Weaviate MCP Server for Claude
Connect Claude to a Weaviate vector database — run hybrid search, inspect collection config, list tenants, and upsert objects — using Weaviate's built-in Model Context Protocol server.
Open the source and read safety notes before installing.
Safety notes
- The MCP server runs inside your Weaviate instance and respects its existing RBAC; scope the API key to least privilege.
- The object-upsert tool writes data — restrict write access to the collections Claude should modify.
Privacy notes
- Query text, retrieved objects, and collection metadata enter the MCP client context and the model's prompt.
- The Weaviate endpoint URL and API key are secrets — keep them in the client config or environment, not in shared repositories.
Prerequisites
- A Weaviate instance on v1.37.1 or later (self-hosted or Weaviate Cloud).
- The MCP server enabled on that instance via MCP_SERVER_ENABLED=true.
- A Weaviate API key with the RBAC permissions for the collections Claude should reach.
- An MCP client such as Claude Code or Claude Desktop.
Schema details
- Install type
- cli
- Troubleshooting
- No
- Scope
- Source repo
- Estimated setup
- 10 minutes
- Difficulty
- intermediate
- Website
- https://weaviate.io
Full copyable content
{
"mcpServers": {
"weaviate": {
"url": "https://<your-weaviate-host>/v1/mcp",
"type": "http"
}
}
}About this resource
Overview
The Weaviate MCP Server lets Claude work with a Weaviate vector database over the Model Context
Protocol. As of Weaviate v1.37.1, the MCP server is built into Weaviate itself (the earlier
standalone server is deprecated): enable it on your instance and Claude connects to the /v1/mcp
endpoint to run hybrid search, inspect collection configuration, list tenants, and upsert objects.
Key capabilities
The built-in server exposes four tools:
weaviate-query-hybrid— run a hybrid (vector + keyword) query over a collection.weaviate-collections-get-config— read a collection's configuration.weaviate-tenants-list— list tenants for a multi-tenant collection.weaviate-objects-upsert— insert or update objects in a collection.
How it compares
Several vector-database MCP servers give Claude retrieval over embeddings; they differ in how they are deployed and connected:
| MCP server | Deployment | Connects via | Notable |
|---|---|---|---|
| Weaviate MCP | Built into Weaviate (v1.37.1+) | Hosted /v1/mcp HTTP endpoint |
Native hybrid search + RBAC |
| Pinecone MCP | Separate server for Pinecone | Local/hosted MCP server | Fully managed vector index |
| Qdrant MCP | Separate server for Qdrant | Local/hosted MCP server | Self-host or Qdrant Cloud |
Choose the Weaviate server when your vectors already live in Weaviate and you want native hybrid search; the Pinecone and Qdrant servers cover their own stores.
Installation
First enable the MCP server on your Weaviate instance (v1.37.1+) by setting the environment variable
MCP_SERVER_ENABLED=true. It is then served at /v1/mcp on the same port as the Weaviate REST API.
Claude Code
claude mcp add --transport http weaviate https://<your-weaviate-host>/v1/mcp
Claude Desktop
{
"mcpServers": {
"weaviate": {
"url": "https://<your-weaviate-host>/v1/mcp",
"type": "http"
}
}
}
Requirements
- A Weaviate instance on v1.37.1 or later (self-hosted or Weaviate Cloud).
MCP_SERVER_ENABLED=trueset on that instance.- A Weaviate API key whose RBAC role covers the collections Claude should access.
- An MCP client (Claude Code or Claude Desktop).
Security
- The server runs inside Weaviate and honors its existing API-key authentication and RBAC.
- Scope the API key to least privilege — read-only where Claude only needs to query.
- The
weaviate-objects-upserttool writes data; restrict write access accordingly. - Treat the endpoint URL and API key as secrets.
Source Verification Notes
Verified on 2026-06-17:
- Weaviate's documentation (
docs.weaviate.io/weaviate/configuration/mcp-server) describes the built-in MCP server, theMCP_SERVER_ENABLEDflag, the/v1/mcpendpoint, API-key/RBAC auth, and the four tools listed above. - The former standalone repository
github.com/weaviate/mcp-server-weaviatestates it is deprecated in favor of the built-in server. - Claude Code's MCP documentation describes the HTTP connector setup used here.
