Chroma documents an official Model Context Protocol server in the chroma-core/chroma-mcp repository and docs.trychroma.com/integrations/frameworks/anthropic-mcp, started with `uvx chroma-mcp` over stdio. Tools include `chroma_list_collections`, `chroma_create_collection`, `chroma_peek_collection`, `chroma_modify_collection`, `chroma_delete_collection`, `chroma_add_documents`, `chroma_query_documents`, `chroma_get_documents`, `chroma_update_documents`, and `chroma_delete_documents` per the README. Client types documented: ephemeral (default), persistent (`--client-type persistent --data-dir`), HTTP self-hosted, and Chroma Cloud (`--client-type cloud` with API keys). Embedding function options include default, Cohere, OpenAI, Jina, VoyageAI, and Roboflow per Chroma MCP docs.
Use cases
- Let Cursor agents create collections and run semantic queries during RAG prototyping
- Persist agent memory locally with `--client-type persistent` and a project data directory
- Connect Chroma Cloud from MCP for shared team vector stores
- Teach MCP tool boundaries with separate add/query/update/delete document tools
- Prototype hybrid metadata filters before wiring production retrieval pipelines
Key features
- Cursor
- Claude Desktop
- Claude Code
- VS Code
- Codex
Frequently Asked Questions
- Does Chroma Cloud require extra flags?
- Chroma docs describe `--client-type cloud` with API key environment variables—verify chroma-mcp README for current Cloud auth fields.
- Which embedding functions are supported?
- README lists default, Cohere, OpenAI, Jina, VoyageAI, and Roboflow embedding integrations.
- Is this the Package Search MCP?
- No—chroma-mcp is the database MCP; Chroma's separate package-search MCP lives in another repository per chroma-core docs.
Related
Related
3 Indexed items
LanceDB MCP Server
LanceDB maintains a reference Model Context Protocol server in the lancedb/lancedb-mcp-server repository (linked from lancedb/lancedb issue #2341), implemented with FastMCP and LanceDB embeddings. Tools include `ingest_docs` (embed and store documents), `query_table` (semantic retrieval with configurable top_k and query_type), and `table_details` (schema and row counts) per the README. Configuration uses `uv run lancedb_mcp.py` with environment variables `LANCEDB_URI` (default `~/lancedb`), `TABLE_NAME`, `EMBEDDING_FUNCTION` (default sentence-transformers), and `MODEL_NAME` (default all-MiniLM-L6-v2). The repo describes itself as a basic serverless MCP reference for building more complex LanceDB agent apps—not a full production managed endpoint.
Upstash MCP Server
Upstash documents an official Model Context Protocol server at upstash.com/docs/agent-resources/mcp implemented in the `upstash/mcp-server` repository and npm package `@upstash/mcp-server`. Started with `npx -y @upstash/mcp-server@latest --email YOUR_EMAIL --api-key YOUR_API_KEY`, it exposes tools for serverless Redis, QStash, Workflow runs, and Upstash Box so agents can manage and debug account resources from Cursor, Claude Code, VS Code, Codex, and other MCP clients. Read-only API keys automatically disable mutating tools per docs; optional `--transport http`, `--disable-telemetry`, and Upstash Box API key flags are documented for advanced setups.
Weaviate MCP Server
Weaviate documents a built-in Model Context Protocol server in the main `weaviate/weaviate` binary from v1.37.1 onward at docs.weaviate.io/weaviate/mcp/mcp-server, exposed as a Streamable HTTP endpoint at `/v1/mcp` on the same port as the REST API (default 8080). Enable with `MCP_SERVER_ENABLED=true`; optional `MCP_SERVER_WRITE_ACCESS_ENABLED=true` registers `weaviate-objects-upsert`. Tools include `weaviate-collections-get-config`, `weaviate-tenants-list`, `weaviate-query-hybrid`, and `weaviate-objects-upsert` (write-gated). Authentication uses existing API keys/Bearer tokens with RBAC permissions `read_mcp`, `create_mcp`, and `update_mcp` per Weaviate 1.37 release notes. The standalone weaviate/mcp-server-weaviate repository is deprecated in favor of this built-in server.