Chroma MCP

Not yet source-checked

Official MCP server that gives LLM clients direct access to the Chroma vector database.

Machine-drafted from the vendor's site · not yet source-checkedProfile updated Aug 6, 2026Link checked Oct 24, 2026How we rate

Free· Open source (Apache 2.0). Free to run locally or self-hosted; embedding-function API keys (OpenAI, Cohere, Jina, VoyageAI, Roboflow) billed by those providers. Chroma Cloud pricing set separately by Chroma.MCP Servers

Visit website →

In short

Chroma MCP provides a direct bridge between LLM clients like Claude Desktop and the Chroma vector database. It allows agents to persist, search, and manage vector data using standard MCP tools, eliminating the need for bespoke integration code or REST wrappers.

Best for

Developers who already use Chroma (or want to) and need to give Claude Desktop, Cursor, or another MCP client durable vector memory or a searchable knowledge base with minimal glue code.

Skip if

Teams needing hosted, multi-tenant vector search with auth and quotas out of the box, or anyone who wants an opinionated end-to-end RAG framework rather than a database bridge.

Chroma MCP is the official Model Context Protocol server for Chroma, the open-source embedding database. It exposes Chroma's collection and document APIs as MCP tools so any MCP-aware LLM client - Claude Desktop, Cursor, Continue, Windsurf, or custom agents - can persist, search, and manage vector data without bespoke integration code. The server ships as a Python package installable via uvx or pip, and supports four client modes: ephemeral (in-memory, ideal for tests), persistent (local file-based storage), HTTP (against a self-hosted Chroma server), and cloud (Chroma Cloud at api.trychroma.com). Once wired into a client's MCP config, the LLM gets a dozen structured tools: create/list/modify/delete collections, add/get/query/update/delete documents, peek at samples, count records, and configure HNSW parameters. Query tools support semantic search plus metadata and full-text filters. Collections persist their embedding-function choice (default all-MiniLM plus optional OpenAI, Cohere, Jina, VoyageAI, or Roboflow) from v1.0.0 onward, so retrieval always uses the same vectors used at insert. Typical use: give Claude a durable long-term memory across sessions, build a shared team knowledge base an agent can search, or attach a code/document index to a coding assistant. It is the canonical way to plug Chroma into the MCP ecosystem and a good pick when you want vector search without standing up LangChain glue or writing a REST wrapper yourself.

Editor's take

The cleanest way to hand Claude a real vector store. Install is two lines of JSON, the tool surface maps 1:1 to Chroma's own API, and the ephemeral/persistent/HTTP/cloud switch means the same server scales from a laptop test to Chroma Cloud without rewriting configs. It is a bridge, not a RAG framework - bring your own chunking and re-ranking - but as an MCP citizen it is exactly what you want.

— The AI Tool Bible editorial team

Pros

✅ Official server from the Chroma team, tracks the database's features closely
✅ Four deployment modes (ephemeral, persistent, HTTP, Chroma Cloud) from one binary
✅ Twelve well-scoped MCP tools cover the full collection and document lifecycle
✅ Supports six embedding functions including OpenAI, Cohere, Jina, and VoyageAI with per-collection persistence
✅ Zero-config install via uvx - drops into Claude Desktop or Cursor in a couple of JSON lines
✅ Apache 2.0 licensed and readable Python source; easy to fork or extend
✅ Query tools expose HNSW tuning and metadata/full-text filters, not just naive semantic search

Cons

⚠️ You still have to run and back up the Chroma store yourself unless you pay for Chroma Cloud
⚠️ Command-line API key arguments are convenient but leak into process lists; env/.env path is safer but extra setup
⚠️ No built-in access control or multi-tenant isolation - anything the MCP client sees, it can delete
⚠️ Embedding-function persistence only works for collections created on Chroma v1.0.0+; older stores need migration
⚠️ Python-only server; teams on pure Node stacks add a runtime dependency
⚠️ MCP tool surface is CRUD-shaped - no higher-level RAG primitives like chunking, re-ranking, or hybrid fusion

Facts

API available: Yes
Open source: Yes (license: Apache-2.0)
GitHub stars: 600 (checked Oct 29, 2026)
Last GitHub push: Sep 17, 2025
First commit: Feb 2025

Where this tool sits

MCP Servers MCP database Servers MCP reference Servers AI codebase search AI knowledge base search Open-source AI tools Self-hosted AI tools For Developers Has Api Open Source Self Hostable Supports RAG

Use cases

Long-term memory for Claude DesktopTeam knowledge base shared across agentsRAG over local documentsSemantic code search in Cursor or ContinueVector store for custom MCP agentsPersonal notes and journal recallMetadata-filtered document retrievalChroma Cloud access from LLM clients

Frequently asked

What is the primary function of Chroma MCP?: It exposes Chroma's collection and document APIs as MCP tools, allowing any MCP-aware LLM client to persist, search, and manage vector data directly.
Which LLM clients are compatible with Chroma MCP?: It supports any MCP-aware client, including Claude Desktop, Cursor, Continue, Windsurf, and custom agents.
What deployment modes does Chroma MCP support?: The server supports four modes: ephemeral (in-memory), persistent (local file-based), HTTP (self-hosted server), and cloud (Chroma Cloud).
Is Chroma MCP free to use?: Yes, it is open source under the Apache 2.0 license and free to run locally or self-hosted, though external embedding API keys and Chroma Cloud services may incur separate costs.
Does Chroma MCP include built-in RAG features like chunking?: No, it is a database bridge rather than an end-to-end RAG framework, so users must provide their own chunking, re-ranking, or hybrid fusion logic.