Integration

Chroma integration

Chroma Cloud vector database, REST API v2. Browse the databases and collections of a tenant, create and delete them, and read, write and search records: add, upsert, update and delete documents with their embeddings and metadata, fetch records by id or metadata filter, count them, and run nearest-neighbour queries. Embeddings are always supplied by the caller, the REST API never computes them.

Connect Chroma How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Chroma.Built from the 17 Chroma tools below, on the connection you add once.

Common Chroma use cases

removing a collection built for an experiment
cleaning up a per-customer database at offboarding
resolving the tenant name before listing collections
retagging stored documents without re-embedding them
discovering the database name that holds a collection
reading back the stored text of specific document ids
re-running an ingestion job without creating duplicates
removing every document of a source that was decommissioned
renaming a collection after a knowledge base is reorganised
checking a database exists before creating collections in it

What you can do with Chroma

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Record, 7 operations

add_recordsAdd recordsPOSTAdds records with precomputed embeddings to a collection.
count_recordsCount recordsGETCounts the records in a collection.
delete_recordsDelete recordsPOSTDeletes records selected by id or by metadata filter.
get_recordsGet recordsPOSTFetches records by id or metadata filter, without similarity search.
query_recordsQuery recordsPOSTRuns a nearest-neighbour search with precomputed query vectors.
update_recordsUpdate recordsPOSTUpdates fields of records that already exist.
upsert_recordsUpsert recordsPOSTAdds or replaces records with precomputed embeddings.

Collection, 5 operations

create_collectionCreate collectionPOSTCreates a vector collection.
delete_collectionDelete collectionDELETEDeletes a collection and all of its records.
get_collectionGet collectionGETRetrieves a collection by its identifier.
list_collectionsList collectionsGETLists the collections of a database.
update_collectionUpdate collectionPUTRenames a collection or updates its metadata.

Database, 4 operations

create_databaseCreate databasePOSTCreates a new database in a tenant.
delete_databaseDelete databaseDELETEDeletes a database and all of its collections.
get_databaseGet databaseGETRetrieves a database by name.
list_databasesList databasesGETLists the databases of a tenant.

Identity, 1 operation

get_user_identityGet user identityGETReturns the tenant and databases the token grants access to.

Use Chroma from Claude Code, Cursor or Codex

Connect Chroma in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Chroma operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Chroma

Create your workspace
Sign up free. Nothing to install.
Connect Chroma once
Add your Chroma connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Chroma integration FAQ

What can you do with the Chroma integration?

LiveContext exposes 17 operations on Chroma, covering record, collection, database and identity. Common uses include removing a collection built for an experiment, cleaning up a per-customer database at offboarding and resolving the tenant name before listing collections.