About semantic-search-mcp-server
semantic-search-mcp-server is an MCP server built with mcp-framework for Claude Desktop users who need semantic search. Its tools can be extended by developers using the framework's CLI.
Key features
- 01Semantic search for Claude Desktop
- 02Built with mcp-framework
- 03Extensible tool structure
- 04CLI-based tool scaffolding
Use cases
- 01Adding semantic search to Claude Desktop
- 02Extending the server with custom tools
MCP support
It exposes tools to MCP clients as an MCP server. The README describes Claude Desktop configuration and adding tools through mcp-framework.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEsemantic-search-mcp-server
A Model Context Protocol (MCP) server built with mcp-framework for enhancing Claude Desktop with semantic search capabilities.
Documentation
For detailed setup instructions and usage:
- User Guide - Step-by-step setup instructions for Claude Desktop users
- Developer Guide - Technical information for developers working on or extending this server
Quick Start
# Install dependencies
npm install
# Build the project
npm run build
Project Structure
semantic-search-mcp-server/
├── src/
│ ├── tools/ # MCP Tools
│ │ └── ExampleTool.ts
│ └── index.ts # Server entry point
├── Userguide.md # Setup guide for Claude Desktop users
├── DeveloperGuide.md # Technical guide for developers
├── package.json
└── tsconfig.json
For Developers
The sections below contain technical information for those who want to modify or extend the server.
Adding Components
The project comes with an example tool in src/tools/ExampleTool.ts. You can add more tools using the CLI:
# Add a new tool
mcp add tool my-tool
# Example tools you might create:
mcp add tool data-processor
mcp add tool api-client
mcp add tool file-handler
Tool Development
Example tool structure:
import { MCPTool } from "mcp-framework";
import { z } from "zod";
interface MyToolInput {
message: string;
}
class MyTool extends MCPTool<MyToolInput> {
name = "my_tool";
description = "Describes what your tool does";
schema = {
message: {
type: z.string(),
description: "Description of this input parameter",
},
};
async execute(input: MyToolInput) {
// Your tool logic here
return `Processed: ${input.message}`;
}
}
export default MyTool;
Publishing to npm
-
Update your package.json:
- Ensure
nameis unique and follows npm naming conventions - Set appropriate
version - Add
description,author,license, etc. - Check
binpoints to the correct entry file
- Ensure
-
Build and test locally:
npm run build npm link semantic-search-mcp-server # Test your CLI locally -
Login to npm (create account if necessary):
npm login -
Publish your package:
npm publish
After publishing, users can add it to their claude desktop client (read below) or run it with npx
## Using with Claude Desktop
### Local Development
Add this configuration to your Claude Desktop config file:
**MacOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`
**Windows**: `%APPDATA%/Claude/claude_desktop_config.json`
```json
{
"mcpServers": {
"semantic-search-mcp-server": {
"command": "node",
"args":["/absolute/path/to/semantic-search-mcp-server/dist/index.js"]
}
}
}
After Publishing
Add this configuration to your Claude Desktop config file:
MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"semantic-search-mcp-server": {
"command": "npx",
"args": ["semantic-search-mcp-server"]
}
}
}
Building and Testing
- Make changes to your tools
- Run
npm run buildto compile - The server will automatically load your tools on startup
Learn More
Comments
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.