MCP Servers / database / Chroma MCP Server

Chroma MCP Server

stdionone★ 26database

An MCP server for the Chroma embedding database, providing persistent, searchable working memory for AI-assisted development with features like automated context recall and codebase indexing.

github ↗

Install

How to run this server

[ { "cmd": "pip install chroma-mcp-server", "imports": [] } ]

server path: chroma-mcp-server

Tools

What this server exposes

add_memory

Add a memory to the working memory store

search_memories

Search working memory for relevant context

get_memory

Retrieve a specific memory by ID

delete_memory

Delete a memory from the store

list_collections

List all available collections

create_collection

Create a new collection

delete_collection

Delete a collection

add_documents

Add documents to a collection

query_documents

Query documents from a collection

update_documents

Update documents in a collection

delete_documents

Delete documents from a collection

get_collection_info

Get information about a collection

setup_collections

Set up multiple collections with consistent configuration

update_embedding_function

Update the embedding function for a collection

promote_to_learning

Promote a working memory entry to a verified learning

auto_promote

Automatically promote high-confidence entries to learnings

validate_learning

Validate a learning with evidence

capture_test_failure

Capture a test failure for automated learning workflow

monitor_test_fix

Monitor for a test fix and promote to learning

Configuration

Environment & auth

authnone

Resources

githubhttps://github.com/djm81/chroma_mcp_server ↗