
A discovery layer for the cyanheads MCP ecosystem. Two tools: semantic search across 40+ servers in research, government, public data, and utility categories, plus install snippet generation for any server or tool in the fleet. Search uses Snowflake Arctic embeddings truncated to 256 dimensions, returns cosine similarity scores, and lets you filter by category or scope (tools vs servers). Describe returns connection URLs and per-client config snippets for both stdio and Streamable HTTP transports. The catalog lives at caseyjhand.com/fleet.json with baked embeddings, refreshed hourly. Useful when you need to browse or programmatically discover what's available in the fleet without checking individual repos.
Fleet discovery for the cyanheads MCP ecosystem — semantic search + install snippets.
Public Hosted Server: https://cyanheads.caseyjhand.com/mcp
Fleet discovery for the cyanheads MCP ecosystem, built on a hosted fleet.json catalog of pre-computed tool and server embeddings. Search the catalog by natural-language query, or resolve a known tool or server name to its description, connection URL, and per-client install snippet. Runs as a stdio process, a local Streamable HTTP server, or the public hosted endpoint above.
| 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 description, connection URL, and per-client install snippet for a named tool or server. |
cyanheads_search_catalog toolquery 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 1–20 (default 5).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.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.cyanheads_describe_entry toolname 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, codex, cursor, gemini, streamable-http, or curl.client: "curl" returns successful metadata with an installNotice naming a stdio client to try. Required environment variables remain visible even without snippets.tools/list.not_found, ambiguous_kind (set kind), or retryable catalog_empty.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:
CATALOG_REFRESH_SECONDS, default 3600) with an atomic index swap when generatedAt changes — no restart needed@huggingface/transformers; document embeddings are pre-computed, L2-normalized, and Matryoshka-truncated, shipped inside fleet.jsonfetch — avoids a cold-cache model-load failure under OTELcyanheads_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 itCATALOG_URL can point at any endpoint serving the same schema, to front a custom fleetAgent-friendly output:
result.kind (tool | server) on cyanheads_describe_entry lets callers branch on data, not string parsingscore field for trust calibration, plus a servers roll-up so agents can see which servers matched without a second callA 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
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
git clone https://github.com/cyanheads/cyanheads-mcp-server.git
cd cyanheads-mcp-server
bun install
cp .env.example .env
# edit .env to override any defaults
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_SESSION_MODE | HTTP session posture: auto, stateful, or stateless. src/index.ts declares stateless; set this only to override it. | stateless |
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 |
OTEL_EXPORTER_OTLP_ENDPOINT | OTLP base URL for traces and metrics | Unset |
OTEL_EXPORTER_OTLP_LOGS_ENDPOINT | Explicit OTLP logs URL; requires the OTel log peers included in the default Docker build | Unset |
LOG_TOOL_FAILURE_PAYLOADS | Log failed arguments and results, redacted by key name. Secrets inside free-form values are not redacted. | false |
LOG_TOOL_FAILURE_PAYLOAD_MAX_BYTES | UTF-8 byte cap for each logged failure payload | 16384 |
See .env.example for the full list of optional overrides.
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 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.
| 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. |
See CLAUDE.md for development guidelines and architectural rules. The short version:
try/catch in tool logicctx.log for logging, ctx.state for storagetools array passed to createApp() in src/index.tsIssues are welcome. Run checks and tests before submitting:
bun run devcheck
bun run test
Apache-2.0 — see LICENSE for details.
MCP_LOG_LEVELdefault: infoMinimum log level: debug, info, notice, warning, error.
CATALOG_URLdefault: https://caseyjhand.com/fleet.jsonRemote fleet.json endpoint (schema v2 with baked embeddings).
CATALOG_REFRESH_SECONDSdefault: 3600Background poll interval for fleet.json refresh. 0 disables.
EMBEDDING_MODEL_IDdefault: Snowflake/snowflake-arctic-embed-m-v1.5Hugging Face model id for query embedding. Must match fleet.json.embeddingModel.
SIMILARITY_FLOORdefault: 0.3Cosine similarity cutoff for cyanheads_search results (0-1).
MCP_HTTP_HOSTdefault: 127.0.0.1Hostname for the HTTP server.
MCP_HTTP_PORTdefault: 3010Port to run the HTTP server on.
MCP_HTTP_ENDPOINT_PATHdefault: /mcpEndpoint path for the MCP server.
MCP_AUTH_MODEdefault: noneAuthentication mode: none, jwt, or oauth.