mcpField
C
cyanheads-mcp-server

cyanheads-mcp-server

Remote
github.com/cyanheadsDeveloper Tools1Updated today
Repository

About cyanheads-mcp-server

A semantic catalog for discovering tools and servers across the cyanheads MCP fleet. It returns ranked matches and can provide descriptions, connection details, and client-specific installation snippets.

Key features

  1. 01Search tools and servers with natural-language queries
  2. 02Rank matches by semantic similarity
  3. 03Retrieve entry descriptions and connection URLs
  4. 04Generate per-client installation snippets
  5. 05Refresh the catalog in the background

Use cases

  1. 01Find an MCP tool for a described task
  2. 02Identify which server owns a matching tool
  3. 03Get connection and setup details for a catalog entry

MCP support

Exposes catalog search and entry-description tools to MCP clients, including connection URLs and installation snippets. Supports STDIO and Streamable HTTP transports.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://cyanheads.caseyjhand.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Packages
npm@cyanheads/cyanheads-mcp-server0.5.0

Tools

2
ParameterTypeRequiredDescription
limitintegerNoMaximum number of results to return (1-20). Default 5.
querystringYesNatural language search query. Describe what you want to accomplish, a workflow, or a capability area. 1-500 raw characters; surrounding whitespace is trimmed. Must contain non-whitespace text.
scopeenumNoWhat to search. "tools" returns individual tool matches; "servers" returns server-level matches.tools | servers
offsetintegerNoResult offset. Use nextOffset with the same query, scope, category, and limit; pages use the current catalog.
categoryenumNoFilter by catalog category. Omit to search all categories.research | government | public-data | utility
serversOffsetintegerNoIndependent server roll-up offset (10 per page). Use nextServersOffset; must be zero in servers scope.

Details

From the project README

@cyanheads/cyanheads-mcp-server

Fleet discovery for the cyanheads MCP ecosystem — semantic search + install snippets.

2 Tools • 0 Resources • 0 Prompts

Version License Docker MCP SDK npm TypeScript Bun

Install in Claude Desktop Install in Cursor Install in VS Code

Framework

Public Hosted Server: https://cyanheads.caseyjhand.com/mcp


Overview

Find the right MCP tool for the job across the cyanheads fleet. Describe a task in plain language to search every tool and server, then get a description, connection URL, and install snippet for your client.

Tools
ToolDescription
cyanheads_search_catalogSearch fleet tools and servers by natural-language query. Returns ranked matches with brief summaries and the owning server.
cyanheads_describe_entryReturn the description, connection URL, and per-client install snippet for a named tool or server.

Capability reference

cyanheads_search_catalog tool
  • query 1–500 raw characters, with non-whitespace text required; surrounding whitespace is trimmed before embedding and echo. scope selects tools (default) or servers; optional category: research, government, public-data, utility; limit 1–1000 (default 5), served at most 20 per call: when a larger limit leaves matches past the page, the response adds truncated, shown, cap, and a notice naming the offset to continue from.
  • Results carry cosine-similarity score ([0, 1], comparable within one response). Tool searches include a servers roll-up with ten entries per page and serversTotal; an unloaded catalog returns retryable catalog_empty.
  • Page results with offset and the tools-scope roll-up independently with serversOffset (both default to 0). Reuse the same query, scope, category, and limit with nextOffset / nextServersOffset; null means exhausted. Each call uses the current catalog, so a refresh between pages can change ordering. Servers scope requires serversOffset: 0 and omits roll-up fields.
  • SIMILARITY_FLOOR (default 0.3) filters matches before the limit applies.
  • An empty category string is treated as omitted; other unknown category values are rejected.

cyanheads_describe_entry tool
  • name 1–64 characters accepts a tool or server name, auto-detected or pinned via kind. Exact names win, then unique case-insensitive names; output uses canonical names. client optionally selects claude-code, cline, codex, cursor, gemini, streamable-http (generic mcpServers JSON), or curl.
  • server (optional, 1–64 characters) names the owning server: a search result's name + server describes exactly that row, in either scope. It is required when more than one server owns the tool name; with a server name, it must name the same server.
  • Empty kind, client, and server strings are treated as omitted. Other unknown kind or client values are rejected.
  • Both kinds return connection metadata and install snippets; server results also include the full tool inventory. Published servers get local snippets; hosted servers also get HTTP snippets. For local-only entries, client: "curl" returns successful metadata with an installNotice naming a stdio client to try. Required environment variables remain visible even without snippets.
  • Descriptions are catalog text; obtain tool schemas from the connected server's tools/list.
  • Failures return not_found, ambiguous_kind (set kind), ambiguous_owner (set server; the error lists the owners), or retryable catalog_empty.

Features

Built on @cyanheads/mcp-ts-core: stdio and Streamable HTTP transports, pluggable auth (none / jwt / oauth), swappable storage (in-memory, filesystem, Supabase, Cloudflare KV/R2/D1), structured logging with optional OpenTelemetry tracing.

