GraphRAG Llama Index MCP Server
This server provides a GraphRAG (Graph-based Retrieval Augmented Generation) engine for indexing documents, building knowledge graphs, and querying/analyzing them through multiple search modes and graph exploration.
Keyword Search (
keyword_lookup): Exact BM25-based retrieval for specific terms, ticker symbols (e.g., ASTS, RKLB), acronyms, or product names.Entity Relationship Search (
entity_connections): Query the knowledge graph to discover entities, their relationships, competitive landscapes, and connections within the corpus.Thematic Overview (
thematic_overview): Retrieve high-level patterns, trends, and macro narratives across the entire document corpus — useful for sector analysis and broad topic exploration.Entity Graph Exploration (
explore_entity_graph): Traverse the knowledge graph from a specific named entity, exploring direct connections up to 3 hops away — useful for building reasoning chains or verifying facts.Corpus Statistics (
get_corpus_stats): Retrieve health and scale metrics including counts of documents, chunks, entities, and relationships.Index Documents: Ingest local documents into a knowledge graph using a full ML indexing pipeline.
Manage Databases: Initialize, list, check status, and delete knowledge base entries via CLI.
Deploy to Cloud: Supports deployment to Fly.io and AWS (ECR, S3, App Runner) with a lightweight ~1GB query server footprint.
Integrate with MCP-compatible agents (e.g., Claude Desktop, Cursor) to give AI assistants access to your document knowledge base.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@GraphRAG Llama Index MCP Server search for recent acquisitions in the AI chip industry"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
GraphRAG LlamaIndex
Full-stack GraphRAG engine optimized for local indexing and lightweight cloud querying. Built on DuckDB, LlamaIndex, and the Model Context Protocol (MCP).
1. Context
This project implements a Decoupled Architecture:
Indexer (Image A): Heavy-duty ML environment (PyTorch, GLiNER) for local graph construction.
Query (Image B): Lightweight API environment (Node.js, DuckDB) for fast cloud deployment (~1GB footprint).
Related MCP server: Mnemosyne MCP
2. Building the Images
# Build specialized images via Docker Compose
docker compose build3. Running Indexer & Query
Load the shell aliases for the fastest workflow:
macOS (Zsh):
source .graphrag-alias.zshWSL/Bash:
source .graphrag-alias.shPowerShell:
. .\.graphrag-alias.ps1
Indexing Documents
# 1. Initialize a database entry
graphrag start my_project --source /app/documents/source_files
# 2. Run the ingestion pipeline (Indexer Image)
graphrag index my_project [--reset] [--prune]Querying
# CLI Search (Query Image)
graphrag search my_project "What are the common themes?"
# Start MCP Server for Agents
docker compose up query4. Deployment Folder
deployment/fly/: Scripts for zero-latency hosting on Fly.io (optimized for free-tier fly-machines).deployment/aws/: Infrastructure scripts for ECR, S3 backups, and App Runner deployments.
5. Setup & Configuration
Environment (.env)
Copy .env.example and set:
OPENAI_API_KEY: For LLM reasoning and extraction.DOCUMENTS_HOME: Absolute path to your local data folder (mapped to/app/documentsin Docker).
Engine Configuration (core/graphrag_config.py)
Tweak these parameters to refine performance:
SearchType: Switch betweenentity_connections(graph-heavy) orthematic_overview(summary-heavy).ExtractionMode: Choosellm(creative) orgliner(fast/cost-effective).
6. Local Integration & Testing
Integrate this project as an MCP Server in Desktop Agents (Claude Desktop, Cursor, etc.) to give them memory of your documents.
Add to your MCP Config:
{
"mcpServers": {
"graphrag": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-v",
"C:/Users/<USER>/.graphrag:/root/.graphrag",
"graphrag-query"
]
}
}
}7. Database Cheatsheet
Core Commands
graphrag list: Show all registered databases.graphrag status <db>: Check entity/relationship counts and health.graphrag delete <db> [--files]: Unregister database entry and optionally remove physical files.graphrag index <db> [--reset]: Index documents into database (use--resetto skip duplicate checks).
Managed Storage Workflow
To keep your project portable, move database files into a Managed/ folder inside your data directory.
