GameCode MCP2
A Model Context Protocol (MCP) server for tool integration, configured using a tools.yaml file.
GameCode MCP2
A clean (and possibly naive) implementation of the Model Context Protocol (MCP) for tool integration.
Motivation - as few dependencies as possible, as simple and auditable a configuration as possible.
⚠️ Security Notice
MCP is early technology. Allowing LLMs to execute system commands is inherently risky. This implementation prioritizes auditability over features - you can read every line that processes LLM requests. Even so, proceed with caution. Only time will tell if MCP's approach is sound.
Key Features
- Direct tool exposure - Tools defined in
tools.yamlare exposed directly via MCP, not through meta-tools - Clean protocol implementation - Pure JSON-RPC 2.0 over stdio without external dependencies
- Dynamic tool loading - Configure tools via YAML without recompiling
- Built-in and external tools - Support for both internal handlers and external commands
Architecture
This workspace contains two crates:
mcp-server- The MCP server that loads tools fromtools.yamland exposes them via the protocolmcp-client- A client library for testing and integration
Usage
Running the Server
# Build the server
cargo build --release --bin gamecode-mcp2
# Create a tools.yaml file (see examples/tools.yaml)
cp examples/tools.yaml .
# Run the server (it communicates via stdio)
./target/release/gamecode-mcp2
Using with Claude Desktop
Add to your Claude Desktop configuration:
{
"mcpServers": {
"gamecode": {
"command": "/path/to/gamecode-mcp2"
}
}
}
Using with gamecode-cli
The mcp-client crate can be used as a dependency in gamecode-cli for MCP integration.
Tool Configuration
Tools are defined in tools.yaml:
tools:
- name: my_tool
description: Description for the LLM
command: /path/to/command # or "internal" for built-in
args:
- name: param1
description: Parameter description
required: true
type: string
cli_flag: --param # null for positional
internal_handler: handler_name # for internal tools
Protocol
This implementation follows the MCP specification:
initialize- Handshake with clienttools/list- Returns all available toolstools/call- Execute a specific tool
Tools are exposed directly, not through meta-tools like "run".
Похожие серверы
Scout Monitoring MCP
спонсорPut performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
спонсорAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
Remote MCP Server (Authless)
An example of a remote MCP server without authentication, deployable on Cloudflare Workers.
mcpcodeserver
Instead of direct calling MCP tools, mcpcode server transforms MCP tool calls into TypeScript programs, enabling smarter, lower-latency orchestration by LLMs.
Agent Forge
A platform for creating and managing AI agents with specific personalities and simulating their responses. Requires a DeepSeek API key.
Angular MCP Server
An MCP server for accessing the official Angular documentation.
MediaWiki
Interact with MediaWiki installations through the MediaWiki API as a bot user.
Swift Package Index
Search for Swift packages and retrieve their READMEs and metadata from the Swift Package Index.
mcproc
Manage background processes for AI agents using the Model Context Protocol (MCP).
MCPStore
An enterprise-grade MCP tool management solution for simplifying AI Agent tool integration, service management, and system monitoring.
Shrike Security
AI agent security scanner — protect LLM-powered apps from prompt injection, SQL injection, data exfiltration, and adversarial attacks via MCP.
ProjectFlow
A workflow management system for AI-assisted development with MCP support, featuring flexible storage via file system or PostgreSQL.