerabilities, OpenSSF scorecard, GitHub stats, and dependency count \u2014 all in one call.
hound_license_check
Scan a lockfile for license compliance. Resolves licenses for every dependency and flags packages that violate the chosen policy (permissive, copyleft, or none).
hound_popular
Scan a list of popular (or user-specified) packages for known vulnerabilities. Quickly surface which widely-used packages in an ecosystem have open security issues.
hound_preinstall
Safety check before installing a package. Checks known vulnerabilities, typosquatting risk, abandonment, and license concerns. Returns a go/no-go verdict.
hound_score
Compute a 0-100 Hound Score for a package version combining vulnerability severity, OpenSSF Scorecard, release recency, and license risk. Returns a letter grade (A-F) with a breakdown.
hound_tree
Show the full resolved dependency tree for a package version, including all transitive dependencies with their depth and relation type.
hound_typosquat
Check if a package name looks like a typosquat of a popular package. Generates likely typo variants and checks which ones exist in the registry.
hound_upgrade
Find the minimum version upgrade that resolves all known vulnerabilities for a package. Checks every published version and returns the nearest safe one.
hound_vulns
List all known vulnerabilities for a specific package version, grouped by severity with fix versions and advisory links.

Public scan report

scanner v0.1.10 · 2026-09-28 · same rubric, same numbers if you re-run it

no findings

Code scan2 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 5 days ago15/15
Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

How Hound compares

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

Safety score: 92/100; higher than 95% of 48,255 servers
Tools: 12; the typical server has 7
Tools that change things: 0%; typical: 0%. Fewer write tools means less an agent can break
GitHub stars: 17; more than 90% of 28,688 servers
Downloads a week: 59; more than 48% of 12,191 servers with a package

What its tools let an agent do: 12 read

Install Hound in Claude Code, Cursor or VS Code

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

claude mcp add hound -- npx -y hound-mcp

Add to Cursor

What the publisher says

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

Hound MCP

The dependency bloodhound for AI coding agents.

Hound MCP Deployment Diagram

Why Hound?

AI coding agents recommend and install packages without knowing if they're safe — and most security tools require accounts, API keys, or paid plans to tell you. Hound fixes that: it scans for vulnerabilities, checks licenses, audits dependency trees, and detects typosquatting across 7 ecosystems — zero config, zero API keys, zero cost.

Hound is the only security tool built specifically for AI coding agents — works across npm, PyPI, Go, Cargo, Maven, NuGet, and RubyGems, and plugs into Claude Code, Cursor, VS Code, and any MCP client out of the box.

It uses two fully free, unauthenticated public APIs: deps.dev (Google Open Source Insights) and OSV (Google Open Source Vulnerabilities).

Quickstart

Claude Code

claude mcp add hound -- npx -y hound-mcp

Claude Desktop / Cursor / Windsurf

Add to your MCP config file:

{
  "mcpServers": {
    "hound": {
      "command": "npx",
      "args": ["-y", "hound-mcp"]
    }
  }
}

VS Code (Copilot)

{
  "mcp": {
    "servers": {
      "hound": {
        "type": "stdio",
        "command": "npx",
        "args": ["-y", "hound-mcp"]
      }
    }
  }
}

Config file locations

Tools

12 tools → Full reference with example outputs

Supported ecosystems: npm · pypi · go · maven · cargo · nuget · rubygems

Built-in Prompts

Shortened. The full README is on GitHub.

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

Hound: common questions

Is Hound MCP server safe?: Yes, by our scan: it is graded A (92/100). Read the Hound safety report
How do I install Hound?: It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Hound need an API key?: Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Hound maintained?: The last commit was 42 days ago (2026-09-23). The latest release is v0.2.1.
How does Hound compare with other MCP servers?: safety score 92/100 (higher than 95% of 48,255 servers); tools 12 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.