grag-mcp
PulseGate's liveness check found it on 4 Oct 2026; it is registered on GitHub and PyPI and has been in the index since 4 Sep 2026. How this is checked
grag-mcp is an open-source graph RAG knowledge base for coding agents. It stores and retrieves connected knowledge with Neo4j and exposes the system through the Model Context Protocol for agent use.
Inferred · not functionally tested
Overview
6 featuresPurpose: Giving coding agents persistent, graph-based knowledge retrieval through a self-hosted MCP service.
Inferred · not functionally tested
Audience: developers building coding agents
Inferred · not functionally tested
Functions: rag, agents
Inferred · not functionally tested
Interfaces: API: indicated (inferred, not tested) · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)
Recorded constraints: pricing: open_source · license: Apache-2.0 · platforms: CLI · deployment: cli, self_hosted, api_only
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: pypi.org · github.com. These links do not verify the individual claims.
grag-mcp is a RAG, search & retrieval project. Inferred · not functionally tested: It focuses on giving coding agents persistent, graph-based knowledge retrieval through a self-hosted MCP service. Inferred · not functionally tested: It is built as an open-source project for developers building coding agents. Basis unknown · not verified: The project is open source (Apache-2.0). Basis unknown · not verified: It ships for the command line and API, and it can be self-hosted.
tmustafiz builds and maintains grag-mcp, and it first shipped in 2026. The project is developed in the open on GitHub with 43 commits in the last 90 days. Inferred · not functionally tested: Among its 6 catalogued features are Graph RAG, knowledge graph, and agent memory. Inferred · not functionally tested: Catalogued interfaces include an MCP server.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- Graph RAG
- Knowledge graph
- Agent memory
- Neo4j backend
- MCP server
- Codebase retrieval
Topics: Inferred · not functionally tested
Built with & integrations
Trust & compliance
Indexing history
1What PulseGate has recorded for this listing
Frequently asked questions about grag-mcp
- What does grag-mcp do?
- Inferred · not functionally tested: Grag-mcp focuses on giving coding agents persistent, graph-based knowledge retrieval through a self-hosted MCP service. It is catalogued under RAG, search & retrieval on PulseGate.
- Who should use grag-mcp?
- Inferred · not functionally tested: grag-mcp is an open-source project built for developers building coding agents.
- Is grag-mcp free?
- Basis unknown · not verified: Yes — grag-mcp is open source under the Apache-2.0 license and free to use.
- What platforms does grag-mcp run on?
- Basis unknown · not verified: grag-mcp runs on the command line and API. It can also be self-hosted.
- Is grag-mcp still maintained?
- PulseGate's liveness check found it on 4 Oct 2026. Its GitHub repository shows 43 commits in the last 90 days.
- What are alternatives to grag-mcp?
- Similar projects tracked by PulseGate include mcp-agensgraph-memory, ogmem-rag-mcp, and mcp-agensgraph-cypher.mcp-agensgraph-memoryogmem-rag-mcpmcp-agensgraph-cypher
- Who develops grag-mcp?
- grag-mcp is developed by tmustafiz.
- When did grag-mcp launch?
- grag-mcp first shipped in 2026.
Similar projects
Closest matches by what these projects do