Ambient Code MCP

MCP开发工具

提供方 ambient-code

开发工具 stdio · 本地进程 Token 社区 / 第三方 Claude DesktopClaude
查看接入方式

MCP ACP服务器是一个用于通过公共API网关管理Ambient Code Platform(ACP)会话的模型上下文协议服务器,提供会话管理、监控、标签操作和集群管理等功能。

一句话选型结论

按资料字段整理

Ambient Code MCP 属于开发工具类 MCP 服务器,stdio · 本地进程,Token,可直接接入 Claude Desktop、Claude,有可直接执行的安装命令。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类开发工具 传输方式stdio · 本地进程 鉴权Token 部署方式本地部署
GitHub 星标 0 仓库热度,无公开仓库时显示未标注
工具数 26 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

开发工具
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量26暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

支持客户端

适用场景

会话管理Python本地部署监控工具标签系统集群管理开发工具

安装与配置

stdio · 本地进程 Token
客户端在本机拉起子进程,数据不出本机
pip install . # installs the 'mcp-acp' command

这条命令只是入口,具体启动参数请按官方文档补齐,不要直接照搬到别的服务器。

  1. 1
    准备运行环境

    stdio 服务在本地起进程,需要先装好 Node.js 等运行时,再按安装命令拉取依赖。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后客户端会列出约 26 个工具,随便调一个只读工具确认能返回结果。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
代码与仓库操作

在对话里直接查代码、提 issue、走 PR,省掉来回切工具。

本地命令与脚本

把构建、测试、格式化这类重复命令交给模型执行。

接口联调与测试

让模型调你的接口、跑一遍用例,快速定位问题。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 资料标注 26 个工具,覆盖面较广,能满足多种调用。
  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 已适配 Claude Desktop、Claude,换客户端不用重新研究配置。

先想清楚的地方

  • stdio 方式要求本地装好运行时(如 Node.js),换机器要重新装一遍。
  • 使用前要准备好Token对应的凭据,并按最小权限配置。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在开发工具场景里让模型直接调用外部能力的人。
  • 已经在用 Claude Desktop、Claude 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 完全不想在本地装环境的人。
  • 不方便管理密钥或第三方授权的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Ambient Code MCP当前 26 stdio · 本地进程 本地部署 有 2026-05-17
Git 838e2ec1 12 stdio · 本地进程 本地部署 有 2026-05-17
Markitdown MCP 2c653a5f 1 stdio · 本地进程 本地部署 有 2026-05-17
JavaGuide 未标注 stdio · 本地进程 本地部署 有 2026-04-11
awesome-claude-skills 未标注 stdio · 本地进程 本地部署 有 2026-04-26
Context7 831acf40 未标注 stdio · 本地进程 本地部署 有 2026-05-17

服务器档案

开发工具
字段来自项目仓库与公开索引,中文说明由本站标注
提供方ambient-code上游标注的维护方 ambient-code
分类开发工具本站按上游分类展示
连接方式stdio · 本地进程客户端在本机拉起子进程,数据不出本机
鉴权方式Token远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · 未标注本地安装时用到的包标识与运行时
部署类型本地部署上游给出的部署形态
最近核验2026-05-17上游最后核验时间

详细介绍

14.8 KB
来自项目仓库与上游目录的原文,未做删改

MCP ACP Server

A Model Context Protocol (MCP) server for managing Ambient Code Platform (ACP) sessions via the public-api gateway.


Table of Contents

  • Quick Start
  • Features
  • Installation
  • Configuration
  • Usage
  • Tool Reference
  • Troubleshooting
  • Architecture
  • Security
  • Development
  • Roadmap
  • Contributing
  • Status

Quick Start```bash

Install

git clone https://github.com/ambient-code/mcp
cd mcp
pip install . # installs the 'mcp-acp' command

Configure

mkdir -p ~/.config/acp
cat > ~/.config/acp/clusters.yaml <<EOF
clusters:
my-cluster:
server: https://public-api-ambient.apps.your-cluster.example.com
token: your-bearer-token-here
default_project: my-workspace
default_cluster: my-cluster
EOF
chmod 600 ~/.config/acp/clusters.yaml


Then add to your MCP client (Claude Desktop, Claude Code, or uvx) and try:```
List my ACP sessions

Features

Session Management

Tool Description
acp_list_sessions List/filter sessions by status, age, with sorting and limits
acp_get_session Get detailed session information by ID
acp_create_session Create sessions with custom prompts, repos, model selection, and timeout
acp_create_session_from_template Create sessions from predefined templates (triage/bugfix/feature/exploration)
acp_delete_session Delete sessions with dry-run preview
acp_restart_session Restart a stopped session
acp_clone_session Clone an existing session's configuration into a new session
acp_update_session Update session metadata (display name, timeout)

