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/AI-Directory-Partners/tooldirectory-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/ai-directory-partners/tooldirectory-mcp/catalog)<a href="https://agentmods.dev/mcp/ai-directory-partners/tooldirectory-mcp/catalog"><img src="https://agentmods.dev/badge/mcp/ai-directory-partners/tooldirectory-mcp/catalog/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/ai-directory-partners/tooldirectory-mcp/catalog"><img src="https://agentmods.dev/badge/mcp/ai-directory-partners/tooldirectory-mcp/catalog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
catalog 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 10d 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
{ "catalog": { "url": "https://tooldirectory.ai/api/mcp", "type": "streamable-http" } }
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.
- 10d ago First seen · 6 lines scan A 77a21515bd71
catalog is an MCP server published in the GitHub repository AI-Directory-Partners/tooldirectory-mcp (1 stars, last pushed 2mo 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 2026-08-31.
Other mcp servers, from other repositories
aisotools
Search, compare, and find alternatives across a curated catalog of 1,100+ AI tools. Remote server at aisotools.com.
ninjaone-mcp
MCP server "ninjaone-mcp" as configured in WYRE-AI/ninjaone-mcp. Runs in Docker (ghcr.io/wyre-ai/ninjaone-mcp:v2.3.0). Needs 6 environment variables to run.
AynOps
A Model Context Protocol server that gives AI Clients real-time cybersecurity reconnaissance capabilities — WHOIS, DNS enumeration, port scanning, SSL inspection, CVE lookup, IP reputation, ASN lookup and more. Runs locally from the AynOps Python package. Needs 2 environment variables to run.
apibase
327 tools, 92 providers. Pay per call via x402 + MPP. One MCP endpoint. Runs locally from the apibase-mcp-client npm package.
calc-mcp
21 MCP tools for math, randomness, dates, encoding, hashing, and more — deterministic and accurate. Runs locally from the @coo-quack/calc-mcp npm package.
mcp-server
MCP server for Zooza — class scheduling, attendance, and booking for activity businesses. Remote server at mcp.zooza.app.