Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/tiluckdave/hound-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/tiluckdave/hound-mcp/hound)<a href="https://agentmods.dev/mcp/tiluckdave/hound-mcp/hound"><img src="https://agentmods.dev/badge/mcp/tiluckdave/hound-mcp/hound/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/tiluckdave/hound-mcp/hound"><img src="https://agentmods.dev/badge/mcp/tiluckdave/hound-mcp/hound.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
hound scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"hound": {
"command": "npx",
"args": [
"-y",
"hound-mcp"
],
"env": {}
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 10 lines scan A 4993d398a956
hound is an MCP server published in the GitHub repository tiluckdave/hound-mcp (17 stars, last pushed 4d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other mcp servers, from other repositories
proof-of-commitment
Supply chain risk scoring for npm, PyPI, Cargo, and Go. 9 tools. Behavioral signals. Runs locally from the proof-of-commitment npm package.
depguard
A powerful CLI tool to check and update npm/yarn dependencies in your projects. Runs locally from the depguard npm package.
blastradius
Dependency blast-radius analyzer: before you upgrade an npm package, see exactly which of YOUR files and functions touch its changed API surface. Runs locally from the @justfeltlikerunning/blastradius npm package.
dependency-fitness-mcp
MCP server that returns a cross-validated dependency FITNESS verdict for npm packages: deprecated / yanked / superseded status plus an inferred safe migration target — what to move to and how confident we are — cross-checked across the npm registry, deps. Runs locally from the dependency-fitness-mcp npm package.
apidog-mcp
MCP server for managing Apidog API documentation — import, export, diff, cases, schemas, bulk ops, analysis, and more. Runs locally from the @lstpsche/apidog-mcp npm package.
mcp-tool-factory
Generate MCP servers from natural language, OpenAPI specs, or database schemas. Runs locally from the @heshamfsalama/mcp-tool-factory npm package. Needs 4 environment variables to run.