KosmoKrator

other

Weaviate MCP Integration for Vercel AI SDK

Connect Weaviate to Vercel AI SDK through the local KosmoKrator MCP gateway with scoped tools, credentials, and write policy.

7 functions 5 read 2 write API key auth
Submit Weaviate feedback View package source

Connect Weaviate to Vercel AI SDK

Use KosmoKrator as a local integration gateway for Vercel AI SDK agents and scripts.

Create an MCP client that starts or connects to the KosmoKrator gateway for the selected integration. The gateway is local, scoped to this integration, and starts with --write=deny so Vercel AI SDK can inspect read-capable tools without receiving write access by default.

Weaviate MCP Config for Vercel AI SDK

Prefer CLI JSON calls when a workflow only needs one deterministic integration operation.

{
  "mcpServers": {
    "kosmokrator-weaviate": {
      "type": "stdio",
      "command": "kosmo",
      "args": [
        "mcp:serve",
        "--integration=weaviate",
        "--write=deny"
      ]
    }
  }
}

Run the Gateway Manually

kosmokrator mcp:serve --integration=weaviate --write=deny

Why Use KosmoKrator Here

Scoped tools

Expose only Weaviate instead of a broad multi-service tool list.

Local credentials

Reuse credentials already configured for the KosmoKrator CLI and Lua runtime.

Write policy

Start read-only, then opt into ask or allow for trusted workspaces.

Weaviate Tools Visible to Vercel AI SDK

Vercel AI SDK sees stable MCP tool names generated from the Weaviate integration catalog.

MCP toolSource functionTypeDescription
integration__weaviate__weaviate_list_schemas weaviate.weaviate_list_schemas Read List all schemas (collections/classes) defined in the Weaviate instance. Returns the full schema including all classes and their properties.
integration__weaviate__weaviate_get_schema weaviate.weaviate_get_schema Read Get the schema definition for a specific class (collection) in Weaviate. Returns the class name, properties, vectorizer config, and module settings.
integration__weaviate__weaviate_create_class weaviate.weaviate_create_class Write Create a new class (collection) in the Weaviate schema. Provide a class definition with the class name and an array of property definitions (name, dataType, etc.).
integration__weaviate__weaviate_search_objects weaviate.weaviate_search_objects Read Search and query objects in Weaviate using GraphQL. Supports Get, Aggregate, and Explore queries with filters, sorting, and vector/nearVector/nearText search.
integration__weaviate__weaviate_create_object weaviate.weaviate_create_object Write Create a new data object in a Weaviate class. Provide the class name and a properties object with the data fields. Optionally specify a UUID for the object.
integration__weaviate__weaviate_get_object weaviate.weaviate_get_object Read Retrieve a specific data object from Weaviate by its class name and UUID. Returns the full object including all properties and metadata.
integration__weaviate__weaviate_get_health weaviate.weaviate_get_health Read Check the health and liveness of the Weaviate instance. Returns a status indicating whether the service is alive and responsive.

Related Weaviate Pages

Weaviate CLIUse direct JSON commands instead of MCP discovery. Weaviate MCPFull gateway reference and MCP tool names. KosmoKrator for Vercel AI SDKClient-level gateway setup.