About TypesenseKit
TypesenseKit is an open-source MCP server that exposes typed Typesense operations to AI agents. It covers search, schema inspection, collection operations, and cluster administration, with read-only mode enabled by default.
Key features
- 01Expose typed Typesense operations
- 02Search Typesense collections
- 03Inspect schemas and collections
- 04Support cluster administration
- 05Default to read-only operation
Use cases
- 01Search Typesense data from an AI agent
- 02Inspect a Typesense collection schema
- 03Connect an agent to Typesense in read-only mode
MCP support
The MCP server exposes Typesense operations as structured tools for AI agents. It runs in read-only mode by default; setting TYPESENSEKIT_READ_ONLY=false enables write, delete, and admin tools.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y @typesensekit/mcpTYPESENSE_URLURL of the Typesense server, including protocol and port when required.TYPESENSE_API_KEYSecretTypesense API key used to authenticate server operations.TYPESENSEKIT_READ_ONLYExpose only read operations unless explicitly disabled.TYPESENSE_CONNECTION_TIMEOUT_SECONDSOptional Typesense connection timeout in seconds.Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project README@typesensekit/mcp
An open-source Typesense MCP server that gives AI agents structured tools for search, schema inspection, collection operations, and cluster administration. It runs in read-only mode by default.
Typesense MCP overview · Client setup · Security guide · GitHub
TYPESENSE_URL=http://localhost:8108 TYPESENSE_API_KEY=xyz pnpm dlx @typesensekit/mcp
Set TYPESENSEKIT_READ_ONLY=false to expose write/delete/admin tools.
Run the stateless Streamable HTTP server:
TYPESENSE_URL=http://localhost:8108 TYPESENSE_API_KEY=xyz pnpm dlx --package @typesensekit/mcp typesensekit-mcp-http
See the API coverage inventory for supported Typesense operations.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.