MultilspyLSP MCP server

MCP-MultilspyLSP is an MCP server that provides Language Server Protocol (LSP) capabilities to language models through multilspy. It enables AI assistants to access powerful language intelligence features like code completions, finding definitions, and references across multiple programming languages.

Features

• Language Intelligence: Get code completions, find definitions, references, and more
• Multi-language Support: Works with multiple programming languages including Python, Java, TypeScript, and more
• Easy Integration: Works with any MCP-compatible client like Claude Desktop
• Static Analysis: Leverage the power of language servers for code understanding

Installation

You can install the MCP-MultilspyLSP server using pip:

pip install mcp-multilspy

Requirements

• Python 3.12 or higher
• Language-specific requirements:
  • For Java: JDK 17.0.6 or higher
  • For JavaScript/TypeScript: Node.js v18.16.0 or higher

Usage

Starting the Server

You can start the server directly:

mcp-multilspy

Or install it in Claude Desktop:

mcp install mcp-multilspy

Supported Languages

The server supports multiple programming languages through various language servers:

• Java (Eclipse JDTLS)
• Python (jedi-language-server)
• Rust (Rust Analyzer)
• C# (OmniSharp/RazorSharp)
• TypeScript (TypeScriptLanguageServer)
• JavaScript (TypeScriptLanguageServer)
• Go (gopls)
• Dart (Dart Language Server)
• Ruby (Solargraph)

Example Usage

Here's how to use this server with an MCP client:

# Initialize a TypeScript language server session
session = await initialize_language_server(
    session_id="ts-session", 
    project_root="/path/to/project",
    language="typescript"
)

# Find where a symbol is defined
definitions = await request_definition(
    session_id="ts-session",
    file_path="src/index.ts",
    line=10,  # 0-indexed
    column=15  # 0-indexed
)

# Find all references to a symbol
references = await request_references(
    session_id="ts-session",
    file_path="src/index.ts",
    line=10,
    column=15
)

# Get code completion suggestions
completions = await request_completions(
    session_id="ts-session",
    file_path="src/index.ts", 
    line=10,
    column=15
)

# Get hover information
hover_info = await request_hover(
    session_id="ts-session",
    file_path="src/index.ts",
    line=10,
    column=15
)

# Get document symbols
symbols = await request_document_symbols(
    session_id="ts-session",
    file_path="src/index.ts"
)

# Clean up when done
await shutdown_language_server(session_id="ts-session")

This example demonstrates how to initialize a language server session, request various types of language intelligence information, and properly shut down the session when you're done.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.