Observability

Tool Description
acp_get_session_logs Retrieve container logs for a session
acp_get_session_transcript Retrieve conversation history (JSON or Markdown)
acp_get_session_metrics Get usage statistics (tokens, duration, tool calls)

Labels

Tool Description
acp_label_resource Add labels to a session for organizing and filtering
acp_unlabel_resource Remove labels from a session by key
acp_list_sessions_by_label List sessions matching label selectors
acp_bulk_label_resources Add labels to multiple sessions (max 3)
acp_bulk_unlabel_resources Remove labels from multiple sessions (max 3)

Bulk Operations

Tool Description
acp_bulk_delete_sessions Delete multiple sessions (max 3) with confirmation and dry-run
acp_bulk_stop_sessions Stop multiple running sessions (max 3)
acp_bulk_restart_sessions Restart multiple stopped sessions (max 3)
acp_bulk_delete_sessions_by_label Delete sessions matching label selectors (max 3 matches)
acp_bulk_stop_sessions_by_label Stop sessions matching label selectors (max 3 matches)
acp_bulk_restart_sessions_by_label Restart sessions matching label selectors (max 3 matches)

Cluster Management

Tool Description
acp_list_clusters List configured cluster aliases
acp_whoami Check current configuration and authentication status
acp_switch_cluster Switch between configured clusters
acp_login Authenticate to a cluster with a Bearer token

Safety Features:

  • Dry-Run Mode — All mutating operations support dry_run for safe preview before executing
  • Bulk Operation Limits — Maximum 3 items per bulk operation with confirmation requirement
  • Label Validation — Labels must be 1-63 alphanumeric characters, dashes, dots, or underscores

Installation

From Source (end users)```bash

git clone https://github.com/ambient-code/mcp
cd mcp
pip install . # installs the 'mcp-acp' command


### From Wheel

Requires `make` to be installed.```bash
# &quot;make install&quot; sets up the dev environment (.venv + dependencies),
# which &quot;make build&quot; then uses to produce the wheel in dist/
make install
make build
pip install dist/mcp_acp-*.whl

Development Install (contributors)```bash

git clone https://github.com/ambient-code/mcp
cd mcp
uv venv
uv pip install -e ".[dev]"


### Virtual Environment Install

On some Linux distributions (Debian, Ubuntu, Fedora 38+), PEP 668
prevents `pip install` into the system Python. If you get an &quot;externally-managed-environment&quot; error,
install into a virtual environment instead:```bash
git clone https://github.com/ambient-code/mcp
cd mcp
python3 -m venv .venv
source .venv/bin/activate
pip install .

Note that the mcp-acp command will only be available inside the venv. To use it
from an MCP client like Claude Code, reference the full path:```bash
claude mcp add mcp-acp -t stdio /full/path/to/mcp/.venv/bin/mcp-acp


**Requirements:**

- Python 3.12+
- Bearer token for the ACP public-api gateway
- Access to an ACP cluster

---

## Configuration

### Cluster Config

Create `~/.config/acp/clusters.yaml`:```yaml
clusters:
  vteam-stage:
    server: https://public-api-ambient.apps.vteam-stage.example.com
    token: your-bearer-token-here
    description: &quot;V-Team Staging Environment&quot;
    default_project: my-workspace

  vteam-prod:
    server: https://public-api-ambient.apps.vteam-prod.example.com
    token: your-bearer-token-here
    description: &quot;V-Team Production&quot;
    default_project: my-workspace

default_cluster: vteam-stage

Then secure the file:```bash
chmod 600 ~/.config/acp/clusters.yaml


### Authentication

Add your Bearer token to each cluster entry under the `token` field, or set the `ACP_TOKEN` environment variable:```bash
export ACP_TOKEN=your-bearer-token-here

Get your token from the ACP platform administrator or the gateway's authentication endpoint.

Claude Desktop

Edit your configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Linux: ~/.config/claude/claude_desktop_config.json
  • Windows: `%APPDATA%\Claude\claude_desktop_config.json````json
    {
    "mcpServers": {
    "acp": {
    "command": "mcp-acp",
    "args": [],
    "env": {
    "ACP_CLUSTER_CONFIG": "${HOME}/.config/acp/clusters.yaml"
    }
    }
    }
    }

After editing, **completely quit and restart Claude Desktop** (not just close the window).