Manual Move:
Move
your_db.duckdbto[DOCUMENTS_HOME]/Managed/.Re-register the path:
graphrag register my_db --db-path /app/documents/Managed/your_db.duckdbFor S3 management see S3_CHEATSHEET.md.
Available Tools
3 toolsexplore_entity_graphA
Traverse the knowledge graph starting from a specific entity. Returns the entity, its direct connections (other entities), and the relationships between them. Use this to build reasoning chains or verify facts about a known entity.
Inputs: entityName (required), hops.
get_corpus_statsA
Get statistics about the indexed knowledge base. Returns counts of documents, chunks, entities, and relationships. Use for corpus health checks or to understand the scale of available data.
Inputs: no named parameters.
searchA
Search the GraphRAG knowledge base with THREE distinct modes:
CRITICAL: For ticker symbols (ASTS, RKLB, NBIS) or acronyms, ALWAYS use 'keyword_lookup' FIRST. Semantic search (entity_connections/thematic_overview) can MISS exact ticker matches.
Workflow:
Ticker/Acronym Query → Use 'keyword_lookup' to find raw mentions
If found → Extract entity names from results
Then use 'entity_connections' or 'thematic_overview' with full entity names for deeper analysis
Mode Selection Guide:
'keyword_lookup': Direct BM25 retrieval for EXACT terms (tickers, acronyms, specific names) → Returns: Raw text chunks containing the literal search term → Use for: ASTS, NYSE:RKLB, "Direct-to-Cell", specific product names
'entity_connections': Find entities and their knowledge graph relationships → Returns: Entities + relationships + supporting chunks → Use for: Company relationships, competitive landscape, partnerships → Example: After finding 'AST SpaceMobile' via keyword_lookup, search 'AST SpaceMobile competitors partners'
'thematic_overview': High-level patterns and trends across corpus → Returns: Broad thematic context → Use for: Industry trends, macro narratives, sector analysis → Example: 'satellite telecommunications market trends'
Inputs: query (required), mode, topK.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose with no ambiguity: explore_entity_graph is for graph traversal from a specific entity, get_corpus_stats is for corpus-level statistics, and search is for querying the knowledge base with three distinct modes (keyword_lookup, entity_connections, thematic_overview). The tools do not overlap in functionality.
The tool names follow a consistent snake_case pattern (explore_entity_graph, get_corpus_stats, search), but 'search' is a generic verb compared to the more descriptive 'explore' and 'get', which is a minor deviation. Overall, the naming is predictable and readable.
With only 3 tools, the server feels thin for a GraphRAG system, as it might lack operations like updating or managing the knowledge base. However, the tools cover core query and exploration functions, making it borderline appropriate for basic usage.
The tool surface covers key operations for querying and exploring a GraphRAG knowledge base, including graph traversal, corpus statistics, and multi-mode search. Minor gaps exist, such as no tools for adding or modifying data, but agents can work around this for read-only analysis.
Maintenance
Related MCP Connectors
Private, multimodal knowledge store for agents: hybrid search with cited, provenance-backed results.
Cloud or self-hosted knowledge for AI agents: hybrid search, reranking, GraphRAG, scoped MCP tools.
Persistent memory and knowledge graphs for AI agents. Hybrid search, context checkpoints, and more.
Persistent memory and knowledge management for AI agents with semantic search and 50+ tools.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables semantic search and question answering over a knowledge base using hybrid retrieval and grounded answers, all running offline with no API keys.4MIT
- AlicenseBqualityDmaintenanceProvides persistent knowledge graph memory for AI agents with local semantic search using Neo4j and ONNX embeddings, enabling offline operation with zero API costs.1720 npmMIT
- AlicenseAqualityBmaintenanceEnables local AI agents to perform hybrid search (BM25 + vector) over privately indexed local files, including notes, PDFs, DOCX, source code, and OCR'd images. All indexing and retrieval stay on the machine with read-only, whitelist-scoped access.3MIT
- AlicenseNot gradedqualityNot gradedmaintenanceEnables agents to build and query structured semantic graphs, extracting, traversing and multi-hop reasoning over entity-relation-object triples while producing Cypher and JSON-LD graph output. It also combines BM25 lexical and dense vector retrieval with rank fusion, semantic caching and context reordering for grounded agentic memory.MIT