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.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。