Skip to main content
Glama

Chroma MCP Server

Official

chroma_create_collection

Create a new Chroma collection with configurable HNSW parameters, including distance functions, construction, and search settings, for efficient vector search and data management.

Instructions

Create a new Chroma collection with configurable HNSW parameters.

Args: collection_name: Name of the collection to create space: Distance function used in HNSW index. Options: 'l2', 'ip', 'cosine' ef_construction: Size of the dynamic candidate list for constructing the HNSW graph ef_search: Size of the dynamic candidate list for searching the HNSW graph max_neighbors: Maximum number of neighbors to consider during HNSW graph construction num_threads: Number of threads to use during HNSW construction batch_size: Number of elements to batch together during index construction sync_threshold: Number of elements to process before syncing index to disk resize_factor: Factor to resize the index by when it's full embedding_function_name: Name of the embedding function to use. Options: 'default', 'cohere', 'openai', 'jina', 'voyageai', 'ollama', 'roboflow' metadata: Optional metadata dict to add to the collection

Input Schema

NameRequiredDescriptionDefault
batch_sizeNo
collection_nameYes
ef_constructionNo
ef_searchNo
embedding_function_nameNodefault
max_neighborsNo
metadataNo
num_threadsNo
resize_factorNo
spaceNo
sync_thresholdNo

Input Schema (JSON Schema)

{ "properties": { "batch_size": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null, "title": "Batch Size" }, "collection_name": { "title": "Collection Name", "type": "string" }, "ef_construction": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null, "title": "Ef Construction" }, "ef_search": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null, "title": "Ef Search" }, "embedding_function_name": { "default": "default", "title": "Embedding Function Name", "type": "string" }, "max_neighbors": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null, "title": "Max Neighbors" }, "metadata": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null, "title": "Metadata" }, "num_threads": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null, "title": "Num Threads" }, "resize_factor": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null, "title": "Resize Factor" }, "space": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "title": "Space" }, "sync_threshold": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null, "title": "Sync Threshold" } }, "required": [ "collection_name" ], "title": "chroma_create_collectionArguments", "type": "object" }

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/chroma-core/chroma-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server