Catalog-specific:

  • Hourly background catalog refresh (CATALOG_REFRESH_SECONDS, default 3600) with an atomic index swap when generatedAt changes — no restart needed
  • Empty catalogs, conflicting duplicate identities, and vectors that can't be normalized (wrong dimension, all zeros, or a non-finite component) fail before index replacement; refresh retains the last valid catalog. Identical duplicates collapse before indexing, with a bounded load-time warning; servers with no tools remain valid.
  • Query embeddings are computed at request time via @huggingface/transformers; document embeddings are pre-computed, L2-normalized, and Matryoshka-truncated, shipped inside fleet.json. The server normalizes each document vector again at load, so scores stay cosine similarities even when a catalog's vectors drift from unit length, and a bounded warning names vectors more than 1e-4 off.
  • The embedding model is warmed up during startup, before OpenTelemetry's HTTP instrumentation patches fetch — avoids a cold-cache model-load failure under OTEL
  • Self-describing: cyanheads_describe_entry resolves this server's own name and tools from a static fallback record, consulted only when the remote catalog doesn't carry an entry for it
  • CATALOG_URL can point at any endpoint serving the same schema, to front a custom fleet

Agent-friendly output:

  • Search responses echo the effective query, report the total match count before the limit, include broadening guidance when nothing matches, and name the offset to continue from when a limit above 20 is cut to the per-call cap
  • Discriminated result.kind (tool | server) on cyanheads_describe_entry lets callers branch on data, not string parsing
  • Every search result carries a score field for trust calibration, plus a servers roll-up so agents can see which servers matched without a second call

Getting started

Public Hosted Instance

A public instance is available at https://cyanheads.caseyjhand.com/mcp — no installation required. It serves Streamable HTTP; each client takes its own config shape.

For Claude Code:

claude mcp add --transport http cyanheads https://cyanheads.caseyjhand.com/mcp

For Cline (cline_mcp_settings.json):

{
  "mcpServers": {
    "cyanheads-mcp-server": {
      "type": "streamableHttp",
      "url": "https://cyanheads.caseyjhand.com/mcp"
    }
  }
}

For Cursor (mcp.json):

{
  "mcpServers": {
    "cyanheads-mcp-server": {
      "url": "https://cyanheads.caseyjhand.com/mcp"
    }
  }
}

Claude Desktop adds remote servers under Settings → Connectors.

Claude Desktop bundle

Download the MCPB bundle for a local stdio install. It includes ONNX WebAssembly inference, so it does not need platform-specific native libraries. The first start downloads the embedding model; subsequent starts reuse the model cache. npm and Docker installs use native CPU inference.

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
Installation
  1. Clone the repository:
git clone https://github.com/cyanheads/cyanheads-mcp-server.git
  1. Navigate into the directory:
cd cyanheads-mcp-server
  1. Install dependencies:
bun install
  1. Configure environment:
cp .env.example .env
# edit .env to override any defaults

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.

VariableDescriptionDefault
MCP_TRANSPORT_TYPETransport: stdio or httpstdio
MCP_HTTP_PORTHTTP server port3010
MCP_HTTP_HOSTHTTP server bind host127.0.0.1
MCP_HTTP_ENDPOINT_PATHHTTP endpoint path where the MCP server is mounted/mcp
MCP_AUTH_MODEAuthentication: none, jwt, or oauthnone
MCP_SESSION_MODEHTTP session posture: auto, stateful, or stateless. src/index.ts declares stateless; set this only to override it.stateless
MCP_LOG_LEVELLog level (debug, info, warning, error, etc.)info
CATALOG_URLRemote 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_MSPer-request timeout for fleet.json fetches: integer milliseconds, 1–2147483647.10000
CATALOG_REFRESH_SECONDSBackground poll interval for fleet.json refresh. 0 disables; positive values up to 2147483.647 seconds use the runtime's millisecond timer resolution.3600
EMBEDDING_MODEL_IDHugging Face model id for query embedding. Must match fleet.json.embeddingModel.Snowflake/snowflake-arctic-embed-m-v1.5
SIMILARITY_FLOORCosine similarity cutoff for cyanheads_search_catalog results. Must be within [0, 1].0.3
OTEL_ENABLEDEnable OpenTelemetryfalse
OTEL_EXPORTER_OTLP_ENDPOINTOTLP base URL for traces and metricsUnset
OTEL_EXPORTER_OTLP_LOGS_ENDPOINTExplicit OTLP logs URL; requires the OTel log peers included in the default Docker buildUnset
LOG_TOOL_FAILURE_PAYLOADSLog failed arguments and results, redacted by key name. Secrets inside free-form values are not redacted.false
LOG_TOOL_FAILURE_PAYLOAD_MAX_BYTESUTF-8 byte cap for each logged failure payload16384

See .env.example for the full list of optional overrides.

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
    
Docker
docker build -t cyanheads-mcp-server .
docker run --rm -p 3010:3010 cyanheads-mcp-server

The Dockerfile defaults to HTTP transport, stateless session mode, and logs to /var/log/cyanheads-mcp-server. OpenTelemetry peer dependencies are installed by default — build with --build-arg OTEL_ENABLED=false to omit them.

Project structure

DirectoryPurpose
src/mcp-server/toolsTool definitions (*.tool.ts). Two tools — cyanheads_search_catalog and cyanheads_describe_entry.
src/services/catalogCatalog 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/configServer-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/catch in tool logic
  • Use ctx.log for logging, ctx.state for storage
  • Register new tools in the tools array passed to createApp() in src/index.ts
  • Wrap external data: validate raw → normalize to domain type → return output schema; never fabricate missing fields

Contributing

Issues are welcome. Run checks and tests before submitting:

bun run devcheck
bun run test

License

Apache-2.0 — see LICENSE for details.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.