GET /heartbeat — verifies Chroma is reachable. Returns nanosecond heartbeat. Use before any workload.
Generate MCP URLOverview: GET /heartbeat — verifies Chroma is reachable. Returns nanosecond heartbeat. Use before any workload through Chroma.
Benefits:
Common Use Cases:
1. Semantic Search & Retrieval
AI agents store and query document embeddings in Chroma to power natural language search across knowledge bases, wikis, and internal documentation.
2. RAG Pipeline Automation
AI agents use Chroma as the vector store in retrieval-augmented generation workflows, automatically indexing new documents and serving relevant context to LLMs.
3. Content Recommendation Engine
AI agents query Chroma embeddings to surface similar articles, products, or resources based on user behavior and content similarity.
4. Duplicate & Similarity Detection
Automatically detect near-duplicate content, support tickets, or records by comparing embeddings in Chroma, reducing redundancy across systems.
5. AI Model Evaluation & Testing
AI agents store test embeddings in Chroma and run similarity benchmarks to evaluate model performance, track drift, and compare embedding quality over time.
Creates a collection with name, optional metadata JSON, embedding function config. Returns collection id.
Runs multiple query_embeddings in one request (batch nearest neighbor). Pass query_embeddings as JSON array of vectors.
Creates database under tenant.
Query with mandatory where JSON metadata filter preset.
Creates an auth token (admin).
Gets a small sample via CHROMA_GET_DOCUMENTS with limit 5.
Adds documents with auto-generated sequential ids when ids omitted (server-dependent); pass documents JSON array.
Query with include embeddings in response for debugging.
Returns count of collections (uses list endpoint if dedicated count is unavailable).
Updates existing ids with new embeddings/documents/metadata.
Returns server version/build metadata. Use to confirm compatibility with client expectations.
Upserts vectors/documents by id.
Updates collection name or metadata (PUT/PATCH per server).
Vector similarity query with query_embeddings or query_texts JSON arrays, n_results, where, where_document, include. Returns distances and payloads.
Adds ids, embeddings, documents, metadatas, uris to a collection. Pass parallel JSON arrays as strings.
Lists auth tokens when server auth is enabled.
Lists collections in the tenant/database scope. Returns ids and metadata. Use before querying; for counts use CHROMA_COUNT_COLLECTIONS.
Simplified query: collection_id + query_texts JSON array + n_results. Use when you only have text and default embedding.
Creates tenant (Chroma Cloud / multi-tenant servers).
POST /reset — **destroys all collections and data** on the server. Use only when explicitly wiping dev data; never on production without confirmation.
Gets collection metadata by id or name depending on server. Use CHROMA_LIST_COLLECTIONS to resolve ids.
Counts records in collection.
Deletes auth token by id.
Gets tenant by name.
Deletes a collection and all vectors.
Fetches documents/embeddings/metadata by ids or where filter.
Creates collection with get_or_create true to avoid duplicates.
Gets database metadata.
Deletes by ids or where metadata filter JSON.
Do I need my own developer credentials to use Chroma MCP with Adopt AI?
No, you can get started immediately using Adopt AI's built-in Chroma integration. For production use, we recommend configuring your own API credentials for greater control and security.
Can I connect Chroma with other apps through Adopt AI?
Yes! Adopt AI supports multi-app workflows, so your AI agents can seamlessly move data between Chroma and LLM platforms, knowledge bases, search tools, and more.
Is Adopt AI secure?
Absolutely. Adopt AI is SOC 2 Type 2 certified and ISO/IEC 27001 compliant, and adheres to EU GDPR, CCPA, and HIPAA standards. All data is encrypted in transit and at rest, ensuring the confidentiality, integrity, and availability of your data. Learn more here.
What happens if the Chroma API changes?
Adopt AI maintains and updates all integrations automatically, so your agents always work with the latest API versions, no manual maintenance required.
Do I need coding skills to set up the Chroma integration?
Not at all. Adopt AI's zero-shot API discovery means your agents understand Chroma's schema on first contact. Setup takes minutes with no code required.
How do I set up custom Chroma MCP in Adopt AI?
For a step-by-step guide on creating and configuring your own Chroma API credentials with Adopt AI, see here.
