MCP server for FalkorDB — exposes graph query and management tools to LLM agents
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"mcp-server-falkordb","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# mcp-server-falkordb [](https://pypi.org/project/mcp-server-falkordb/) [](https://pypi.org/project/mcp-server-falkordb/) [](https://opensource.org/licenses/MIT) [](https://modelcontextprotocol.io/) MCP server for [FalkorDB](https://falkordb.com/) — a property graph database built on Redis. Connects LLM agents (Claude, or any MCP client) to a running FalkorDB instance via 6 agent-centric tools covering graph discovery, read queries, writes, and schema inspection. ## Quick Start One-block install + first call: ```bash # 1. Start FalkorDB (if not already running) docker run -d -p 6379:6379 falkordb/falkordb # 2. Register the MCP in Claude Code claude mcp add falkordb -- uvx mcp-server-falkordb # 3. From your agent: explore a graph # (Claude will call: graph_explore(graph="my_graph")) ``` That's it. Six graph tools now available to any MCP-compatible agent. ## Tools | Tool | Purpose | Destructive? | |------|---------|--------------| | `graph_list` | List all graphs with names | No | | `graph_describe` | Full schema: labels, rel types, property keys, counts | No | | `graph_query` | Execute read-only Cypher (write keywords rejected) | No | | `graph_mutate` | Execute write Cypher (CREATE, MERGE, SET, DELETE, REMOVE) | Yes | | `graph_explore` | One-call overview: schema + 3 sample nodes + 3 sample edges | No | | `graph_delete` | Drop an entire graph (requires `confirm: true`) | Yes — irreversible | **Not in v1** (by design): - No direct node/edge CRUD — Cypher via `graph_mutate` is more powerful and honest - No index management — advanced, add via `graph_mutate` when needed - No backup/restore — use `docker exec` + RDB snapshots ## Installation ### Requirements - Python 3.12+ - Runni…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.