Source citations
Add this badge to your README
How it compares
Weaviate MCP Server for Claude side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
| Field | Weaviate MCP Server for Claude Connect Claude to a Weaviate vector database — run hybrid search, inspect collection config, list tenants, and upsert objects — using Weaviate's built-in Model Context Protocol server. Open dossier | Milvus MCP Server MCP server from Zilliz for connecting Claude to Milvus vector database collections, text search, vector search, hybrid search, inserts, deletes, indexes, collection loading, database switching, and collection metadata. Open dossier | Pinecone Developer MCP Server Official Pinecone Developer MCP server that connects Claude and other MCP clients to Pinecone projects and documentation for index management, record upserts, semantic search, cascading multi-index search, reranking, and documentation lookup over integrated-inference indexes. Open dossier | Chroma MCP Server Official Chroma MCP server for connecting Claude to Chroma collections, documents, semantic search, full-text search, metadata filtering, persistent storage, self-hosted Chroma, and Chroma Cloud. Open dossier |
|---|---|---|---|---|
| Trust | ||||
| Install risk | Review first | Review first | Review first | Review first |
| Notes | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ |
| Category | mcp | mcp | mcp | mcp |
| Source | source-backed | source-backed | source-backed | source-backed |
| Author | Weaviate | Zilliz | Pinecone | Chroma |
| Added | 2026-06-17 | 2026-06-06 | 2026-06-11 | 2026-06-06 |
| Platforms | Claude CodeClaude Desktop | Claude CodeClaude Desktop | Claude CodeClaude Desktop | Claude CodeClaude Desktop |
| Source repo | — | — | — | — |
| Safety notes | ✓The MCP server runs inside your Weaviate instance and respects its existing RBAC; scope the API key to least privilege. The object-upsert tool writes data — restrict write access to the collections Claude should modify. | ✓Milvus MCP can read collection metadata, query collections, and run text, vector, text-similarity, multi-vector, and hybrid searches. Write-capable tools can create collections, insert data, upsert data, delete entities, create indexes, bulk insert records, load collections, release collections, and switch databases. The README notes that the environment file has higher priority than command-line arguments, so stale or unexpected environment settings can silently change the target Milvus instance. SSE and Streamable HTTP modes can expose database operations over HTTP and should be network-restricted. Remote Milvus or Zilliz Cloud credentials should be scoped to the collections and databases Claude is allowed to access. | ✓The server can create indexes and upsert records, so an agent with a write-capable API key can change live Pinecone project state. Run the npm package `@pinecone-database/mcp` through `npx`, which downloads and executes the published package on each launch; pin to a trusted version if reproducibility matters. Scope the Pinecone API key to the intended project and use read-only or least-privilege keys when index creation and writes are not needed. Require human review before `create-index-for-model` and `upsert-records` runs that mutate production indexes. | ✓Chroma MCP can create, modify, and delete collections. Document tools can add, update, query, retrieve, and delete documents, metadata, custom IDs, and embeddings. Persistent, HTTP, and cloud modes can mutate durable retrieval stores rather than temporary test collections. External embedding functions can send document text or image-derived content to third-party embedding providers. Chroma Cloud and self-hosted HTTP modes require careful handling of tenants, databases, API keys, custom auth credentials, SSL settings, and network exposure. Retrieved context can influence Claude output even when stale, irrelevant, over-broad, or not authorized for the task. |
| Privacy notes | ✓Query text, retrieved objects, and collection metadata enter the MCP client context and the model's prompt. The Weaviate endpoint URL and API key are secrets — keep them in the client config or environment, not in shared repositories. | ✓Milvus collections can contain embeddings, sparse vectors, scalar fields, IDs, document chunks, metadata, image or multimodal references, query logs, and retrieval results that reveal sensitive project or user data. Milvus URI, tokens, database names, collection names, vector payloads, filter expressions, and retrieved records should stay out of prompts, issues, logs, screenshots, and committed files. Search results can include private source content that may be re-exposed in model transcripts or downstream tickets. HTTP transports, debug tools, query traces, failed-search artifacts, backups, and benchmark datasets need retention and access-control review. | ✓The `PINECONE_API_KEY` is read from the MCP client environment and grants access to the associated Pinecone project; keep it out of prompts, notes, and committed files. Index names, configurations, namespaces, statistics, record contents, and search queries can be exposed to the MCP client and model provider. Records and search text may contain embedded documents, customer data, or proprietary content, so review what is sent into indexes and returned by searches. Documentation search and tool calls reach Pinecone endpoints such as api.pinecone.io, so network access and request metadata leave the local machine. | ✓Collections can store source documents, chunks, embeddings, metadata, IDs, filters, and query results that reveal private project, customer, or research data. Query text, retrieved documents, metadata filters, and embedding inputs may expose sensitive information to Chroma Cloud, self-hosted operators, embedding providers, logs, or downstream model providers. CHROMA_API_KEY, custom auth credentials, embedding provider API keys, tenant IDs, database names, hostnames, and dotenv files should stay out of prompts, issues, logs, screenshots, and committed files. Persistent data directories and exported collections need the same access control, backup, encryption, and retention review as the source documents they index. |
| Prerequisites |
|
|
|
|
| Install | | | | |
| Config | | | | |
| Citations | ||||
| Claim | Unclaimed | Unclaimed | Unclaimed | Unclaimed |
Signals
Loading live community signals…
A short, calm digest of reviewed Claude resources. Unsubscribe any time.