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
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.
Milvus MCP Server
The zilliztech/mcp-server-milvus project (documented at milvus.io/docs/milvus_and_mcp.md) exposes Milvus vector-database operations to MCP clients such as Claude Desktop and Cursor. The recommended launch path is `uv run src/mcp_server_milvus/server.py --milvus-uri http://localhost:19530` without a separate install step, with optional `MILVUS_URI`, `MILVUS_TOKEN`, and `MILVUS_DB` environment variables. Tools listed in Milvus docs include `milvus-text-search`, `milvus-hybrid-search`, `milvus-multi-vector-search`, `milvus-query`, and `milvus-count` for collection management, semantic retrieval, filtered hybrid search, and entity counts.
PlanetScale MCP Server
PlanetScale documents a hosted Model Context Protocol server at planetscale.com/docs/connect/mcp, reachable at `https://mcp.pscale.dev/mcp/planetscale` with OAuth authentication for organizations, databases, branches, schemas, and Insights data. An insights-only endpoint at `https://mcp.pscale.dev/mcp/planetscale-insights-only` omits read/write query tools. Tools documented include organization/database/branch listing, schema inspection, `planetscale_get_insights`, documentation search, and—when scopes allow—`planetscale_execute_read_query` and `planetscale_execute_write_query` with replica routing, ephemeral credentials, and destructive-query safeguards per the January 2026 changelog. PlanetScale notes the older local CLI MCP path is deprecated in favor of the hosted HTTP server for Cursor, Claude Code, and other MCP clients.