MCP server
Weaviate MCP server
An MCP server built into Weaviate that lets AI read collection settings, list tenants, run hybrid search and, when allowed, upsert objects.
- Official server
- Databases
At a glance
- Maintained by
- Weaviate
- Tools exposed
- 4 listed below
- Reviewed
- September 24, 2026
Why it matters
What it does and why it matters
Weaviate is an open-source vector database with strong hybrid search, which combines keyword and meaning-based search. Weaviate now builds its MCP server into the database itself, from version 1.37.1, so there is no separate server to run. An assistant can read collection settings, list tenants, run hybrid searches and, if allowed, upsert objects.
Hybrid search matters for business content, because many questions mix natural language with exact terms such as product codes or names.
The built-in server is in preview at review time. It uses Weaviate API keys and respects role-based access control. Write access is off by default on Weaviate Cloud and must be enabled with a server setting. The older standalone repository is deprecated.
Use cases
Best business use cases
Hybrid search
Multi-tenant apps
Collection review
Knowledge assistants
Controlled updates
Tools
Available tools
Tool names as published by the maintainer at review time. Versions change, so check the repository for the current list.
Read and write: Mostly read; the upsert tool needs write access, which is off by default on Weaviate Cloud.
-
weaviate-collections-get-configShows collection schema configuration.
-
weaviate-tenants-listLists tenants in multi-tenant collections.
-
weaviate-query-hybridRuns hybrid vector and keyword search.
-
weaviate-objects-upsertInserts or updates objects in batch (write access only).
Workflows
Example workflows
Tune product search
-
1
Read the products collection settings.
-
2
Run hybrid searches for real queries.
-
3
Compare results for exact and vague queries.
-
4
Adjust the keyword and vector balance.
-
5
Repeat until results look right.
Search one tenant
-
1
List tenants in the collection.
-
2
Pick the customer's tenant.
-
3
Run the search within it.
-
4
Return results with sources.
-
5
No cross-tenant data is exposed.
Prompts
Example prompts
“Show the configuration of the Articles collection.”
“Run a hybrid search for "invoice template VAT" and show the top five.”
“List the tenants in the Documents collection.”
Setup
Installation and configuration
Examples for Claude Desktop and Claude Code. Replace the placeholder values with your own keys, and store secrets outside version control.
Claude Desktop: claude_desktop_config.json
{
"mcpServers": {
"weaviate-local": {
"type": "streamable-http",
"url": "http://localhost:8080/v1/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}Claude Code: terminal
claude mcp add --transport http weaviate http://localhost:8080/v1/mcp --header "Authorization: Bearer YOUR_API_KEY"- Hosted server: http(s)://<your-weaviate-host>/v1/mcp on the REST API port (for example http://localhost:8080/v1/mcp). Enable with MCP_SERVER_ENABLED=true..
- Needs: Weaviate API key (Bearer), respects RBAC; Server env: MCP_SERVER_ENABLED=true; optional MCP_SERVER_WRITE_ACCESS_ENABLED.
Security
Security considerations
-
Write off by default
Keep write access disabled unless needed.
-
Role-based access
Use API keys tied to roles with minimal permissions.
-
Preview feature
The built-in server is in preview. Test before relying on it.
-
Tenant isolation
Confirm tenant boundaries in multi-tenant setups.
Related servers
Servers that pair well with it
Qdrant
Qdrant's official MCP server gives AI a semantic memory: store information in a Qdrant collection and find it again by meaning.
Pinecone
Pinecone's official developer MCP server lets AI search Pinecone docs, manage indexes, upsert records, search and rerank.
Elasticsearch
Elastic's Agent Builder MCP endpoint lets AI search indices, run ES|QL queries and read mappings and documents in Elasticsearch.
Keep exploring
Solutions and services that use it
Related services
View all related services- MCP integration Connect AI assistants to your CRM, files, databases and tools through Model Context Protocol servers, with safe permissions.