### Claude Code (CLI)```bash
claude mcp add mcp-acp -t stdio mcp-acp

Using uvx

uvx provides zero-install execution — no global Python pollution, auto-caching, and fast startup.```bash

Install uv (if needed)

curl -LsSf https://astral.sh/uv/install.sh | sh


Claude Desktop config for uvx:```json
{
  &quot;mcpServers&quot;: {
    &quot;acp&quot;: {
      &quot;command&quot;: &quot;uvx&quot;,
      &quot;args&quot;: [&quot;mcp-acp&quot;]
    }
  }
}

For a local wheel (before PyPI publish):```json
{
"mcpServers": {
"acp": {
"command": "uvx",
"args": ["--from", "/full/path/to/dist/mcp_acp-0.3.0-py3-none-any.whl", "mcp-acp"]
}
}
}


---

## Usage

### Examples```
# List sessions
List my ACP sessions
Show running sessions in my-workspace
List sessions older than 7 days in my-workspace
List sessions sorted by creation date, limit 20

# Session details
Get details for ACP session session-name
Show AgenticSession session-name in my-workspace

# Create a session
Create a new ACP session with prompt &quot;Run all unit tests and report results&quot;

# Create from template
Create an ACP session from the bugfix template called &quot;fix-auth-issue&quot;

# Restart / clone
Restart ACP session my-stopped-session
Clone ACP session my-session as &quot;my-session-v2&quot;

# Update session metadata
Update ACP session my-session display name to &quot;Production Test Runner&quot;

# Observability
Show logs for ACP session my-session
Get transcript for ACP session my-session in markdown format
Show metrics for ACP session my-session

# Labels
Label ACP session my-session with env=staging and team=platform
Remove label env from ACP session my-session
List ACP sessions with label team=platform

# Delete with dry-run (safe!)
Delete test-session from my-workspace in dry-run mode

# Actually delete
Delete test-session from my-workspace

# Bulk operations (dry-run first)
Delete these sessions: session-1, session-2, session-3 from my-workspace (dry-run first)
Stop all sessions with label env=test
Restart sessions with label team=platform

# Cluster operations
Check my ACP authentication
List my ACP clusters
Switch to ACP cluster vteam-prod
Login to ACP cluster vteam-stage with token

Trigger Keywords

Include one of these keywords so your MCP client routes the request to ACP: ACP, ambient, AgenticSession, or use tool names directly (e.g., acp_list_sessions, acp_whoami). Without a keyword, generic phrases like "list sessions" may not trigger the server.

Quick Reference

Task Command Pattern
Check auth Use acp_whoami
List all List ACP sessions in PROJECT
Filter status List running sessions in PROJECT
Filter age List sessions older than 7d in PROJECT
Get details Get details for ACP session SESSION
Create Create ACP session with prompt &quot;...&quot;
Create from template Create ACP session from bugfix template
Restart Restart ACP session SESSION
Clone Clone ACP session SESSION as &quot;new-name&quot;
Update Update ACP session SESSION timeout to 1800
View logs Show logs for ACP session SESSION
View transcript Get transcript for ACP session SESSION
View metrics Show metrics for ACP session SESSION
Add labels Label ACP session SESSION with env=test
Remove labels Remove label env from ACP session SESSION
Filter by label List ACP sessions with label team=platform
Delete (dry) Delete SESSION in PROJECT (dry-run)
Delete (real) Delete SESSION in PROJECT
Bulk delete Delete session-1, session-2 in PROJECT
Bulk by label Stop sessions with label env=test
List clusters Use acp_list_clusters
Login Login to ACP cluster CLUSTER

Tool Reference

For complete API specifications including input schemas, output formats, and behavior details, see API_REFERENCE.md.

Category Tool Description
Session acp_list_sessions List/filter sessions
acp_get_session Get session details
acp_create_session Create session with prompt
acp_create_session_from_template Create from template
acp_delete_session Delete with dry-run support
acp_restart_session Restart stopped session
acp_clone_session Clone session configuration
acp_update_session Update display name or timeout
Observability acp_get_session_logs Retrieve container logs
acp_get_session_transcript Get conversation history
acp_get_session_metrics Get usage statistics
Labels acp_label_resource Add labels to session
acp_unlabel_resource Remove labels by key
acp_list_sessions_by_label Filter sessions by labels
acp_bulk_label_resources Bulk add labels (max 3)
acp_bulk_unlabel_resources Bulk remove labels (max 3)
Bulk acp_bulk_delete_sessions Delete multiple sessions (max 3)
acp_bulk_stop_sessions Stop multiple sessions (max 3)
acp_bulk_restart_sessions Restart multiple sessions (max 3)
acp_bulk_delete_sessions_by_label Delete by label (max 3)
acp_bulk_stop_sessions_by_label Stop by label (max 3)
acp_bulk_restart_sessions_by_label Restart by label (max 3)
Cluster acp_list_clusters List configured clusters
acp_whoami Check authentication status
acp_switch_cluster Switch cluster context
acp_login Authenticate with Bearer token

Troubleshooting

"No authentication token available"

Your token is not configured. Either:

  1. Add token: your-token-here to your cluster in ~/.config/acp/clusters.yaml
  2. Set the ACP_TOKEN environment variable

"HTTP 401: Unauthorized"

Your token is expired or invalid. Get a new token from the ACP platform administrator.

