How do I install FalkorDB-MCPServer?

Its README did not state an install command plainly enough for us to quote one, so we do not guess. The repository has the instructions: https://github.com/FalkorDB/FalkorDB-MCPServer

What does FalkorDB-MCPServer connect to, and what does it need?

It reaches falkordb. The credentials we found in its source are FALKORDB_PASSWORD and MCP_API_KEY.

Is FalkorDB-MCPServer official and is it maintained?

We found nothing naming it as a vendor’s official server. Its repository has 41 GitHub stars and its state in our directory is listed. Its last commit we recorded was on 2026-10-21.

What licence does FalkorDB-MCPServer use?

The repository declares the MIT licence.

InfratoApp / Resources / MCP servers / FalkorDB-MCPServer

FalkorDB-MCPServer

FalkorDB-MCPServer is an MCP server, listed under mcp tooling. It reaches falkordb. It needs FALKORDB_PASSWORD and MCP_API_KEY to authenticate. Its repository has 41 GitHub stars and is licensed under MIT; we last read it on 2026-10-22.

FalkorDB-MCPServer is an MCP server that connects language models to FalkorDB.

Install

MCP servers are packaged differently from each other -- some run via npx, some as a Docker image, some as a plain script you clone and run. FalkorDB-MCPServer’s own README did not state one plainly enough for this page to quote it rather than guess, so it will not guess. The repository below states it.

Read FalkorDB-MCPServer’s own install instructions ↗

What it reaches, and what it needs

Reaches

falkordb

Credential

FALKORDB_PASSWORD, MCP_API_KEY

Maintenance

Stars

State

listed

Licence

MIT

From the repository

FalkorDB-MCPServer is an MCP (Model Context Protocol) server that connects LLMs to FalkorDB

View on GitHub ↗2026-10-22

What FalkorDB-MCPServer can do

6 tools documented in its README. An AI client calls these by name.

query_graph: Show me all people who know each other
query_graph_readonly: Run a read-only query on the replica instance
list_graphs: List all available graphs
get_graph_schema: Returns node labels, relationship types, and (optionally) the connection topology
get_node_schema: Sample up to `sampleSize` (default `100`) nodes of a given label and rank their property keys by frequency
get_relationship_schema: Sample up to `sampleSize` (default `100`) relationships of a given type and rank their property keys by frequency

Read from the README; names are kept only if the README contains them.