- Database design Data models that stay fast and correct as your business grows, with backups and access rules in place.
- AI Product Development AI agents, knowledge assistants, copilots and document automation built into the way your team already works.
- Multi-tenant architecture One product serving many customer accounts, with each account's data kept separate and secure.
- RAG knowledge assistants Assistants that answer questions from your own documents and show where each answer came from.
- SaaS Product Development MVPs, subscription platforms, admin panels and multi-tenant products, planned to grow past the first launch.
Solutions
View all solutions- Automated reporting Reports that build themselves from your systems on schedule, with a plain-language summary of what changed.
- Knowledge assistant (RAG) Ask a question in plain words and get an answer from your own documents, with links to the sources.
- Internal help desk assistant An assistant in Slack or Teams that answers policy and how-to questions from your handbooks and opens tickets when needed.
- AI sales research agent Short, sourced briefings on each prospect before a call, drafted by an AI agent from public information and your CRM.
- Forecasting dashboards Forecast demand from your sales history and seasonality, and flag items to reorder before they run out.
- Payroll automation Turn pay rules, attendance and leave into tested software so the monthly run becomes a review and payslips go out in one batch.
Industries
View all industries- Property management Tenant portals, maintenance tracking, owner statements and inbox automation for property managers.
- Legal Contract review assistants, knowledge search, intake and document automation for law firms and in-house legal teams.
- Professional services Client portals, proposal drafting, knowledge assistants and internal tools for consultancies, agencies and firms.
Case studies
View all case studiesGuides and articles
View all guides and articles- How to connect AI to your database safely Let staff ask questions of your data in plain English without risking production systems or sensitive records.
- What is RAG and when do you need it? How retrieval-augmented generation lets AI answer from your documents, when it fits and how to build it well.
- How to automate reporting with AI and MCP Build reports that assemble themselves from your systems through MCP, with a written summary people can trust.
- PostgreSQL vs MySQL The two most popular open-source databases compared for business applications.
- RAG vs fine-tuning Two ways to make AI work with your knowledge, compared by cost, accuracy and upkeep.
AI models
View all ai models- text-embedding-3-large OpenAI's most capable embedding model for search and retrieval, with 3,072-dimension vectors and support for English and other languages.
- text-embedding-3-small OpenAI's efficient, lowest-cost embedding model, with 1,536-dimension vectors for search, retrieval and similarity at scale.
- Cohere Embed v4 Cohere's multimodal embedding model for enterprise search, embedding text, images and mixed documents, with flexible vector sizes and long inputs.
- Voyage 4 Voyage AI's current embedding series, now part of MongoDB, with large, standard and lite models that share one embedding space.
- Embeddings Models that turn text into vectors for search, retrieval, clustering and recommendations.
- Gemini Embedding 2 Google's current embedding model, multimodal: it embeds text, images, video, audio and PDFs for search and retrieval.
Glossary terms
View all glossary terms- RAG RAG, or retrieval-augmented generation, is a method where an AI system first finds relevant passages in your documents, then answers using only those passages.
- Multi-tenant Multi-tenant describes software where one application and database serve many customers, called tenants, while keeping each customer's data separate.
- Database A database is an organized store of data that software can search, update and keep consistent, such as customers, orders or bookings.
- Embeddings Embeddings are lists of numbers that represent the meaning of text or images, so software can find items that are similar in meaning.
- Semantic search Semantic search finds results by meaning rather than exact words, so a search for "reset my login" can find an article titled "Forgot your password".
- Vector database A vector database stores embeddings, lists of numbers that represent meaning, and quickly finds the ones most similar to a query.
FAQ
Questions people ask us
Have a question that is not here? Ask us directly.
The standalone repository is deprecated. The MCP server is now built into Weaviate from version 1.37.1.
Only with write access enabled, which is off by default on Weaviate Cloud.
It was in preview at review time. Test it on your own workload.