Schema | sqlite-rag-mcp

sqlite-rag-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`OLLAMA_HOST`	No	Ollama endpoint	http://localhost:11434
`SQLITE_RAG_DB`	No	Index database path	~/.local/share/sqlite-rag-mcp/index.db
`SQLITE_RAG_EMBED_MODEL`	No	Embedding model	nomic-embed-text
`SQLITE_RAG_CHUNK_TOKENS`	No	Chunk size (approx. tokens)	800
`SQLITE_RAG_CHUNK_OVERLAP`	No	Chunk overlap (approx. tokens)	100

Features and capabilities supported by this server

Capability	Details
`tools`	{ "listChanged": false }
`prompts`	{ "listChanged": false }
`resources`	{ "subscribe": false, "listChanged": false }
`experimental`	{}

Functions exposed to the LLM to take actions

Name	Description
index_documentsA	Index text/markdown files from a directory into the local SQLite index. Args: path: Directory to index (absolute or ~-expanded). glob: Glob pattern relative to the directory (default '*/.md'). Use e.g. '*/.txt' or '*/' for other text files.
searchA	Search the indexed documents. Args: query: Natural-language query or keywords. k: Number of results to return (1-50, default 8). mode: 'hybrid' (RRF fusion of semantic + lexical, default), 'semantic' (vector KNN only), or 'lexical' (FTS5 BM25 only). If Ollama is offline, hybrid/semantic fall back to lexical and a warning is included in the response.
get_chunkA	Fetch the full text and source of a chunk returned by search.
statsB	Index statistics: document/chunk/embedding counts and configuration.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/giuseppeferretti/sqlite-rag-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server