@neurynae/toolcairn-mcp

Source for @neurynae/toolcairn-mcp on npm. Install via the package, not from this repo.

ToolCairn is an MCP server that connects your AI coding agent to a continuously-updated graph of 30,000+ open-source tools across npm, PyPI, Cargo, Maven, Go, Composer, RubyGems, NuGet, Homebrew, and 35+ more registries. Search, compare, build stacks, and check version compatibility — all from inside Claude Code, Cursor, or any MCP-compatible client.

Concrete example. Your agent receives "I need a fast HTTP client for Node" → it calls search_tools → ToolCairn returns ranked candidates with maintenance and community signals, alternatives, and a warning if the top pick has questionable activity. No more guessing from blog posts and stale tutorials.

The MCP server runs locally as a stdio child of your agent. Tool calls travel over MCP to this package, which proxies the network-bound ones to the ToolCairn Cloud API and handles the local-only ones (project scan, config, audit log) on disk.

Why ToolCairn?

Plain web search and LLM training data are insufficient for tool selection — knowledge cutoffs miss latest releases, search engines surface tutorials over authoritative ranking, and version-compatibility answers live in scattered issue threads.

ToolCairn fixes this with three things you can't get from raw registry APIs:

• Graph-aware ranking — recommendations consider how tools relate to each other (dependencies, integrations, replacements, conflicts), not just popularity.
• Version-aware compatibility — declared peer ranges and cross-registry version metadata give you "Next.js 14 needs React 18.x" instead of "they're both popular, probably fine?"
• A continuous learning loop — every accepted, rejected, or replaced recommendation feeds back into the graph, so quality improves with use.

Quick Start

Step 1. Create a free account at toolcairn.neurynae.com/signup.

Step 2. Add to your MCP config and restart your agent:

{
  "mcpServers": {
    "toolcairn": {
      "command": "npx",
      "args": ["@neurynae/toolcairn-mcp"]
    }
  }
}

Step 3. A browser window opens for sign-in on first start. Once you confirm, all tools are available immediately — no further setup.

Requires Node.js 22+.

Setup — Claude Code

The fastest path:

claude mcp add toolcairn -- npx @neurynae/toolcairn-mcp

Or paste the JSON block above into ~/.claude/claude_desktop_config.json under mcpServers.

Other MCP-compatible clients (Cursor, Claude Desktop, VS Code Copilot, Windsurf, Zed, …) work with the same npx @neurynae/toolcairn-mcp command — see the docs for client-specific config locations.

What you can do

Find a tool

Your agent receives "I need a real-time analytics database for event tracking" → calls search_tools → gets ranked candidates (ClickHouse, TimescaleDB, InfluxDB, …) with maintenance signals. If the intent is ambiguous, the response carries clarification questions; the agent answers via search_tools_respond and gets refined results.

Build a stack

Your agent receives "Help me architect a full-stack TypeScript SaaS" → calls refine_requirement to decompose, then get_stack with the per-layer needs → gets a 3–5 tool stack (web framework + database + auth + payments) with a version-compatibility matrix showing which versions work together across the stack.

Compare options

"Express vs Fastify for a REST API?" → compare_tools returns side-by-side health (stars, maintenance score, last commit, open issues, contributor trends), graph relationships (what each integrates with, what they replace), and a recommendation grounded in your stated use case.

Check version compatibility

"I want to upgrade Next.js to 14 but keep React 17." → check_compatibility evaluates declared peer ranges and returns satisfied/unsatisfied checks with the source (declared_dependency / graph_edges / shared_neighbors).

Track project tools

On first session, toolcairn_init walks your repo, parses every manifest (package.json, requirements.txt, pyproject.toml, Cargo.toml, go.mod, pom.xml, Gemfile, composer.json, …), classifies each tool against the ToolCairn graph, and writes a local .toolcairn/ snapshot. Subsequent sessions read this snapshot first — your agent stops re-searching for things it already knows about.

Available Tools

The MCP server exposes 16 tools, grouped by purpose. Most are local (no network) or fire-and-forget; the search, compare, and stack tools call the ToolCairn API.

Discovery

Stacks & Compatibility

Project Configuration

Feedback Loop

Session

Configuration

Where things live

• Credentials → ~/.toolcairn/credentials.json (mode 0600, 90-day expiry).
• Per-project state → .toolcairn/{config.json, audit-log.jsonl, tracker.html} at each detected project root.

The tracker.html file is a self-contained dashboard — open it in any browser to see every tool call, pending evaluation, and audit entry in real time.

Session management

Your sign-in lives at ~/.toolcairn/credentials.json and lasts 90 days. From inside your agent:

toolcairn_auth { action: "status" }   # check current sign-in
toolcairn_auth { action: "logout" }   # clear credentials

To re-authenticate, simply restart your agent — the sign-in flow opens automatically.

Privacy & telemetry

We're explicit about what leaves your machine.

Sent to ToolCairn (when tracking is enabled):

• Tool name, duration, and success/error status — for service health and product analytics.
• Never full prompts, response bodies, or project file contents.

Stays local:

• Every audit entry (.toolcairn/audit-log.jsonl).
• Project state and tool snapshots.
• Your credentials file.

Opt out at any time:

TOOLCAIRN_TRACKING_ENABLED=false

Tools still work normally; only the lightweight usage events are skipped.