- Explore MCP Servers
- mcp-nim
Mcp Nim
What is Mcp Nim
mcp-nim is a Nim SDK designed for implementing the Model Context Protocol (MCP) specifically for AI agents, enabling them to manage and utilize contextual information effectively.
Use cases
Use cases for mcp-nim include building AI agents that can read and process files, respond to user queries in a contextual manner, and manage complex interactions across different platforms.
How to use
To use mcp-nim, first install the Nim compiler, then clone the repository and configure the MCP settings according to your environment. You can create MCP servers by defining request handlers and connecting them to the transport layer.
Key features
Key features of mcp-nim include asynchronous request handling, integration with Claude and Cursor applications, and the ability to create custom MCP servers tailored to specific use cases.
Where to use
mcp-nim can be used in various fields such as AI development, chatbot implementation, and any application requiring context-aware AI interactions.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Overview
What is Mcp Nim
mcp-nim is a Nim SDK designed for implementing the Model Context Protocol (MCP) specifically for AI agents, enabling them to manage and utilize contextual information effectively.
Use cases
Use cases for mcp-nim include building AI agents that can read and process files, respond to user queries in a contextual manner, and manage complex interactions across different platforms.
How to use
To use mcp-nim, first install the Nim compiler, then clone the repository and configure the MCP settings according to your environment. You can create MCP servers by defining request handlers and connecting them to the transport layer.
Key features
Key features of mcp-nim include asynchronous request handling, integration with Claude and Cursor applications, and the ability to create custom MCP servers tailored to specific use cases.
Where to use
mcp-nim can be used in various fields such as AI development, chatbot implementation, and any application requiring context-aware AI interactions.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Content
Nim Model Context Protocol (MCP) SDK
Nim implementation of the Model Context Protocol (MCP) for building AI agent capabilities.
Installation
- Install Nim compiler
- Clone repository:
git clone https://github.com/yourusername/mcp-nim.git
cd mcp-nim
Configuration
Claude Integration
-
Locate MCP config file:
- Claude Desktop:
~/Library/Application Support/Claude/claude_desktop_config.json(macOS) - Claude Desktop:
C:\Users\xxx\AppData\Roaming\Claude\claude_desktop_config.json(Windows) - Cursor:
%APPDATA%\Cursor\User\globalStorage\rooveterinaryinc.roo-cline\settings\cline_mcp_settings.json(Windows)
- Claude Desktop:
-
Add server configuration:
{
"mcpServers": {
"filesystem-server": {
"command": "nim",
"args": [
"c",
"-r",
"examples/filesystem_server.nim"
],
"cwd": "/path/to/sdk/root",
"disabled": false
}
}
}
Development
Creating MCP Servers
import std/[asyncdispatch, json, options]
import ../src/mcp/[client, types]
import ../src/mcp/shared/[protocol, stdio, transport]
proc main() {.async.} =
let transport = newStdioTransport()
let protocol = newProtocol(some(ProtocolOptions()))
protocol.setRequestHandler(Request, proc(
request: Request,
extra: RequestHandlerExtra
): Future[McpResult] {.async.} =
if request.`method` == "your-method":
result = McpResult()
else:
raise newMcpError(ErrorCode.MethodNotFound)
)
await protocol.connect(transport)
await sleepAsync(1000)
await protocol.close()
when isMainModule:
waitFor main()
Examples
Filesystem Server
protocol.setRequestHandler("tools/list", proc(request: base_types.JsonRpcRequest, extra: protocol.RequestHandlerExtra): Future[JsonNode] {.async.} =
result = %*{
"tools": [
{
"name": "read_file",
"description": "Read file contents",
"inputSchema": {
"type": "object",
"properties": {
"path": {"type": "string"}
},
"required": ["path"],
"additionalProperties": false
}
}
]
}
)
Features
- Type-safe RPC communication
- JSON serialization/deserialization
- Async I/O with progress notifications
- Capability-based security model
- Thread-safe implementations
Building
nimble build
nimble test
nimble docs
License
MIT License
Dev Tools Supporting MCP
The following are the main code editors that support the Model Context Protocol. Click the link to visit the official website for more information.










