Can I use Chroma as a CLI?

Yes. KosmoKrator exposes a Chroma CLI through kosmo integrations:call and the provider shortcut command. Commands can return JSON for scripts, CI, and coding agents.

Can I expose Chroma through MCP?

Yes. The KosmoKrator MCP gateway can expose selected Chroma tools to clients such as Claude Code, Cursor, Codex, and other MCP-compatible tools.

Where are Chroma credentials stored?

Chroma credentials are configured in KosmoKrator's local integration settings and reused by CLI, Lua, and MCP gateway surfaces.

Can I deny write access for Chroma MCP tools?

Yes. Start the gateway with --write=deny for read-only clients, or use ask/allow only for trusted workspaces.

data

Chroma CLI for AI Agents

Use the Chroma CLI from KosmoKrator to call Chroma tools headlessly, return JSON, inspect schemas, and automate workflows from coding agents, scripts, and CI.

7 functions 5 read 2 write API key auth

Submit Chroma feedback View package source

Chroma CLI Setup

Chroma can be configured headlessly with `kosmokrator integrations:configure chroma`.

# Install KosmoKrator first if it is not available on PATH.
curl -fsSL https://raw.githubusercontent.com/OpenCompanyApp/kosmokrator/main/install.sh | bash

# Configure and verify this integration.
kosmokrator integrations:configure chroma --set api_key="$CHROMA_API_KEY" --enable --read allow --write ask --json
kosmokrator integrations:doctor chroma --json
kosmokrator integrations:status --json

Credentials

Authentication type: API key api_key. Configure credentials once, then use the same stored profile from scripts, coding CLIs, Lua code mode, and the MCP gateway.

Key	Env var	Type	Required	Label
`api_key`	`CHROMA_API_KEY`	Secret `secret`	yes	API Key
`url`	`CHROMA_URL`	URL `url`	no	Chroma Server URL

Call Chroma Headlessly

Use the generic call form when another coding CLI or script needs a stable universal interface.

kosmo integrations:call chroma.chroma_list_collections '{
  "limit": 1,
  "after": "example_after"
}' --json

Use the provider shortcut form for shorter human-facing commands.

kosmo integrations:chroma chroma_list_collections '{
  "limit": 1,
  "after": "example_after"
}' --json

Agent Discovery Commands

These commands return structured output for coding agents that need to inspect capabilities before choosing a function.

kosmo integrations:docs chroma --json
kosmo integrations:docs chroma.chroma_list_collections --json
kosmo integrations:schema chroma.chroma_list_collections --json
kosmo integrations:search "Chroma" --json
kosmo integrations:list --json

All CLI Functions

Every function below can be called headlessly. The generic form is stable across all integrations; the provider shortcut is shorter but specific to Chroma.

`chroma.chroma_list_collections`

Read read

List all vector collections in Chroma. Returns collection names and IDs that can be used for further operations.

Parameters: limit, after

Generic CLI call

kosmo integrations:call chroma.chroma_list_collections '{"limit":1,"after":"example_after"}' --json

Provider shortcut

kosmo integrations:chroma chroma_list_collections '{"limit":1,"after":"example_after"}' --json

`chroma.chroma_get_collection`

Read read

Get details of a specific Chroma collection by its name or UUID, including metadata and document count.

Parameters: collection_id

Generic CLI call

kosmo integrations:call chroma.chroma_get_collection '{"collection_id":"example_collection_id"}' --json

Provider shortcut

kosmo integrations:chroma chroma_get_collection '{"collection_id":"example_collection_id"}' --json

`chroma.chroma_create_collection`

Write write

Create a new vector collection in Chroma. Collections are used to store and query document embeddings.

Parameters: name, description, metadata

Generic CLI call

kosmo integrations:call chroma.chroma_create_collection '{"name":"example_name","description":"example_description","metadata":"example_metadata"}' --json

Provider shortcut

kosmo integrations:chroma chroma_create_collection '{"name":"example_name","description":"example_description","metadata":"example_metadata"}' --json

`chroma.chroma_add_documents`

Write write

Add documents with embeddings to a Chroma collection. Each document requires an ID and either embeddings or text content.

Parameters: collection_id, ids, embeddings, documents, metadatas

Generic CLI call

kosmo integrations:call chroma.chroma_add_documents '{"collection_id":"example_collection_id","ids":"example_ids","embeddings":"example_embeddings","documents":"example_documents","metadatas":"example_metadatas"}' --json

Provider shortcut

kosmo integrations:chroma chroma_add_documents '{"collection_id":"example_collection_id","ids":"example_ids","embeddings":"example_embeddings","documents":"example_documents","metadatas":"example_metadatas"}' --json

`chroma.chroma_query_documents`

Read read

Search for similar documents in a Chroma collection using query embeddings or text. Returns the most similar documents ranked by distance.

Parameters: collection_id, query_embeddings, query_texts, n_results, where, where_document, include

Generic CLI call

kosmo integrations:call chroma.chroma_query_documents '{"collection_id":"example_collection_id","query_embeddings":"example_query_embeddings","query_texts":"example_query_texts","n_results":1,"where":"example_where","where_document":"example_where_document","include":"example_include"}' --json

Provider shortcut

kosmo integrations:chroma chroma_query_documents '{"collection_id":"example_collection_id","query_embeddings":"example_query_embeddings","query_texts":"example_query_texts","n_results":1,"where":"example_where","where_document":"example_where_document","include":"example_include"}' --json

`chroma.chroma_get_document`

Read read

Retrieve specific documents from a Chroma collection by their IDs. Returns the full documents including text, embeddings, and metadata.

