Sandbox
@GopherSecurity/gopher-mcp

C++ MCP SDK for servers, clients, and bindings

This repository provides a C++ implementation of the Model Context Protocol for building MCP servers and clients. It supports stdio, HTTP+SSE, Streamable HTTP, WebSocket, and TCP, with filters, observability, security, and a C API for other languages.

147 stars20 forksC++Updated 12d ago
Who it's for

Builders who want to add MCP protocol support to C++ apps or expose it through bindings in other languages.

What it delivers

You can build MCP servers and clients in C++ and reuse them from other languages without rewriting the protocol layer.

What it does

Multiple MCP transports

Supports stdio, HTTP+SSE, HTTPS+SSE, Streamable HTTP, WebSocket, and TCP.

Protocol and JSON-RPC handling

Implements MCP request, response, notification, and tool-calling flows on top of JSON-RPC 2.0.

Filter chain and middleware

Adds routing, CORS, rate limiting, circuit breaking, authentication, and metrics as composable filters.

Stable C API

Exposes `libgopher_mcp_c` so Python, TypeScript, Go, Rust, Java, C#, and Ruby can use the SDK.

Production-oriented runtime

Includes connection pooling, graceful shutdown, structured logging, and health endpoints.

Examples and tests

Provides sample servers and clients under `examples/` and broad coverage under `tests/` and `shell/`.

How to get it

  1. 1Run
    # From Cygwin bash shell
    ./build-mingw.sh           # Release build (default)
    ./build-mingw.sh debug     # Debug build
    ./build-mingw.sh release   # Release build
    ./build-mingw.sh clean     # Clean build directory

README

MCP C++ SDK - Model Context Protocol Implementation for C++

C++14 MCP License Platform Multi-Language

The most comprehensive C++ implementation of the Model Context Protocol (MCP) for building AI-powered applications. Production-ready SDK with enterprise features including multi-transport support, connection pooling, and multi-language bindings via C API (Python, TypeScript, Go, Rust, Java, C#, Ruby and more).

Please give a star if you find this useful!

Table of Contents

Architecture Overview

┌─────────────────────────────────────────────────────────────────────┐
│                         Application Layer                           │
│  ┌────────────────────────────────────────────────────────────────┐ │
│  │      MCP Server │ MCP Client │ Custom Applications             │ │
│  └────────────────────────────────────────────────────────────────┘ │
├─────────────────────────────────────────────────────────────────────┤
│                    Cross-Language Binding Layer                     │
│  ┌────────────────────────────────────────────────────────────────┐ │
│  │   Python │ TypeScript │ Go │ Rust │ Java │ C# │ Ruby │ Swift   │ │
│  └────────────────────────────────────────────────────────────────┘ │
├─────────────────────────────────────────────────────────────────────┤
│                          C API (FFI Layer)                          │
│  ┌────────────────────────────────────────────────────────────────┐ │
│  │   libgopher_mcp_c: Opaque Handles │ RAII Guards │ Type Safety  │ │
│  └────────────────────────────────────────────────────────────────┘ │
├─────────────────────────────────────────────────────────────────────┤
│                            Protocol Layer                           │
│  ┌──────────────┐ ┌──────────────┐ ┌──────────────┐ ┌────────────┐  │
│  │   JSON-RPC   │ │   Requests   │ │  Responses   │ │   Notify   │  │
│  │   Codec      │ │   Dispatch   │ │   Routing    │ │   Stream   │  │
│  └──────────────┘ └──────────────┘ └──────────────┘ └────────────┘  │
├─────────────────────────────────────────────────────────────────────┤
│                          Filter Chain Layer                         │
│  ┌──────────────┐ ┌──────────────┐ ┌──────────────┐ ┌────────────┐  │
│  │  HTTP / SSE  │ │   Routing    │ │ Rate Limiter │ │   Auth     │  │
│  │    Codecs    │ │   & CORS     │ │ Circuit Brk  │ │  Metrics   │  │
│  └──────────────┘ └──────────────┘ └──────────────┘ └────────────┘  │
├─────────────────────────────────────────────────────────────────────┤
│                           Transport Layer                           │
│  ┌────────────────────────────────────────────────────────────────┐ │
│  │   Stdio │ HTTP(S)+SSE │ Streamable HTTP │ WebSocket │ TCP      │ │
│  └────────────────────────────────────────────────────────────────┘ │
├─────────────────────────────────────────────────────────────────────┤
│                            Network Layer                            │
│  ┌────────────────┐ ┌────────────────┐ ┌────────────────┐           │
│  │   Connection   │ │    Listener    │ │     Socket     │           │
│  │   Management   │ │    & Accept    │ │   Interface    │           │
│  └────────────────┘ └────────────────┘ └────────────────┘           │
├─────────────────────────────────────────────────────────────────────┤
│                       Event Loop & Dispatcher                       │
│  ┌────────────────────────────────────────────────────────────────┐ │
│  │   Libevent │ Timer Management │ I/O Events │ Buffer │ Result   │ │
│  └────────────────────────────────────────────────────────────────┘ │
└─────────────────────────────────────────────────────────────────────┘

