# Mcpc > Build agentic-MCP servers by composing existing MCP tools. - **Type:** MCP server - **Install:** `agentstack add mcp-mcpc-tech-mcpc` - **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior - **Seller:** [mcpc-tech](https://agentstack.voostack.com/s/mcpc-tech) - **Installs:** 0 - **Category:** [Integrations](https://agentstack.voostack.com/c/integrations) - **Latest version:** 0.1.0 - **License:** MIT - **Upstream author:** [mcpc-tech](https://github.com/mcpc-tech) - **Source:** https://github.com/mcpc-tech/mcpc - **Website:** https://mcpc.tech ## Install ```sh agentstack add mcp-mcpc-tech-mcpc ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About # MCPC [](https://jsr.io/@mcpc/core) [](https://www.npmjs.com/package/@mcpc-tech/core) **Build agentic MCP servers by composing existing MCP tools.** MCPC is the SDK for building agentic MCP (Model Context Protocol) Servers. You can use it to: 1. **Create Powerful Agentic MCP Tools:** Simply describe your vision in text and reference tools from the [expanding MCP community](https://registry.modelcontextprotocol.io/docs#/operations/list-servers). As standard MCP tools, your agents work everywhere and collaborate seamlessly. 2. **Fine-Tune Existing Tools:** Flexibly modify existing tool descriptions and parameters, or wrap and filter results to precisely adapt them to your specific business scenarios. 3. **Build Multi-Agent Systems:** By defining each agent as a MCP tool, you can compose and orchestrate them to construct sophisticated, collaborative multi-agent systems. ## Key Features - **Portability and agent interoperability**: Build once, run everywhere as MCP tools - agents work across all MCP clients and can discover and collaborate with each other through standard MCP interfaces - **Simple composition and fine-tuning**: Compose MCP servers as building blocks, select and customize tools, or modify their descriptions and parameters - **Logging and tracing**: Built-in MCP logging and OpenTelemetry tracing support - **Skills support**: Define domain-specific knowledge following the [Agent Skills specification](https://agentskills.io) - deploy to production, share via MCP, and declare tool dependencies - **Flexible execution modes**: Multiple specialized modes to fit different scenarios - interactive agent (`agentic`), AI SDK sampling (`ai_sampling`), AI ACP mode (`ai_acp`), secure code execution ([`code_execution`](packages/plugin-code-execution/)), and sandbox + sampling ([`code_execution_sampling`](packages/plugin-code-execution-sampling/)) - each with dedicated implementations ## Quick Start ### Three Ways to Get Started #### 1. Use the Website (Fastest) Visit **[mcpc.tech](https://mcpc.tech)** to browse servers from the official MCP registry, discover tools, and generate ready-to-use agents. #### 2. Use the Agent (Interactive) Let AI help you discover servers and build agents: **Add to your MCP client:** ```json { "mcpServers": { "mcpc-builder-agent": { "command": "npx", "args": ["-y", "@mcpc-tech/builder", "mcpc-builder-agent"] } } } ``` #### 3. Write Code (Full Control) Use the SDK directly for complete customization. See examples below. --- ### Installation ```bash # npm (from npm registry) npm install @mcpc-tech/core # npm (from jsr) npx jsr add @mcpc/core # deno deno add jsr:@mcpc/core # pnpm (from npm registry) pnpm add @mcpc-tech/core # pnpm (from jsr) pnpm add jsr:@mcpc/core ``` Or run directly with the CLI (no installation required): ```bash # Run with remote configuration npx -y @mcpc-tech/cli --config-url \ "https://raw.githubusercontent.com/mcpc-tech/mcpc/main/packages/cli/examples/configs/codex-fork.json" ``` ### Examples: Create a Simple Codex/Claude Code Fork ```typescript import { mcpc } from "@mcpc/core"; const server = await mcpc( [{ name: "coding-agent", version: "0.1.0" }, { capabilities: { tools: {} } }], [{ name: "coding-agent", description: ` You are a coding assistant with advanced capabilities. Your capabilities include: - Reading and writing files - Executing terminal commands to build, test, and run projects - Interacting with GitHub to create pull requests and manage issues Available tools: `, deps: { mcpServers: { "desktop-commander": { command: "npx", args: ["-y", "@wonderwhy-er/desktop-commander@latest"], transportType: "stdio", }, github: { transportType: "streamable-http", url: "https://api.githubcopilot.com/mcp/", }, }, }, }], ); ``` > **Complete Example**: See the full > [Codex fork tutorial](docs/examples/creating-a-codex-fork.md). ### Install the MCPC Core Skill Install the `mcpc-core` skill into your project using [skills.sh](https://skills.sh): ```bash npx skills add mcpc-tech/mcpc ``` This installs the skill into `.agents/skills/mcpc-core/`, giving your agent on-demand access to the full `@mcpc/core` API reference, usage patterns, plugin guide, and gotchas. --- ### Examples: Load Agent Skills For complex agents where inline `description` becomes unwieldy, use [Agent Skills](https://agentskills.io) to organize domain knowledge in separate files that are loaded on-demand. ```typescript import { createBashPlugin, createSkillsPlugin } from "@mcpc/core/plugins"; const server = await mcpc( [{ name: "my-agent", version: "1.0.0" }, { capabilities: { tools: {} } }], [{ name: "my-agent", description: 'An agent with domain knowledge\n\n', plugins: [ createSkillsPlugin({ paths: ["./skills"] }), createBashPlugin(), ], }], ); ``` Skills load domain knowledge on-demand, while bash plugin enables script execution. For scripts in `scripts/` directory, skills returns the path - use bash tool to execute. > **Complete Examples**: See > [14-skills-plugin.ts](packages/core/examples/14-skills-plugin.ts) and > [25-skills-with-bash.ts](packages/core/examples/25-skills-with-bash.ts). ### Examples: Progressive Manual Disclosure For agents with detailed instructions, use the `manual` field to reduce initial prompt length - the full manual is fetched on-demand via `man { manual: true }`: ```typescript const server = await mcpc( [{ name: "code-reviewer", version: "1.0.0" }, { capabilities: { tools: {} }, }], [{ name: "code-reviewer", description: "AI code reviewer for quality and security analysis.", manual: `Detailed review guidelines... ## Review Categories 1. Code Quality - readability, naming, complexity 2. Security - SQL injection, XSS, credentials ...`, deps: { mcpServers: { "desktop-commander": { command: "npx", args: ["-y", "@wonderwhy-er/desktop-commander@0.1.20"], transportType: "stdio", }, }, }, }], ); ``` > **Complete Example**: See > [21-progressive-manual.ts](packages/core/examples/21-progressive-manual.ts). ## How It Works Three simple steps: 1. **Define dependencies** - List the MCP servers you want to use 2. **Write agent description** - Describe what your agent does and reference tools 3. **Create server** - Use `mcpc()` to build and connect your server ## Execution Modes MCPC provides multiple flexible execution modes to fit different scenarios: | Mode | Description | Use Case | Requires Plugin | | ------------------------- | --------------------------------------------- | ---------------------------------------------------- | --------------- | | `agentic` | Interactive step-by-step execution | Standard agent interactions | Built-in | | `ai_sampling` | AI SDK sampling mode | Autonomous AI SDK execution | Built-in | | `ai_acp` | AI SDK ACP mode | Coding agents (Claude Code, etc.) | Built-in | | `code_execution` | Secure JavaScript sandbox with tool access | Code generation and execution | External | | `code_execution_sampling` | Secure sandbox plus MCP sampling-backed calls | Sandbox execution that can also ask the client model | External | > **Note:** `agentic`, `ai_sampling`, and `ai_acp` are built-in modes — just set > `options.mode` and they work. `code_execution` and `code_execution_sampling` > require installing and loading their respective plugin packages. ### Quick Example ```typescript // Interactive agent (default) { options: { mode: "agentic" } } // Autonomous agent { options: { mode: "ai_sampling", samplingConfig: { maxIterations: 10 } } } // Code execution with sandbox import { createCodeExecutionPlugin } from "@mcpc/plugin-code-execution/plugin"; { plugins: [createCodeExecutionPlugin()], options: { mode: "code_execution" } } ``` > **Detailed Documentation**: See > [Execution Modes Guide](docs/execution-modes.md) for comprehensive information > on each mode, configuration options, and best practices. ## Documentation - **[Getting Started](docs/quickstart/installation.md)** - Installation and first steps - **[Creating Your First Agent](docs/quickstart/create-your-first-agentic-mcp.md)** - Complete tutorial - **[Execution Modes](docs/execution-modes.md)** - Comprehensive guide to all execution modes - **[CLI Usage Guide](docs/quickstart/cli-usage.md)** - Using the MCPC CLI - **[Logging and Tracing](docs/logging-and-tracing.md)** - MCP logging and OpenTelemetry tracing - **[Examples](docs/examples/)** - Real-world use cases - **[FAQ](docs/faq.md)** - Common questions and answer ## Examples See working examples in the [examples directory](packages/core/examples/) or check out the [Codex fork tutorial](docs/examples/creating-a-codex-fork.md). ## Contributing We welcome contributions! See [CONTRIBUTING.md](CONTRIBUTING.md) for details. ## License MIT License - see [LICENSE](LICENSE) for details. ## Source & license This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code. - **Author:** [mcpc-tech](https://github.com/mcpc-tech) - **Source:** [mcpc-tech/mcpc](https://github.com/mcpc-tech/mcpc) - **License:** MIT - **Homepage:** https://mcpc.tech Install and usage instructions live in the source repository linked above. ## Pricing - **Free** — Free ## Security capabilities Automated source analysis of v0.1.0 — what this tool can access: - **Network access:** no - **Filesystem access:** no - **Shell / process execution:** no - **Environment & secrets:** no - **Dynamic code execution:** no *"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** — security scan: passed — Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/mcp-mcpc-tech-mcpc - Seller: https://agentstack.voostack.com/s/mcpc-tech - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.