LabscoMCP early access ↗
daanrongenMCP SERVER

Neo4j MCP by daanrongen

Runs Cypher against Neo4j and shows you the schema first — eight tools, with the read-only query kept separate.

NoSQL, Graph & Key-Value StoresCommunity

LABSCO SUMMARY

The read-only query is a separate tool.

Having run_read_query beside run_query is what makes this comfortable to hand to an assistant: exploration goes through the read tool, and writes need the tool that says so. The schema tools are the other half of that — labels, relationship types, indexes and constraints let a model compose a query against the graph as it actually is rather than as it assumes.

What it is

An MCP server for Neo4j over stdio. It splits the surface into three parts: running Cypher, inspecting the graph's schema, and reading server information — so an assistant can find its way around a graph before querying it.

What you get

  • Cypher execution with the read path kept separate — run_query and run_read_query
  • Schema inspection: the schema itself, node labels and relationship types — get_schema, get_labels, get_relationship_types
  • The metadata that decides whether a query will be fast — get_indexes, get_constraints
  • The server's address and version — get_server_info
  • An install with no build step — bunx @daanrongen/neo4j-mcp
  • A local inspector run — bun run build && bun run inspect — that lists every tool and shows request and response shapes

Requirements

A reachable Neo4j instance and two environment variables: NEO4J_URL, a Bolt URL such as bolt://localhost:7687 or neo4j://localhost:7687, and NEO4J_PASSWORD, with the username defaulting to neo4j. Bun on the machine to run bunx; the documented setups are a Claude Desktop stdio entry and a one-line claude mcp add for the CLI. The package is @daanrongen/neo4j-mcp 1.1.4.

Setup effort

One command plus credentials — bunx @daanrongen/neo4j-mcp, then supply credentials

See installation options