Design Principles

  1. Thread-Safe Dispatcher Model - All I/O in dispatcher threads, no complex synchronization
  2. Filter Chain Architecture - Modular, composable request processing
  3. Production Patterns - Connection pooling, circuit breaker, graceful shutdown

Cross-Language Support

Use MCP C++ SDK from any programming language via the stable C API (libgopher_mcp_c):

LanguageBinding TypeFeatures
Pythonctypes/cffiAsync support, type hints
TypeScript/Node.jsN-APIHigh performance, native async
GoCGOGoroutine-safe wrappers
RustFFISafe wrappers, ownership guarantees
JavaJNIAutomatic resource management
C#/.NETP/InvokeAsync/await support
RubyNative extensionGC integration
# Installation paths
Headers: /usr/local/include/gopher-mcp/mcp/c_api/
Library: /usr/local/lib/libgopher_mcp_c.{so,dylib,dll}

What is MCP?

Model Context Protocol (MCP) is an open protocol that enables AI models (like Claude, GPT, etc.) to securely interact with external tools, data sources, and services. MCP provides a standardized way for:

  • AI assistants to access files, databases, and APIs
  • Developers to expose tools and resources to AI models
  • Applications to integrate AI capabilities with enterprise systems

This MCP C++ SDK implements the official MCP specification in high-performance C++, suitable for:

  • Embedded systems and IoT devices
  • High-frequency trading and real-time applications
  • Game engines and graphics applications
  • Native desktop and mobile applications
  • Backend services requiring low latency

Features

CategoryFeatures
ProtocolFull MCP 2025-06-18, 2025-11-25 and 2026-07-28 specifications, JSON-RPC 2.0, resources, tools, prompts
Transportsstdio, HTTP+SSE, HTTPS+SSE, WebSocket, TCP
PerformanceZero-copy buffers, lock-free operations, connection pooling
ReliabilityCircuit breaker, rate limiting, retry with backoff, graceful shutdown
SecurityTLS/SSL, authentication middleware, request validation
ObservabilityStructured logging, metrics, health endpoints
Cross-LanguageC API for Python, Node.js, Go, Rust, Java, C#, Ruby bindings

Quick Start

Build and Install

# Show all available commands
make help

# Build
make

# Install (auto-prompts for sudo if needed)
make install

# Run tests
make test

Create an MCP Server

#include "mcp/server/mcp_server.h"

int main() {
    mcp::server::McpServerConfig config;
    config.server_name = "my-mcp-server";

    auto server = mcp::server::createMcpServer(config);

    // Register a tool
    mcp::Tool calculator;
    calculator.name = "add";
    calculator.description = "Add two numbers";

    server->registerTool(calculator, [](const std::string& name,
                                         const mcp::optional<mcp::Metadata>& arguments,
                                         mcp::server::SessionContext& ctx) {
        mcp::CallToolResult result;
        auto args = arguments.value();
        auto a_it = args.find("a");
        auto b_it = args.find("b");

        double a = mcp::holds_alternative<double>(a_it->second)
                       ? mcp::get<double>(a_it->second) : 0.0;
        double b = mcp::holds_alternative<double>(b_it->second)
                       ? mcp::get<double>(b_it->second) : 0.0;

        result.content.push_back(mcp::TextContent{"Result: " + std::to_string(a + b)});
        return result;
    });

    server->listen("http://0.0.0.0:3000");
    server->run();
}

Create an MCP Client

#include "mcp/client/mcp_client.h"

int main() {
    mcp::client::McpClientConfig config;
    config.client_name = "my-mcp-client";

    auto client = mcp::client::createMcpClient(config);
    client->connect("http://localhost:3000");

    // Initialize protocol
    auto init = client->initializeProtocol().get();

    // Call a tool
    auto args = mcp::make<mcp::Metadata>()
                    .add("a", 10.0)
                    .add("b", 5.0)
                    .build();

    auto result = client->callTool("add", mcp::make_optional(args)).get();
}

Examples

See examples/mcp/README.md for complete working examples:

# Terminal 1: Start server
./build/examples/mcp/mcp_example_server --verbose

# Terminal 2: Run client with demo
./build/examples/mcp/mcp_example_client --demo --verbose

The example server includes:

  • Resource registration and subscriptions
  • Tool execution (calculator, database query, system info)
  • Prompt templates
  • Session management
  • HTTP/SSE endpoints

Installation

Prerequisites

  • C++14 compiler (GCC 8+, Clang 10+, MSVC 2019+)
  • CMake 3.10+
  • libevent 2.1+
  • OpenSSL 1.1+ (optional, for TLS)

Build Options

# Debug build
make debug

# Release build
make release

# Static libraries only
cmake -B build -DBUILD_SHARED_LIBS=OFF

# Without C API
cmake -B build -DBUILD_C_API=OFF

# Custom install prefix
cmake -B build -DCMAKE_INSTALL_PREFIX=~/.local

Windows (Cygwin + MinGW)

Building on Windows requires Cygwin with MinGW-w64 toolchain:

Prerequisites

Install Cygwin with these packages:

