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/whyy9527/ariadneWrote 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/whyy9527/ariadne/ariadne)<a href="https://agentmods.dev/mcp/whyy9527/ariadne/ariadne"><img src="https://agentmods.dev/badge/mcp/whyy9527/ariadne/ariadne/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/whyy9527/ariadne/ariadne"><img src="https://agentmods.dev/badge/mcp/whyy9527/ariadne/ariadne.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ariadne 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 9d 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
{
"ariadne": {
"command": "uvx",
"args": [
"ariadne-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.
- 9d ago First seen · 9 lines scan A 97e2f4b84adc
ariadne is an MCP server published in the GitHub repository whyy9527/ariadne (2 stars, last pushed 1mo 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
api-agent-ratatoskr
Universal MCP server for querying GraphQL, REST, and gRPC APIs using natural language. Runs locally from the api-agent-ratatoskr Python package.
graphql-mcp-server
MCP server "graphql-mcp-server" as configured in Chakit22/graphql-mcp-server. Runs locally from the graphql-mcp-server npm package.
vectr
Semantic codebase search + persistent working memory for AI code editors. Local, zero-config, MCP. No API key. Runs locally from the vectr Python package.
cockroachdb-toolbox-http
MCP server "cockroachdb-toolbox-http", hosted remotely at 127.0.0.1, as configured in cockroachdb/claude-plugin.
mcp
Moved to net.anyhook/anyhook. Webhook relay for agents: keyless quickstart, replay, mock. Runs locally from the anyhook-mcp npm package. Needs 2 environment variables to run.
universal-connector-mcp
A security-first, local-first MCP server that connects any API (OpenAPI/GraphQL/gRPC/SOAP) to AI agents through a single normalized operation model. Runs locally from the universal-connector-mcp Python package. Needs 5 environment variables to run.