# Weaviate

> Vector database with first-class hybrid (vector + keyword) and modular embeddings.

[Canonical HTML page](https://top-mcps.com/mcp/weaviate) · [server.json](https://top-mcps.com/mcp/weaviate.json) · [methodology](https://top-mcps.com/about/methodology)

## Install

### Claude Desktop — `claude_desktop_config.json`

Paste under mcpServers. Fully quit and reopen Claude after editing.

```json
{
  "mcpServers": {
    "weaviate": {
      "command": "uvx",
      "args": [
        "mcp-server-weaviate"
      ],
      "env": {
        "WEAVIATE_URL": "${WEAVIATE_URL}",
        "WEAVIATE_API_KEY": "${WEAVIATE_API_KEY}"
      }
    }
  }
}
```

### Claude Code — `CLI or .mcp.json`

Run from your repo. Commit .mcp.json to share with your team.

```shell
# export WEAVIATE_URL=https://your-cluster.weaviate.network
# export WEAVIATE_API_KEY=YOUR_API_KEY
claude mcp add weaviate -- uvx mcp-server-weaviate
```

### Cursor — `.cursor/mcp.json`

Global path: ~/.cursor/mcp.json. Reload window after editing.

```json
{
  "mcpServers": {
    "weaviate": {
      "command": "uvx",
      "args": [
        "mcp-server-weaviate"
      ],
      "env": {
        "WEAVIATE_URL": "${WEAVIATE_URL}",
        "WEAVIATE_API_KEY": "${WEAVIATE_API_KEY}"
      }
    }
  }
}
```

### VS Code — `.vscode/mcp.json`

VS Code uses the "servers" key (not "mcpServers").

```jsonc
{
  "servers": {
    "weaviate": {
      "command": "uvx",
      "args": [
        "mcp-server-weaviate"
      ],
      "env": {
        "WEAVIATE_URL": "${WEAVIATE_URL}",
        "WEAVIATE_API_KEY": "${WEAVIATE_API_KEY}"
      }
    }
  }
}
```

### Windsurf — `~/.codeium/windsurf/mcp_config.json`

Open via Cascade → hammer icon → Configure.

```json
{
  "mcpServers": {
    "weaviate": {
      "command": "uvx",
      "args": [
        "mcp-server-weaviate"
      ],
      "env": {
        "WEAVIATE_URL": "${WEAVIATE_URL}",
        "WEAVIATE_API_KEY": "${WEAVIATE_API_KEY}"
      }
    }
  }
}
```

### Cline — `cline_mcp_settings.json`

Open via the Cline sidebar → MCP Servers → Edit.

```json
{
  "mcpServers": {
    "weaviate": {
      "command": "uvx",
      "args": [
        "mcp-server-weaviate"
      ],
      "env": {
        "WEAVIATE_URL": "${WEAVIATE_URL}",
        "WEAVIATE_API_KEY": "${WEAVIATE_API_KEY}"
      }
    }
  }
}
```

### Continue — `~/.continue/config.json`

Continue uses modelContextProtocolServers with a transport block.

```json
{
  "experimental": {
    "modelContextProtocolServers": [
      {
        "transport": {
          "type": "stdio",
          "command": "uvx",
          "args": [
            "mcp-server-weaviate"
          ],
          "env": {
            "WEAVIATE_URL": "${WEAVIATE_URL}",
            "WEAVIATE_API_KEY": "${WEAVIATE_API_KEY}"
          }
        }
      }
    ]
  }
}
```

### Codex CLI — `~/.codex/config.toml`

Codex uses TOML. Each server is a [mcp_servers.<name>] subtable.

```shell
# ~/.codex/config.toml
[mcp_servers.weaviate]
command = "uvx"
args = [
  "mcp-server-weaviate",
]
env = { WEAVIATE_URL = "${WEAVIATE_URL}", WEAVIATE_API_KEY = "${WEAVIATE_API_KEY}" }
```

### Zed — `~/.config/zed/settings.json`

Zed calls them "context_servers". Settings live-reload on save.

```jsonc
{
  "context_servers": {
    "weaviate": {
      "command": {
        "path": "uvx",
        "args": [
          "mcp-server-weaviate"
        ]
      },
      "env": {
        "WEAVIATE_URL": "${WEAVIATE_URL}",
        "WEAVIATE_API_KEY": "${WEAVIATE_API_KEY}"
      }
    }
  }
}
```

### ChatGPT — `ChatGPT → Apps directory`

Weaviate doesn't ship a hosted HTTPS endpoint today. ChatGPT supports remote MCP servers only — to use this server in ChatGPT you'll need to deploy it to a public HTTPS URL first (e.g. via Cloudflare Workers or Vercel) or wait for an official remote build.

```none

```

## At a glance

- **Maintainer:** Weaviate
- **Transport:** stdio
- **Auth model:** API key
- **Required secrets:** WEAVIATE_URL, WEAVIATE_API_KEY
- **Supported clients:** Claude, Cursor, Any MCP-compatible client
- **License:** BSD-3-Clause
- **Language:** Python
- **Latest version:** latest
- **Last verified:** 2026-05-26
- **GitHub stars:** 161 (fetched 2026-05-26T10:50:23.226Z)
- **Score:** 79/100 (rubric 2026-04 — see https://top-mcps.com/about/methodology)
- **Source:** https://github.com/weaviate/mcp-server-weaviate

## Security & scope

- **Access scope:** read-write
- **Sandbox:** API key grants cluster-wide access. Use multi-tenancy primitives to isolate data per tenant.
- **Gotchas:**
  - Schema changes are forward-only in OSS; plan migrations.
  - Generative modules call external LLMs; their privacy policies apply.

## Quick answer

**What it does.** Exposes Weaviate's schema, data, and search APIs as MCP tools. Manage classes, ingest objects with vectors, run hybrid queries, and call generative-search workflows.

**Best for:**
- Hybrid (BM25 + vector) retrieval
- Generative search at the DB layer
- Multi-modal indexing
- Schema-first vector workflows

**Not for:**
- Zero-ops use cases
- Pure vector workloads where simplicity wins

## Description

The Weaviate MCP wraps Weaviate's schema-driven vector database. Strong support for hybrid search (BM25 + vectors), pluggable embedding modules, and a generative search layer that calls an LLM at retrieval time. Self-host or managed.

## Why it matters

When retrieval needs to combine keyword precision with semantic recall, hybrid search beats pure vector search. Weaviate has the most mature hybrid implementation of the open-source vector DBs.

## Key features

- Hybrid search built in
- Generative modules
- Pluggable embedding providers
- Multi-tenancy
- Self-host or managed

## FAQ

### When is hybrid actually better than pure vector?

When the corpus contains rare or out-of-vocab terms (product SKUs, scientific names, code identifiers). Vectors generalize; BM25 nails exact matches. The combination gets you both.

### What is "generative search" in this context?

Weaviate can call an LLM at query time to summarize or transform retrieved objects before returning them — useful when the downstream agent does not want raw chunks.

### Self-host or cloud?

Both supported. Self-host via Docker or Kubernetes; cloud via Weaviate Cloud Services. Schema and APIs are identical across both.

## Changelog

- **2026-05-26** — Refreshed install snippets and fact sheet; verified for 2026.
- **2025-02-20** — Initial directory listing.