KuzuDB
MCP server implementation by jordanburke that provides AI assistants with direct access to Kuzu graph databases through Cypher query execution, schema introspection, and database management operations. Built with TypeScript and featuring comprehensive error handling, the implementation includes multi-agent coordination through file-based write locking to handle Kuzu's single-writer limitation, automatic connection recovery with exponential backoff, and workarounds for specific Kuzu DDL bugs including timeout handling for hanging getAll() operations. The server supports multiple deployment modes including HTTP transport for web integration, Docker containerization, and Smithery platform deployment, with built-in database templates for movies, social networks, and financial data, making it valuable for developers building graph-based AI applications, teams requiring shared persistent memory across multiple AI agents, and organizations needing robust graph database integration with automatic failure recovery and concurrent access management.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Repository
- github.com/jordanburke/kuzudb-mcp-server
- Author type
- human
- Updated
- 2026-04-30
Use via MCP
Resolve KuzuDB from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.