cyanheads-mcp-server
Fleet discovery for the cyanheads MCP ecosystem — semantic search + install snippets.
README
<div align="center"> <h1>@cyanheads/cyanheads-mcp-server</h1> <p><b>Fleet discovery for the cyanheads MCP ecosystem — semantic search + install snippets.</b> <div>2 Tools • 0 Resources • 0 Prompts</div> </p> </div>
<div align="center">
</div>
<div align="center">
</div>
<div align="center">
Public Hosted Server: https://cyanheads.caseyjhand.com/mcp
</div>
Tools
Two tools, semantic ranking, hosted catalog. The catalog itself lives at caseyjhand.com/fleet.json — a single JSON file with baked embeddings, regenerated when servers are added or updated. This server polls it hourly and serves search out of an in-memory vector index.
| Tool | Description |
|---|---|
cyanheads_search_catalog |
Search fleet tools and servers by natural-language query. Returns ranked matches with brief summaries and the owning server. |
cyanheads_describe_entry |
Return the connection URL and per-client install snippets for a named tool or server. |
cyanheads_search_catalog
Semantic search across the fleet. Embeds the query with Snowflake Arctic Embed M v1.5 (Matryoshka-truncated to 256 dimensions) and computes cosine similarity against the catalog's pre-computed document vectors.
queryaccepts 1-500 charactersscope: "tools"(default) returns individual tool matches;scope: "servers"returns server-level matchescategoryfilter narrows to one ofresearch,government,public-data,utility- Configurable
limit(1-20, default 5) and a server-sideSIMILARITY_FLOORthreshold drop low-confidence hits - Returns
score(cosine similarity in [0, 1]) on every result for trust calibration totalCountreports the count above the floor before the limit was applied
cyanheads_describe_entry
Resolve a name to its install instructions. Accepts either a tool name (snake_case, e.g. earthquake_search) or a server name (kebab-case, e.g. earthquake-mcp-server), up to 64 characters — auto-detected from the format, or pinned via the kind parameter.
- For tools: returns the description and the owning server name
- For servers: returns description, version, npm package, GitHub URL, the full tool list (each tool's name and description), and per-client install snippets — local (stdio, via
npx) for every server, plus remote (Streamable HTTP) when a hosted endpoint exists - Each snippet carries a
transport(stdioorhttp); env vars a local install needs are surfaced and scaffolded into the JSON configs clientfilter narrows snippets to one ofclaude-code,codex,cursor,gemini,streamable-http,curl; omit to return every client- Discriminated output on
kind— callers branch on data, not string parsing
Features
Built on @cyanheads/mcp-ts-core:
- Declarative tool definitions — single file per tool, framework handles registration and validation
- Unified error handling with typed error contracts and recovery hints
- Pluggable auth (
none,jwt,oauth) - Structured logging with optional OpenTelemetry tracing
- Runs locally (stdio/HTTP) or on Cloudflare Workers from the same codebase
Fleet-specific:
- Hourly background catalog refresh with atomic swap on
generatedAtchange — no restart needed when the fleet updates - L2-normalized 256-dim Matryoshka-truncated vectors keep memory under 100KB for a 40-server fleet
- Per-client install snippet generation at describe-time, not catalog-generation time — both local (stdio
npx) and remote (Streamable HTTP) transports, kept in sync with the deployed endpoint - Discriminated
result.kindand typedinstallSnippets[].client/installSnippets[].transportenums — agents can branch reliably
What's in the fleet
100+ MCP servers spanning four categories. Each is open source and individually addressable — cyanheads_describe_entry returns its direct connection URL alongside the install snippet. It also describes this server: ask for cyanheads-mcp-server and you get the front door's own endpoint and install snippets.
| Category | Examples |
|---|---|
| Research | arXiv, bioRxiv, ORCID, Crossref, Wikipedia, Wikidata, OpenLibrary |
| Government | OpenStates, USAspending, CourtListener, NIST NVD, Library of Congress |
| Public Data | Earthquake (USGS), NOAA Weather, GBIF Biodiversity, World Bank, WHO, Eurostat |
| Utility | OpenStreetMap geocoding, Reference Data (constants, timezones, units), WSDOT |
Getting started
Public Hosted Instance
A public instance is available at https://cyanheads.caseyjhand.com/mcp — no installation required. Point any MCP client at it via Streamable HTTP:
{
"mcpServers": {
"cyanheads-mcp-server": {
"type": "streamable-http",
"url": "https://cyanheads.caseyjhand.com/mcp"
}
}
}
For Claude Code:
claude mcp add --transport http cyanheads https://cyanheads.caseyjhand.com/mcp
Self-Hosted / Local
Add the following to your MCP client configuration file.
