Loading…
Self-hosted web research for MCP agents.
io.github.MarcellM01/tinysearch is an MCP server entry in ChatHome Skills, sourced from Official MCP Registry and scored 64/100. As a Model Context Protocol server, it exposes tools that MCP-compatible LLM clients such as Claude, Cursor, and Copilot can call directly, extending an agent's reach beyond its built-in capabilities. ChatHome Skills discovered this entry through its daily ingest of official registries and GitHub discovery queries, and re-verifies repository facts, freshness signals, and install metadata on every run. The quality score weighs official-registry presence, a working install command, license clarity, GitHub star trajectory, and repository freshness — the full formula is on the Sources page. The install command above is ready to copy. Review the last-pushed date and repository status before adding io.github.MarcellM01/tinysearch to a production agent workflow; the snapshot facts below are point-in-time values from the most recent ingest.
docker run -i --rm docker.io/marcellm01/tinysearch:v0.4.0Review the upstream source before running this command.
{
"_meta": {
"io.modelcontextprotocol.registry/official": {
"status": "active",
"isLatest": true,
"updatedAt": "2026-07-27T19:47:32.371997Z",
"publishedAt": "2026-07-27T19:47:32.371997Z",
"statusChangedAt": "2026-07-27T19:47:32.371997Z"
}
},
"server": {
"name": "io.github.MarcellM01/tinysearch",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"version": "0.4.0",
"packages": [
{
"transport": {
"type": "stdio"
},
"identifier": "docker.io/marcellm01/tinysearch:v0.4.0",
"registryType": "oci",
"environmentVariables": [
{
"name": "MCP_TRANSPORT",
"description": "MCP transport to serve: stdio (default), sse, or streamable-http."
},
{
"name": "TINYSEARCH_CONFIG_PATH",
"description": "Path to a tinysearch_config.json inside the container, for overriding search/embedding defaults."
},
{
"name": "SEARXNG_URL",
"description": "SearXNG search endpoint URL. Only needed if not using the bundled Compose SearXNG service."
},
{
"name": "TINYSEARCH_EMBEDDING_BACKEND",
"description": "Embedding implementation: onnx (default) or openai_compatible."
},
{
"name": "TINYSEARCH_EMBEDDING_MODEL",
"description": "Local ONNX preset (fast, balanced, quality) or a Hugging Face ONNX repository id."
}
]
},
{
"version": "0.4.0",
"transport": {
"type": "stdio"
},
"identifier": "tinysuite-search",
"registryType": "pypi"
}
],
"repository": {
"id": "1237429296",
"url": "https://github.com/MarcellM01/TinySearch",
"source": "github"
},
"websiteUrl": "https://github.com/MarcellM01/TinySearch",
"description": "Self-hosted web research for MCP agents."
}
}