TL;DR
Chroma is a Databases MCP server that lets Claude Code, Cursor, Windsurf and any MCP-compatible AI agent embeddings, vector search, and document storage with Chroma AI database for RAG applications. Install in 1 minute with mcpizy install chroma.
Chroma
Install verified 5 toolsDatabases
Embeddings, vector search, and document storage with Chroma AI database for RAG applications.
Official homepageRepo audit: 63/100 β showing real gaps β check it still fits your needs
Scored on licence, adoption, maintenance and documentation of chroma-core/chroma-mcp. We show the grade whether it flatters the server or not.
no commit for 11 months Β· 587 stars Β· Apache-2.0 licence Β· 28 open issues
Read the full audit on CheckMCPInstall Chroma
mcpizy install chromauvx chroma-mcpTools exposed
5 tools availablelist_collectionsList Chroma collections
list_collectionsList Chroma collections
create_collectionCreate a new collection
create_collectionCreate a new collection
Inputs
namestringrequired
add_documentsAdd documents with optional embeddings
add_documentsAdd documents with optional embeddings
Inputs
collectionstringrequireddocumentsstring[]requiredidsstring[]required
query_collectionSemantic search in a collection
query_collectionSemantic search in a collection
Inputs
collectionstringrequiredquery_textsstring[]requiredn_resultsnumberoptional
delete_documentsDelete documents by ID
delete_documentsDelete documents by ID
Inputs
collectionstringrequiredidsstring[]required
Configuration
Works identically across clients. Only the config file path differs.
Claude Code~/.claude.json
~/.claude.json{
"mcpServers": {
"chroma": {
"command": "uvx",
"args": [
"chroma-mcp"
],
"env": {
"CHROMA_CLIENT_TYPE": "persistent",
"CHROMA_DATA_DIR": "/path/to/chroma-data"
}
}
}
}Cursor.cursor/mcp.json
.cursor/mcp.json{
"mcpServers": {
"chroma": {
"command": "uvx",
"args": [
"chroma-mcp"
],
"env": {
"CHROMA_CLIENT_TYPE": "persistent",
"CHROMA_DATA_DIR": "/path/to/chroma-data"
}
}
}
}Windsurf~/.codeium/windsurf/mcp_config.json
~/.codeium/windsurf/mcp_config.json{
"mcpServers": {
"chroma": {
"command": "uvx",
"args": [
"chroma-mcp"
],
"env": {
"CHROMA_CLIENT_TYPE": "persistent",
"CHROMA_DATA_DIR": "/path/to/chroma-data"
}
}
}
}Authentication setup
- 1
Chroma runs locally β no credentials needed for the persistent client
What you can do with Chroma MCP
Paste any of these prompts into Claude Code, Cursor or another MCP-compatible client.
βCreate a 'knowledge-base' collection and index these 100 documentsβ
Uses: create_collection, add_documents
βSemantic search my knowledge base for 'refund policy'β
Uses: query_collection
βList every collection and its document countβ
Uses: list_collections
Works with
More Databases MCPs
Alternatives to Chroma
If Chroma doesn't fit your stack, these Databases MCP servers solve similar problems.
Frequently asked questions
What is the Chroma MCP server?
Chroma is listed as an Databases Model Context Protocol server whose documented purpose is to let an MCP-compatible agent embeddings, vector search, and document storage with Chroma AI database for RAG applications. Client support, permissions and authentication remain specific to the upstream project.
How do I install Chroma MCP with Claude Code?
The fastest way is the MCPizy CLI: run `mcpizy install chroma` and MCPizy will add the server to your `.claude.json` automatically. You can also install it manually by adding an entry under `mcpServers` in `.claude.json` with the command `uvx chroma-mcp` and restarting Claude Code.
Does MCPizy charge to view or install Chroma MCP?
No. Reading this profile and copying its install guidance is free. Upstream software, API, account or usage costs are separate, and licence coverage should be checked from the linked source when available.
Does Chroma MCP work with Cursor and Windsurf?
The MCP standard is supported by those clients, but a specific server can still have client-specific setup or transport limits. Use the configuration shown on this page when present and verify the upstream instructions before installation.
What can I do with Chroma MCP?
Its documented purpose is to let an MCP-compatible agent embeddings, vector search, and document storage with Chroma AI database for RAG applications. The exact tools, permissions and write capabilities depend on the server version and configuration shown by the upstream project.
Compare before you commit
Put this server beside an alternative, or return to the full evidence directory.
Compare MCP serversBack to directory