Self-hosted SurrealDB MCP alternatives
SurrealDB's MCP server installs locally and talks to your agent over stdio, querying and mutating a SurrealDB instance with SurrealQL. The process and credentials stay on your own machine. If you want the same local setup pointed at a different engine, the servers below all run that way too.
One caveat that holds across all of them: running the MCP server locally controls where the process and connection details live, but queries still reach whichever database you connect to. Self-host the database as well and the data stays on your hardware.
The 8 best self-hosted alternatives
The lightest option, the SQLite server through Bytebase DBHub runs an agent against a local database file with execute_sql and search_objects. There is no instance to keep running, just a file on disk.
Set up SQLite (DBHub) →DBHub connects an agent to a self-managed Postgres via a DSN over stdio, swapping SurrealQL for standard SQL on the most widely supported relational engine. It runs SQL and searches objects from a process you control.
Set up DBHub (Postgres) →The community Supabase server runs locally and connects to a Supabase project: run SQL, inspect schema, read logs, and manage edge functions. It pairs Postgres with an application platform rather than offering a multi-model engine.
Set up Supabase →MongoDB's official server installs locally and queries and manages databases with find, aggregate, and insert, plus Atlas administration. It is the specialist document store for the part of SurrealDB you might use as one.
Set up MongoDB →Pointed at a self-hosted cluster, ClickHouse's official server lists databases and tables and runs read-only SQL. Its column-oriented design handles analytics far faster than a multi-model engine would.
Set up ClickHouse →Elastic's official server runs locally and lists indices, reads mappings, and runs full-text and ES|QL queries against a cluster you operate. It is the search specialist where SurrealQL falls short.
Set up Elasticsearch →For in-memory state on your own infrastructure, Redis's official server reads and writes strings, hashes, lists, streams, JSON, and vector search over stdio. It sits in front of a primary database rather than replacing one.
Set up Redis →If the graph side of SurrealDB is the draw, Neo4j's official server introspects a graph schema and runs read or write Cypher against your own deployment. It is the dedicated graph database with the deepest traversal support.
Set up Neo4j →
How to choose
Every option here runs as a local stdio server, so the choice is the engine, not the hosting. SurrealDB packs several models into one; these split them out. Postgres or SQLite via DBHub for relational, MongoDB for documents, Neo4j for graphs, ClickHouse for analytics, Elasticsearch for search, Redis for caching. Self-host the database too and both the server and the data stay on your machine.
FAQ
- Can the SurrealDB MCP server be self-hosted?
- Yes. The server installs and runs locally over stdio, and SurrealDB itself can run on your own hardware, so both the MCP process and the data can stay on your infrastructure. The server also manages SurrealDB Cloud if you use the hosted offering.
- Does running a database MCP server locally keep the data on my machine?
- It keeps the MCP server process and connection details local. Whether the data stays local depends on the database: if you self-host Postgres, ClickHouse, Neo4j, or SurrealDB itself, the data is on your hardware. If you point at a managed cloud, queries travel there.