"HTTP 403: Forbidden"

You don't have permission for this operation. Contact your ACP platform administrator.

"Direct Kubernetes API URLs (port 6443) are not supported"

You're using a direct K8s API URL. Use the public-api gateway URL instead:

  • Wrong: https://api.cluster.example.com:6443
  • Correct: https://public-api-ambient.apps.cluster.example.com

"mcp-acp: command not found"

Add Python user bin to PATH:

  • macOS: export PATH=&quot;$HOME/Library/Python/3.*/bin:$PATH&quot;
  • Linux: export PATH=&quot;$HOME/.local/bin:$PATH&quot;

Then restart your shell.

MCP Tools Not Showing in Claude

  1. Check Claude Desktop logs: Help → View Logs
  2. Verify config file syntax is valid JSON
  3. Make sure mcp-acp is in PATH
  4. Restart Claude Desktop completely (quit, not just close)

"Permission denied" on clusters.yaml```bash

chmod 600 ~/.config/acp/clusters.yaml
chmod 700 ~/.config/acp


---

## Architecture

- **MCP SDK** — Standard MCP protocol implementation (stdio transport)
- **httpx** — Async HTTP REST client for the public-api gateway
- **Pydantic** — Settings management and input validation
- **Three-layer design** — Server (tool dispatch) → Client (HTTP + validation) → Formatters (output)

See CLAUDE.md for complete system design.

---

## Security

- **Input Validation** — DNS-1123 format validation for all resource names
- **Gateway URL Enforcement** — Direct K8s API URLs (port 6443) rejected
- **Bearer Token Security** — Tokens filtered from logs, sourced from config or environment
- **Resource Limits** — Bulk operations limited to 3 items with confirmation

See SECURITY.md for complete security documentation including threat model and best practices.

---

## Development```bash
# One-time setup
uv venv &amp;&amp; uv pip install -e &quot;.[dev]&quot;

# Pre-commit workflow
uv run ruff format . &amp;&amp; uv run ruff check . &amp;&amp; uv run pytest tests/

# Run with coverage
uv run pytest tests/ --cov=src/mcp_acp --cov-report=html

# Build wheel
uvx --from build pyproject-build --installer uv

See CLAUDE.md for contributing guidelines.


Roadmap

Current implementation provides 26 tools. 3 tools remain planned:

  • Session export (issue #28)
  • Workflow management (issue #29)

Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Add tests for new functionality
  4. Ensure all tests pass (uv run pytest tests/)
  5. Ensure code quality checks pass (uv run ruff format . &amp;&amp; uv run ruff check .)
  6. Submit a pull request

Status

Code: Production-Ready |
Tests: All Passing |
Security: Input validation, gateway enforcement, token security |
Tools: 26 implemented (3 more planned)


Documentation

  • API_REFERENCE.md — Full API specifications for all 26 tools
  • SECURITY.md — Security features, threat model, and best practices
  • CLAUDE.md — System architecture and development guide

License

MIT License — See LICENSE file for details.

Support

For issues and feature requests, use the GitHub issue tracker.

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
Ambient Code MCP 怎么安装?

在客户端按下面的安装命令接入:pip install . # installs the 'mcp-acp' command。装完在客户端配置里引用同一个包或端点。

Ambient Code MCP 怎么在 Claude Desktop、Claude 里配置?

它的传输方式是stdio · 本地进程,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

Ambient Code MCP 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Ambient Code MCP 需要 API Key 吗?

资料标注需要Token认证,使用前准备好对应凭据,并按最小权限配置。

Ambient Code MCP 支持哪些客户端?

资料标注支持 Claude Desktop、Claude;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

Ambient Code MCP 能提供哪些能力?

资料显示约 26 个工具;能力标签包括 会话管理、Python、Claude、集群管理。具体工具清单以官方文档为准。

Ambient Code MCP 需要什么运行环境?

属于本地进程,需要在本机装好运行环境。

Ambient Code MCP 是本地还是远程?

它是本地进程(stdio),由客户端在本机拉起。传输方式为stdio · 本地进程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 2026-05-17。