  • make, cmake - Build tools
  • mingw64-x86_64-gcc-g++ - MinGW C++ compiler
  • mingw64-x86_64-libevent - Event library
  • mingw64-x86_64-openssl - SSL/TLS library

Build Commands

# From Cygwin bash shell
./build-mingw.sh           # Release build (default)
./build-mingw.sh debug     # Debug build
./build-mingw.sh release   # Release build
./build-mingw.sh clean     # Clean build directory

Output

  • Build directory: build-mingw/
  • Executable: build-mingw/examples/mcp/mcp_example_server.exe

Documentation

MCP C++ Documentation

MCP CPP Core Components

Design Documents

Comparison with Other C++ MCP SDKs

Several C++ implementations of the Model Context Protocol exist. They serve different needs — this table is meant to help you pick the right one:

gopher-mcp (this SDK)hkr04/cpp-mcpNeumann-Labs/mcp-cpp
FocusProduction / enterprise deploymentsLightweight, minimal footprintModern C++20 framework
MCP spec version2025-06-18, 2025-11-25, 2026-07-282025-03-262025-11-25 (in progress)
C++ standardC++14 / 17 / 20C++17C++20
Transportsstdio, HTTP+SSE, HTTPS, Streamable HTTP, WebSocket, TCPstdio, HTTP+SSEstdio, HTTP
Client + serverYesYesYes
TLSYesYes (build flag)
Event modelEvent-driven dispatcher (libevent), thread-safe by design
ResilienceConnection pooling, circuit breaker, rate limiting, backpressure
ObservabilityMetrics, tracing hooks, structured logging
Language bindingsPython, TypeScript, Go, Rust, Java, C#, Ruby via stable C APIC++ onlyC++ only
LicenseApache-2.0MITMIT

If you need a small dependency for a quick stdio tool, a lightweight SDK like cpp-mcp is a fine choice. If you need an MCP C++ SDK for production — long-lived connections, multiple transports, observability, or calling the SDK from other languages — that is what gopher-mcp is built for.

FAQ

What is the Model Context Protocol?

MCP is an open protocol by Anthropic that standardizes how AI models interact with external tools and data. It defines JSON-RPC methods for resources (data), tools (actions), and prompts (templates).

Why use C++ for MCP?

C++ provides maximum performance and portability. This SDK is ideal for embedded systems, real-time applications, game engines, and any environment where Python/Node.js overhead is unacceptable.

Does this work with Claude, GPT, and other AI models?

Yes. MCP is model-agnostic. Any AI system that supports MCP can use servers built with this SDK.

How do I integrate with my Python/Node.js application?

Use the C API bindings. The SDK provides a stable C interface that can be called from any language with FFI support.

Is this production-ready?

Yes. The SDK includes connection pooling, circuit breakers, rate limiting, TLS support, and comprehensive error handling suitable for enterprise deployments.

What transports are supported?

  • stdio - Standard input/output (CLI tools)
  • HTTP+SSE - HTTP with Server-Sent Events (web applications)
  • HTTPS+SSE - Secure HTTP+SSE
  • WebSocket - Bidirectional real-time
  • TCP - Raw TCP sockets

How does this compare to cpp-mcp and other C++ MCP libraries?

See the comparison table. In short: gopher-mcp targets production use — more transports (Streamable HTTP, WebSocket, TCP), connection pooling, circuit breakers, observability, and multi-language bindings — while lighter SDKs optimize for minimal footprint.

How do I contribute?

See CONTRIBUTING.md for guidelines. Issues and pull requests welcome!

Adopters

Using this MCP C++ SDK in your product or project? We'd love to list you here — open a pull request or issue to add yourself.

Keywords & Search Terms

MCP C++, MCP CPP, Model Context Protocol C++, MCP SDK, C++ MCP, CPP MCP, Model Context Protocol CPP, MCP implementation, AI model integration C++, LLM integration C++, MCP server C++, MCP client C++, Model Context Protocol SDK, C++ AI SDK, Enterprise MCP, Production MCP C++

Contributing

Contributions are welcome! Please read our contributing guidelines before submitting pull requests.

License

Apache License 2.0 - see LICENSE for details.

Related Projects

Files in the repo

Repository payload28 top-level entries
  • .github
  • bindings
  • cmake
  • docker-mcp
  • docs
  • examples
  • include
  • scripts
  • sdk
  • shell
  • src
  • tests
  • .clang-format
  • .dockerignore
  • .gitignore
  • .nvmrc
  • build-mingw.sh
  • build.sh
  • CHANGELOG.md
  • client_test.exp
  • CMakeLists.txt
  • CONTRIBUTING.md
  • dump-version.sh
  • LICENSE
  • Makefile
  • README.md
  • test_mcp_client.py
  • vcpkg.json

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More frameworks & sdks

HKUDS/nanobotFrameworks & SDKs

Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps

48k
microsoft/
SkillOpt
microsoft/SkillOptFrameworks & SDKs

SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.

17k
omnigent-ai/omnigentFrameworks & SDKs

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.

9.8k
kyegomez/
OpenMythos
kyegomez/OpenMythosFrameworks & SDKs

A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.

15k
D4Vinci/ScraplingFrameworks & SDKs

🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!

80k