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.

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

Weaviate (MCP archived)

Name: Top MCPs — curated MCP directory
Creator: Top MCPs
License: https://creativecommons.org/licenses/by/4.0/

Archived

Vector database with first-class hybrid (vector + keyword) and modular embeddings (MCP server archived — package no longer published).

Score 67(?)WeaviateBSD-3-Clause 162Verified May 31, 2026Top MCPs for AI & Machine Learning →

Install View on GitHub

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

Setup recipe

Pick your client, then follow the three steps.

Install

claude_desktop_config.jsonjson

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

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

CLI or .mcp.jsonshell

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

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

.cursor/mcp.jsonjson

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

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

.vscode/mcp.jsonjsonc

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

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

~/.codeium/windsurf/mcp_config.jsonjson

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

Open via Cascade → hammer icon → Configure.

cline_mcp_settings.jsonjson

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

Open via the Cline sidebar → MCP Servers → Edit.

~/.continue/config.jsonjson

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

Continue uses modelContextProtocolServers with a transport block.

~/.codex/config.tomlshell

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

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

~/.config/zed/settings.jsonjsonc

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

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

ChatGPT → Apps directorynone

Weaviate (MCP archived) 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.

2
Set required secrets
Set WEAVIATE_URL, WEAVIATE_API_KEY in your shell environment before launching your MCP client.
3
Try a minimum working prompt
Minimum working prompt pending verification. Try any prompt from the MCP’s README once installed.

Tools & permissions

Tools list pending verification. The server exposes tools over MCP; we haven’t yet parsed its capability manifest into this page. Check the GitHub repo for the authoritative list.

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.

Agent prompt pack

— copy into Claude, Cursor, or ChatGPT.

Paste into Claude, Cursor, or ChatGPT. Edit the [brackets] before sending.

Recommend the best MCP servers for [task: e.g. ai & machine learning work] in [client: Claude].

Constraints:
- Prefer tools that are [official | open-source | read-only] — pick what matters for my use case.
- Exclude MCPs that require [e.g. a paid plan, OAuth-only flows, remote-only transport].
- Return at most 3 picks, ranked.

For each pick include:
1. One-sentence rationale.
2. The ready-to-paste install snippet for my client.
3. Any required secrets I need to create before installing.

Cross-check the top-mcps.com listing: https://top-mcps.com/top-mcps-for-ai-machine-learning

Compare Weaviate (MCP archived) against a real alternative. Swap the second MCP in [brackets] if you want a different match.

Compare Weaviate (MCP archived) MCP vs [Pinecone MCP] for the following job: [describe the job, e.g. "let an agent create GitHub issues on bug triage"].

Judge them on:
- Setup time and complexity (what a new user hits first).
- Auth model (none / API key / OAuth 2.1) and credential risk.
- Transport (stdio / Streamable HTTP / SSE) and where the server runs.
- Required secrets and the blast radius if they leak.
- Operational risk in an unattended agent loop.
- Which one is "good enough" for a weekend prototype vs. production.

End with one sentence: which should I pick for my scenario, which is: [my scenario].

References:
- https://top-mcps.com/mcp/weaviate
- top-mcps.com listing for Pinecone

Asks the agent to install and verify. Works inside Claude Code, Cursor Agent, Codex CLI.

Install the Weaviate (MCP archived) MCP server for my [client: Claude] at the default config path for that client.

Use the exact install snippet published at https://top-mcps.com/mcp/weaviate (fetch https://top-mcps.com/mcp/weaviate.json for the canonical server.json if you can read URLs).

Before finishing:
1. Create the required secrets (WEAVIATE_URL, WEAVIATE_API_KEY) and put them in the appropriate env block — do not hard-code them.
2. Restart or reload the client so it picks up the new server.
3. Verify the server is connected (green / running state) and at least one tool is listed.
4. If anything fails, read the client's MCP logs and report the exact error — do not silently retry.

Confirm when done and list the tools the server now exposes.

Frequently asked questions

What changed

— 2 updates tracked.

May 31, 2026
Refreshed install snippets and fact sheet; verified for 2026.
Feb 20, 2025
Initial directory listing.

More AI & Machine Learning MCPs

Other tools in the same category worth evaluating.

Hugging Face

Search, inspect, and run Hugging Face models and datasets from an agent.

huggingfacemlmodelsinference

3 minLow

Replicate

Run any open-source model on Replicate from inside an AI agent.

aimlreplicateinference

3 minLow

OpenRouter

Route one prompt across 300+ LLMs with a single API key.

aillmopenrouterinference

2 minLow

Compared with Weaviate (MCP archived)

Side-by-side breakdowns for the choices people most often weigh against this MCP.

Weaviate (MCP archived)vsPinecone Weaviate (MCP archived)vsQdrant

Exploring Top MCPs for AI & Machine Learning? See all AI & Machine Learning MCPs →