Skip to main content
Glama
nd-wuangr26

Knowledge Graph Builder MCP Server

by nd-wuangr26
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Knowledge Graph Builder

Documents (.pdf/.docx/.txt/.md) or raw text -> entities/relationships (via LLM) -> Neo4j. Architecture inspired by Graphiti: episode-based ingestion, Pydantic entity/edge models, pluggable LLM provider.

Setup

docker compose up -d neo4j          # Neo4j at bolt://localhost:7687, browser at :7474
cp .env.example .env                # fill in ANTHROPIC_API_KEY or OPENAI_API_KEY, set LLM_PROVIDER
pip install -e ".[dev]"

Related MCP server: Knowledge Graph Builder

Usage

kg ingest path/to/document.pdf      # input option 1: CLI
kg serve-mcp                        # input option 2: MCP server (ingest_document, ingest_text,
                                     # search_entities, get_episode tools)

Logs

Every pipeline run writes one JSON line per phase to logs/pipeline.jsonl, tagged with run_id and episode_id:

tail -f logs/pipeline.jsonl | jq
grep '"run_id":"<id>"' logs/pipeline.jsonl | jq

Extending

  • New entity type: subclass BaseNode in src/kg/models/entities.py, add it to ENTITY_TYPES.

  • New document format: add a _load_x(path) -> str function in src/kg/ingestion/loaders.py and register its extension in LOADERS.

  • New LLM provider: subclass LLMClient in src/kg/llm/, add a branch in get_llm_client() (src/kg/llm/base.py) and matching config in src/kg/config.py.

Tests

pytest                     # model/chunker/extraction-schema tests need no external services
                            # test_writer.py needs `docker compose up -d neo4j` and skips otherwise

Known v1 limitations (documented, not hidden)

  • Entity resolution is exact (name, entity_type) match only — no fuzzy/embedding dedupe yet (src/kg/graph/resolver.py).

  • Search is Cypher CONTAINS, not vector/hybrid search.

  • Single graph backend (Neo4j) — no multi-backend abstraction since nothing else was requested.

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivitySlowing
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Neo4j Knowledge Graph

    mjftw
    F
    license
    Not graded
    quality
    D
    maintenance
    Enables storage and retrieval of knowledge in a graph database format, allowing users to create, update, search, and delete entities and relationships in a Neo4j-powered knowledge graph through natural language.
    5
    -

  • Knowledge Graph Builder

    rebots-online
    F
    license
    Not graded
    quality
    D
    maintenance
    Transforms text or web content into structured knowledge graphs using local AI models with MCP integration for persistent storage in Neo4j and Qdrant.
    4
    -

  • GraphRAG MCP Server

    lemondude21
    F
    license
    Not graded
    quality
    C
    maintenance
    Enables building and querying knowledge graphs by ingesting documents into Neo4j using Gemini for entity extraction, and exposes MCP tools for graph health, document ingestion, and knowledge base querying.
    -