C
Consiliency/pmcp
Gateway that reveals MCP tools gradually, to save context
在 GitHub 查看 ↗链接已于 2026-11-12 核查 · HTTP 200 · 打开的是厂商自己的官网
安装与配置
- 复制上面的命令
- 粘成
claude_desktop_config.json里mcpServers的一项（本地服务器用 command + args，示例见 客户端接法） - 重启客户端
客户端配置（取自该仓库的安装命令）
{
"mcpServers": {
"consiliency-pmcp": {
"command": "uvx",
"args": ["pmcp"]
}
}
}解析自我们于 2026-11-04 抓取的该仓库 README；我们未执行过。
command/args 来自仓库写明的安装命令；不确定时请以该项目 README 为准。
VS Code（.vscode/mcp.json —— 键名是 servers）
{
"servers": {
"consiliency-pmcp": {
"command": "uvx",
"args": ["pmcp"]
}
}
}VS Code 顶层键是 <code>servers</code>，其余与上面那份相同。
Claude Code（命令行）
claude mcp add --transport stdio consiliency-pmcp -- uvx pmcp
Claude Code 不收 JSON 文件，用这条命令直接加。
配置项的键名以你的客户端为准：客户端与 CLI
- 来源明细
- 收录自 abordage/awesome-mcp 榜单（我们从中收集的条目之一） · 条目类型：MCP 服务
- 收录与活跃
- 收录于 2026-11-05 · 最近见到 2026-11-14 · 共见到 10 次 · 被 10 个来源列出
- 评分构成
- 综合分 1,003 · 10 个来源 · mcp
- 安装
uvx pmcp
常见问题（答案都来自我们的记录）
怎么安装？
该仓库给出的安装命令是
uvx pmcp。我们的记录里它是仓库自己提供的；不保证在你的客户端上直接可用。它适合谁 / 用来做什么？
我们把它归在这些标签下: MCP 服务。标签来自条目自身，不是我们强加的分类。
谁维护它、还在更新吗？
我们收录于 2026-11-05；最近见到 2026-11-14。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。
# PMCP - Progressive MCP
以下摘录自该仓库的 README（片段） · 在 GitHub 读完整 README →
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
bash
# 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 Capability matching is built-in — no API key needed. gateway.requestcapability
> uses a pure-Python matcher that can return direct CLI guidance for installed
> native tools, MCP server candidates, or registry search guidance.
### Configure with pmcp setup
PMCP includes a wizard-style helper that can render ready-to-use MCP client config for Claude and OpenCode.
The generated config only connects your client to the PMCP gateway. Downstream MCP
servers stay lazy until first use unless you add them to autoStart in your
.mcp.json.
Use pmcp setup to print the generated config:
bash
pmcp setup --client claude --mode stdio # Claude local stdio
pmcp setup --client claude --mode http # Claude shared-service HTTP
pmcp setup --client opencode --mode stdio # OpenCode local stdio
pmcp setup --client opencode --mode http # OpenCode shared-service HTTP
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
bash
# 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 Capability matching is built-in — no API key needed. gateway.requestcapability
> uses a pure-Python matcher that can return direct CLI guidance for installed
> native tools, MCP server candidates, or registry search guidance.
### Configure with pmcp setup
PMCP includes a wizard-style helper that can render ready-to-use MCP client config for Claude and OpenCode.
The generated config only connects your client to the PMCP gateway. Downstream MCP
servers stay lazy until first use unless you add them to autoStart in your
.mcp.json.
Use pmcp setup to print the generated config:
bash
pmcp setup --client claude --mode stdio # Claude local stdio
pmcp setup --client claude --mode http # Claude shared-service HTTP
pmcp setup --client opencode --mode stdio # OpenCode local stdio
pmcp setup --client opencode --mode http # OpenCode shared-service HTTP
收录徽章（可选）
想把收录标记放进 README 就复制这行，可选，不影响收录。
[](https://anclum.com/zh/s/consiliency-pmcp/)
- 来源
- awesome · https://github.com/Consiliency/pmcp
- 按领域浏览
- MCP 服务
- 收录来源
- 10 个独立来源
- 收录于
- 今天
同类推荐
所属领域与标签
每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。