DocSmith MCP Server

MCP (Model Context Protocol) server that exposes DocSmith's semantic search and knowledge graph as tools for AI agents.

Tools

semantic_search

Search documents by semantic similarity with multiple retrieval strategies.

• Strategies: vanilla (cosine similarity), hyde (hypothetical document embeddings), query_fusion (multi-query + RRF)

• Features: metadata filters, context expansion (section/parent/neighbor), graph expansion (breadcrumbs + related entities), cross-encoder reranking

graph_query

Execute read-only Cypher queries against the Neo4j knowledge graph.

• Schema: 6 node types (Entity, Document, Section, Chunk, Cluster, Collection), 9 relationship types

• Patterns: entity relationships, cross-document connections, multi-hop traversal, document hierarchy

• Safety: write operations blocked, $collection_id auto-injected

keyword_search

Exact text matching for error codes, identifiers, and literal strings.

Related MCP server: Dedalus MCP Documentation Server

Knowledge Graph Schema

(Document)-[:CONTAINS]->(Section)-[:CONTAINS]->(Chunk)
(Chunk)-[:MENTIONS]->(Entity)
(Entity)-[:EXTRACTED_FROM]->(Document)
(Entity)-[:RELATED_TO {predicate, confidence}]->(Entity)
(Document)-[:BELONGS_TO]->(Cluster)

Important: canonical_name is always lowercase — use toLower() when matching entities.

Setup

# Install dependencies
uv sync

# Configure environment
cp .env.example .env
# Edit .env with your DocSmith API URL, API key, and collection ID

# Run the server
uv run uvicorn server:app --host 0.0.0.0 --port 8005

Testing with MCP Inspector

npx @modelcontextprotocol/inspector
# Connect to: http://localhost:8005/mcp (Streamable HTTP transport)

See TESTS-MCP.txt for validated test cases.

Configuration

Stack

• Python 3.12

• FastMCP (MCP SDK)

• Starlette (Streamable HTTP transport)

• httpx (async HTTP client)

License

MIT