mcpField
S
Semantic Search MCP Server

Semantic Search MCP Server

Local
github.com/mhartSearch4Updated 77w ago
Repository

About Semantic Search MCP Server

Semantic Search MCP Server searches documentation stored in a Vectorize database using the Agents SDK. It is intended for MCP clients that need to retrieve relevant documentation through semantic search.

Key features

  1. 01Semantic search over documentation
  2. 02Searches a Vectorize database
  3. 03Built with the Agents SDK

Use cases

  1. 01Find relevant documentation by topic
  2. 02Query documentation from an MCP client

MCP support

It exposes semantic search over documentation in a Vectorize database to MCP clients.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "semantic-search": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote"
      ]
    }
  }
}
Run commandnpx -y mcp-remote

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmmcp-remote

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Semantic Search MCP Server

Deploy to Cloudflare

An MCP Server using the Agents SDK that can search documentation stored in a Vectorize database.

The same code that powers the MCP Server at https://mcp.developers.cloudflare.com/sse (or https://mcp.developers.cloudflare.com/mcp for the stateless version)

Using in Claude Desktop

{
  "mcpServers": {
    "cloudflare-docs": {
      "command": "npx", // or may need the full path, eg if using volta: "/Users/myuser/.volta/bin/npx"
      "args": ["mcp-remote@latest", "https://mcp.developers.cloudflare.com/mcp"]
      // Below only needed if you're using a Zero Trust client like Cloudflare WARP
      // "env": {
      //   "NODE_EXTRA_CA_CERTS": "/path/to/certificate.pem"
      // }
    }
  }
}

Testing in Cloudflare's AI Playground

Go to https://playground.ai.cloudflare.com/ and enter https://mcp.developers.cloudflare.com/mcp as the MCP Server

Testing in VSCode

Type Shift-Cmd-P and choose "MCP: Add Server..." and then choose "HTTP (server-sent events)", then enter https://mcp.developers.cloudflare.com/sse as the URL.

Testing locally (requires a populated Vectorize DB)

npm run dev

Then go to https://playground.ai.cloudflare.com/ and enter http://localhost:8787/mcp as the MCP Server

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.