KosmoKrator

data

Chroma MCP Integration for OpenAI Agents SDK

Connect Chroma to OpenAI Agents SDK through the local KosmoKrator MCP gateway with scoped tools, credentials, and write policy.

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

Connect Chroma to OpenAI Agents SDK

Attach KosmoKrator integration tools to OpenAI Agents SDK workflows through a local MCP gateway.

Start the KosmoKrator MCP gateway locally and point the OpenAI Agents SDK MCP tool at that process or wrapper. The gateway is local, scoped to this integration, and starts with --write=deny so OpenAI Agents can inspect read-capable tools without receiving write access by default.

Chroma MCP Config for OpenAI Agents SDK

Use headless JSON commands for CI-style execution and MCP for agent tool discovery.

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

Run the Gateway Manually

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

Why Use KosmoKrator Here

Scoped tools

Expose only Chroma 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.

Chroma Tools Visible to OpenAI Agents

OpenAI Agents sees stable MCP tool names generated from the Chroma integration catalog.

MCP toolSource functionTypeDescription
integration__chroma__chroma_list_collections chroma.chroma_list_collections Read List all vector collections in Chroma. Returns collection names and IDs that can be used for further operations.
integration__chroma__chroma_get_collection chroma.chroma_get_collection Read Get details of a specific Chroma collection by its name or UUID, including metadata and document count.
integration__chroma__chroma_create_collection chroma.chroma_create_collection Write Create a new vector collection in Chroma. Collections are used to store and query document embeddings.
integration__chroma__chroma_add_documents chroma.chroma_add_documents Write Add documents with embeddings to a Chroma collection. Each document requires an ID and either embeddings or text content.
integration__chroma__chroma_query_documents chroma.chroma_query_documents Read Search for similar documents in a Chroma collection using query embeddings or text. Returns the most similar documents ranked by distance.
integration__chroma__chroma_get_document chroma.chroma_get_document Read Retrieve specific documents from a Chroma collection by their IDs. Returns the full documents including text, embeddings, and metadata.
integration__chroma__chroma_get_health chroma.chroma_get_health Read Check the health status of the Chroma vector database server. Returns heartbeat and version information.

Related Chroma Pages

Chroma CLIUse direct JSON commands instead of MCP discovery. Chroma MCPFull gateway reference and MCP tool names. KosmoKrator for OpenAI AgentsClient-level gateway setup.