mcpbeat Sign in

Ariadne MCP Server

local only

Ariadne runs on your own machine — the client starts it, so there is no endpoint to ping. 334 installs a week from pypi. Last commit 27 Oct 2026.

Deterministic local cross-service API-chain discovery for AI coding agents.

Installs per day peak 328 · avg 69 · -46% w/w
a month agotoday
334
Installs / week
pypi · ariadne-mcp
4
Stars
0 open issues
27 Oct 2026
Last commit
from GitHub
MIT
License
Python

What the code does

We read the source, 4 d ago · rules 995398eba69f

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

        out = subprocess.run(
    return os.path.abspath(os.path.join(base, p))

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Three servers free · no card

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add ariadne -- uvx ariadne-mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "ariadne": {
      "command": "uvx",
      "args": [
        "ariadne-mcp"
      ]
    }
  }
}
~/.codex/config.toml
[mcp_servers.ariadne]
command = "uvx"
args = ["ariadne-mcp"]
.cursor/mcp.json
{
  "mcpServers": {
    "ariadne": {
      "command": "uvx",
      "args": [
        "ariadne-mcp"
      ]
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "ariadne": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "ariadne-mcp"
      ]
    }
  }
}

Alternatives to Ariadne

same job, measured the same way
Rosentic
by rosentic

Deterministic cross-branch conflict detection for AI coding agents

148 installs/wk local only
OrchestrUI
by ecd5a

Deterministic UI policy, discovery and audits for coding agents across seven ecosystems.

67 installs/wk local only
oss-search
by sblattj

Fast local and federated OSS code search and repo discovery for AI agents

71 installs/wk local only
One Shot UI
by tn0123

Deterministic UI extraction and screenshot diffing for AI coding agents.

98 installs/wk local only
Cross-Agent Memory
by indamices

Local-first shared memory for AI coding agents: one searchable store, served over MCP. MIT.

local only
Chemistry
by covasyn

Deterministic MCP for AI agents: drug discovery, ADMET, docking, LNPs, DoE, retrosynthesis, ICH M7

answering
Honestcode
by fengrru

Deterministic verification for AI coding agents: catches invented APIs and wrong calls.

144 installs/wk local only
Agentos
by officialtanishsharma

Local-first persistent memory MCP server for AI coding agents.

local only

Ariadne — questions

Answers built from our own checks of this server.

Why is there no uptime for Ariadne?
Ariadne runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package ariadne-mcp was installed 334 times last week.
How do I connect Ariadne?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls ariadne-mcp straight from pypi; nothing to host, nothing to sign up for.
How many people use Ariadne?
The pypi package ariadne-mcp was installed 334 times in the last week. Week over week that is -46%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Ariadne open source?
Yes — it is published under the MIT licence, written in Python and 4 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.