Parameters: collection_id, ids, where, where_document, include, limit, offset

Generic CLI call

kosmo integrations:call chroma.chroma_get_document '{"collection_id":"example_collection_id","ids":"example_ids","where":"example_where","where_document":"example_where_document","include":"example_include","limit":1,"offset":1}' --json

Provider shortcut

kosmo integrations:chroma chroma_get_document '{"collection_id":"example_collection_id","ids":"example_ids","where":"example_where","where_document":"example_where_document","include":"example_include","limit":1,"offset":1}' --json

`chroma.chroma_get_health`

Read read

Check the health status of the Chroma vector database server. Returns heartbeat and version information.

Parameters: none

Generic CLI call

kosmo integrations:call chroma.chroma_get_health '{}' --json

Provider shortcut

kosmo integrations:chroma chroma_get_health '{}' --json

Function Schemas

Use these parameter tables when building CLI payloads without calling integrations:schema first.

`chroma.chroma_list_collections`

List all vector collections in Chroma. Returns collection names and IDs that can be used for further operations.

Operation: Read read
Schema command: kosmo integrations:schema chroma.chroma_list_collections --json

Parameter	Type	Required	Description
`limit`	integer	no	Maximum number of collections to return (default: 100).
`after`	string	no	Cursor for pagination — pass the value from a previous response to get the next page.

`chroma.chroma_get_collection`

Get details of a specific Chroma collection by its name or UUID, including metadata and document count.

Operation: Read read
Schema command: kosmo integrations:schema chroma.chroma_get_collection --json

Parameter	Type	Required	Description
`collection_id`	string	yes	The collection name or UUID.

`chroma.chroma_create_collection`

Create a new vector collection in Chroma. Collections are used to store and query document embeddings.

Operation: Write write
Schema command: kosmo integrations:schema chroma.chroma_create_collection --json

Parameter	Type	Required	Description
`name`	string	yes	The name of the collection to create.
`description`	string	no	An optional description of the collection.
`metadata`	object	no	Optional metadata to attach to the collection (JSON object with string values).

`chroma.chroma_add_documents`

Add documents with embeddings to a Chroma collection. Each document requires an ID and either embeddings or text content.

Operation: Write write
Schema command: kosmo integrations:schema chroma.chroma_add_documents --json

Parameter	Type	Required	Description
`collection_id`	string	yes	The collection name or UUID to add documents to.
`ids`	array	yes	Array of unique document IDs (strings).
`embeddings`	array	no	Array of embedding vectors. Each embedding is an array of floats. Required if no documents text provided.
`documents`	array	no	Array of text documents. Chroma will generate embeddings if no embeddings are provided.
`metadatas`	array	no	Array of metadata objects (one per document) with string values.

`chroma.chroma_query_documents`

Search for similar documents in a Chroma collection using query embeddings or text. Returns the most similar documents ranked by distance.

Operation: Read read
Schema command: kosmo integrations:schema chroma.chroma_query_documents --json

Parameter	Type	Required	Description
`collection_id`	string	yes	The collection name or UUID to query.
`query_embeddings`	array	no	Array of query embedding vectors. Each embedding is an array of floats.
`query_texts`	array	no	Array of query text strings. Chroma will generate embeddings automatically.
`n_results`	integer	no	Number of results to return per query (default: 10).
`where`	string	no	JSON-encoded filter expression for metadata filtering, e.g. {"category": "tech"}.
`where_document`	string	no	JSON-encoded filter on document content, e.g. {"$contains": "search term"}.
`include`	array	no	Fields to include in response: documents, embeddings, metadatas, distances. Default: ["documents", "metadatas", "distances"].

`chroma.chroma_get_document`

Retrieve specific documents from a Chroma collection by their IDs. Returns the full documents including text, embeddings, and metadata.

Operation: Read read
Schema command: kosmo integrations:schema chroma.chroma_get_document --json

Parameter	Type	Required	Description
`collection_id`	string	yes	The collection name or UUID.
`ids`	array	no	Array of document IDs to retrieve.
`where`	string	no	JSON-encoded metadata filter, e.g. {"category": "tech"}.
`where_document`	string	no	JSON-encoded document content filter, e.g. {"$contains": "search term"}.
`include`	array	no	Fields to include: documents, embeddings, metadatas. Default: ["documents", "metadatas"].
`limit`	integer	no	Maximum number of documents to return (default: 100).
`offset`	integer	no	Number of documents to skip for pagination.

`chroma.chroma_get_health`

Check the health status of the Chroma vector database server. Returns heartbeat and version information.

Operation: Read read
Schema command: kosmo integrations:schema chroma.chroma_get_health --json

Parameter	Type	Required	Description
No parameters.

Permissions

Headless calls still follow the integration read/write permission policy. Configure read/write defaults with integrations:configure. Add --force only for trusted automation that should bypass that policy.