{
"mcpServers": {
"cyanheads-mcp-server": {
"type": "stdio",
"command": "bunx",
"args": ["@cyanheads/cyanheads-mcp-server@latest"],
"env": {
"MCP_TRANSPORT_TYPE": "stdio",
"MCP_LOG_LEVEL": "info"
}
}
}
}
Or with npx (no Bun required):
{
"mcpServers": {
"cyanheads-mcp-server": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@cyanheads/cyanheads-mcp-server@latest"],
"env": {
"MCP_TRANSPORT_TYPE": "stdio",
"MCP_LOG_LEVEL": "info"
}
}
}
}
Or with Docker:
{
"mcpServers": {
"cyanheads-mcp-server": {
"type": "stdio",
"command": "docker",
"args": ["run", "-i", "--rm", "-e", "MCP_TRANSPORT_TYPE=stdio", "ghcr.io/cyanheads/cyanheads-mcp-server:latest"]
}
}
}
For Streamable HTTP, set the transport and start the server:
MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 bun run start:http
# Server listens at http://localhost:3010/mcp
Prerequisites
- Bun v1.3.0 or higher (or Node.js v24+).
Installation
- Clone the repository:
git clone https://github.com/cyanheads/cyanheads-mcp-server.git
- Navigate into the directory:
cd cyanheads-mcp-server
- Install dependencies:
bun install
Configuration
All configuration is validated at startup via Zod schemas in src/config/server-config.ts. Every variable has a sensible default — out of the box, the server points at the canonical cyanheads fleet.
| Variable | Description | Default |
|---|---|---|
MCP_TRANSPORT_TYPE |
Transport: stdio or http |
stdio |
MCP_HTTP_PORT |
HTTP server port | 3010 |
MCP_HTTP_HOST |
HTTP server bind host | 127.0.0.1 |
MCP_HTTP_ENDPOINT_PATH |
HTTP endpoint path where the MCP server is mounted | /mcp |
MCP_AUTH_MODE |
Authentication: none, jwt, or oauth |
none |
MCP_LOG_LEVEL |
Log level (debug, info, warning, error, etc.) |
info |
CATALOG_URL |
Remote fleet.json endpoint (schema v2 with baked embeddings). Must be an absolute URL. Override to front your own fleet. | https://caseyjhand.com/fleet.json |
CATALOG_FETCH_TIMEOUT_MS |
Per-request timeout for fleet.json fetches in ms. Must be > 0. | 10000 |
CATALOG_REFRESH_SECONDS |
Background poll interval for fleet.json refresh. 0 disables; otherwise must be > 0. |
3600 |
EMBEDDING_MODEL_ID |
Hugging Face model id for query embedding. Must match fleet.json.embeddingModel. |
Snowflake/snowflake-arctic-embed-m-v1.5 |
SIMILARITY_FLOOR |
Cosine similarity cutoff for cyanheads_search_catalog results. Must be within [0, 1]. |
0.3 |
OTEL_ENABLED |
Enable OpenTelemetry | false |
To point at a different catalog, change CATALOG_URL to your own hosted JSON file. See docs/design.md for the producer-side script and schema.
Running the server
Local development
-
Build and run the production version:
# One-time build bun run rebuild # Run the built server bun run start:http # or bun run start:stdio -
Run checks and tests:
bun run devcheck # Lints, formats, type-checks, runs MCP and packaging linters bun run test # Runs the test suite
Project structure
| Directory | Purpose |
|---|---|
src/mcp-server/tools |
Tool definitions (*.tool.ts). Two tools — cyanheads_search_catalog and cyanheads_describe_entry. |
src/services/catalog |
Catalog service — remote fleet.json provider with atomic-swap refresh, vector index, snippet builders, the self-description fallback record, and the query-time embedding runtime (@huggingface/transformers, behind an injectable interface for deterministic tests). |
src/config |
Server-specific environment variable parsing and validation with Zod. |
tests/ |
Unit and integration tests, mirroring the src/ structure. |
docs/ |
Design doc and schema reference. |
Development guide
See CLAUDE.md for development guidelines and architectural rules. The short version:
- Handlers throw, framework catches — no
try/catchin tool logic - Use
ctx.logfor logging,ctx.statefor storage - Register new tools in the
toolsarray passed tocreateApp()insrc/index.ts
Contributing
Issues and pull requests are welcome. Run checks and tests before submitting:
bun run devcheck
bun run test
License
This project is licensed under the Apache 2.0 License. See the LICENSE file for details.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.