SurrealMCP gives AI assistants, AI agents, IDEs, chatbots, and data platforms the ability to securely store, recall, and reason over live structured data – giving them the persistent, permission-aware memory they’ve been missing.

Built on the open Model Context Protocol standard (modelcontextprotocol.io), SurrealMCP connects any MCP-compatible client to SurrealDB with full portability and interoperability across the AI ecosystem.

“SurrealMCP gives AI agents what they’ve been missing – real, structured, and secure memory. By following the open MCP standard, we’ve made it possible for agents to work directly with live SurrealDB data, respecting every access rule, and remembering what matters,” said Tobie Morgan Hitchcock, CEO and Co-Founder of SurrealDB.

Today’s AI agents are impressive, but without long-term memory they can’t retain context or build on past knowledge. SurrealMCP changes that – giving agents a secure, real-time memory layer backed by SurrealDB’s multi-model engine. With SurrealMCP, agents can:

• Remember and recall events, facts, and conversations over time
• Query and update live data with role-based access controls
• Link vectors, graphs, and documents to create deep contextual understanding
• Perform administrative tasks like creating schemas or seeding data, all through natural language

Example use cases

• Agent Memory: “Store this chat and recall anything about shipping delays.” SurrealMCP stores the conversation as vectors, links related data in graph form, and makes it time-travel queryable
• Business Intelligence: “Recall customers in the top ten percent by lifetime value.” SurrealMCP translates the request into optimised queries, respecting all access policies
• Operational Automation: “Create a dev namespace in Europe, apply the schema, seed sample data.” SurrealMCP executes instantly, no dashboards, no manual scripts
• Enterprise Co-pilots: Power contextual CRM insights, real-time inventory tracking, or customer support histories

SurrealMCP supports multiple transport modes (including stdio, HTTP, and Unix sockets) along with bearer token authentication, rate limiting, health checks, and OpenTelemetry tracing. It implements the MCP specification to expose entities and relationships such as joins, graph structures, and nested documents; enforce dynamic, role-based, context-aware access rules; define field-level semantics like types, units, and constraints; and guide models through query translation layers so they understand what’s retrievable and under which security model.

SurrealMCP is available now for both self-hosted SurrealDB and SurrealDB Cloud. Developers can run it via Docker or as a standalone binary, connect MCP-compatible agents, IDEs, and AI tools directly to SurrealDB, or enable it instantly in SurrealDB Cloud for fully managed hosting. Source code, documentation, and setup guides are available at github.com/surrealdb/surrealmcp.

For more startup news, check out the other articles on the website, and subscribe to the magazine for free. Listen to The Cereal Entrepreneur podcast for more interviews with entrepreneurs and big-hitters in the startup ecosystem.