** AI 코딩 조수가 모두 앞을 적재하지 않고 외부 도구의 수십 가지를 사용할 수있는 게이트웨이. **

PMCP는 조수 (Claude Code, Codex 및 기타)과 서비스 사이에 앉습니다. - GitHub, Jira, Databases, 90+ more. 모든 도구의 전체 스키마를로드하는 대신 당신은 질문을하기 전에, 그것은 짧은 메뉴를 먼저 제공하고 도구가 실제로 사용될 때만 상세한 스키마를 태울.

왜 존재

Assistants는 ** MCP** (Model Context Protocol)을 통해 외부 서비스에 도달합니다. AI의 일반적인 인터페이스는 다른 소프트웨어와 대화합니다. 조수가 직접 수십 MCP 서버에 연결되면 도구 정의의 all를 한 번에 한 번에 로드합니다.

Context는 제한 및 미터화됩니다. 모든 도구 정의 비용 토큰과 실제 작업을위한 방을 혼잡합니다. 50 + 도구를로드하면 전화가 느리고 비싸지 않을 수 있으며, 새 서비스가 보통 재시작을 의미합니다. Anthropic은 MCP 툴링의 핵심 과제로 컨텍스트블로트를 강조했습니다.

PMCP는 이 콤팩트하고 주문한 단일 연결점입니다.

누구를 위해

PMCP - Progressive MCP

A gateway that lets your AI coding assistant use dozens of external tools without loading them all up front.

PMCP sits between your assistant (Claude Code, Codex, and others) and the services it can plug into — GitHub, Jira, databases, 90+ more. Instead of loading every tool’s full schema before you’ve asked a question, it offers a short menu first and fetches the detailed schema only when a tool is actually used.

Why it exists

Assistants reach external services through MCP (Model Context Protocol) — a common interface for an AI to talk to other software. When an assistant connects to a dozen MCP servers directly, it loads all of their tool definitions into context at once.

Context is limited and metered: every tool definition costs tokens and crowds out room for the actual work. Loading 50+ tools you may never call is slow and expensive, and adding a new service usually means restarting the assistant. Anthropic has highlighted context bloat as a key challenge with MCP tooling.

PMCP is the single connection point that keeps this compact and on-demand.

Who it’s for

Developers and teams running AI coding assistants with many connected tools — especially anyone hitting “too many tools” or context-full limits.

What you get

• Lower token cost — the assistant sees a compact capability card, not 50+ full schemas, before doing real work.
• Load tools only when needed — downstream servers stay dormant until first use (“lazy by default”), and eager-start only when listed in autoStart.
• Add tools without restarting — provision a new server on demand from a manifest of 90+.
• One stable connection — your assistant sees ~26 steady meta-tools instead of a shifting set of many.
• Guardrails built in — output size caps and optional secret redaction.
• Works out of the box — core capability matching needs no API key.

Quick Start

Installation

# With uv (recommended)
uv pip install pmcp

# Or run directly without installing
uvx pmcp

# With pip
pip install pmcp

Upgrading from 2.x

3.0.0 refuses several things 2.7.3 accepted. Most importantly, a repository’s .mcp.json, .pmcp/manifest.yaml and .mcp-gateway-policy.yaml are ignored until you approve them with pmcp trust approve . MIGRATING.md has an upgrade checklist, a section for each breaking change (with a check, the fix and how to verify it), and how to roll back. To stay on 2.x for now, pin pmcp<3.

Capability matching is built-in — no API key needed. gateway.request_capability uses a pure-Python matcher that can return direct CLI guidance for installed