Agent skills

Materialize provides the following open-source agent skills to help developers build with Materialize.

Skill	What it provides	When to use
mcp-developer-analysis	Exact catalog schemas, diagnostic workflows, remediation runbooks, and guardrails for known pitfalls (cluster-scoped queries, uint8 ID mismatches, etc.).	Operational introspection and troubleshooting via the materialize-developer server. Examples: “why is my materialized view stale?”, “what can I optimize to save costs?”, “is my source healthy?”
materialize-docs	Comprehensive Materialize documentation, including SQL syntax, idiomatic patterns, data ingestion, concepts, and best practices (400+ reference files).	Authoring view definitions, learning concepts, looking up patterns. Useful with either MCP server. Examples: “show me how to deduplicate a stream”, “what’s the idiomatic top-K pattern?”, “how do I create a Kafka source?”

MCP servers

Materialize provides built-in Model Context Protocol (MCP) servers that AI agents can use. The MCP interface is served directly by the database; no sidecar process or external server is required. These endpoints use JSON-RPC 2.0 over HTTP POST (default port 6876) and support the MCP initialize, tools/list, and tools/call methods.

Endpoint	Path	Description
Agent	/api/mcp/agent	Discover and query your real-time data products over HTTP. For details, see MCP Server for agents. Available starting in v26.24
Developer	/api/mcp/developer	Read mz_* system catalog tables for troubleshooting and observability. For details, see MCP Server for developer.

See also

• MCP Server Troubleshooting
• Appendix: MCP Server (Python) for locally-run, separate MCP Server.