Skill Management MCP Server

MCPAI代理

提供方 fkesheh

AI代理 stdio · 本地进程 API Key 社区 / 第三方 Claude DesktopClaudeCursor
查看接入方式

一个基于Model Context Protocol (MCP)的服务器,用于程序化创建、编辑、运行和管理技能脚本,支持多技能统一执行和环境变量管理。

一句话选型结论

按资料字段整理

Skill Management MCP Server 属于AI代理类 MCP 服务器,stdio · 本地进程,API Key,可直接接入 Claude Desktop、Claude、Cursor,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AI代理 传输方式stdio · 本地进程 鉴权API Key 部署方式本地部署
GitHub 星标 26 仓库热度,无公开仓库时显示未标注
工具数 9 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

AI代理
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9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

技能管理Python本地部署代码执行环境管理多技能组合MCP协议

安装与配置

stdio · 本地进程 API Key
客户端在本机拉起子进程,数据不出本机
uv run python script.py # Run Python with project environment

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 Python,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 9 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
给代理接外部能力

让代理在任务中途调用搜索、数据库等真实工具。

多步任务编排

把一串操作拆成步骤,由代理按顺序执行。

自动化重复流程

把固定流程交给代理跑,减少手工操作。

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 9 个工具,职责相对集中,接入后不容易误操作。
  • 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、Cursor,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API Key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AI代理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
Skill Management MCP Server当前 9 stdio · 本地进程 本地部署 有 2026-05-17
Filesystem 560c4363 13 未标注 本地部署 无 2026-05-17
Server Everything (everything) 11 stdio · 本地进程 本地部署 有 2026-05-17
Time 7365cb6d 2 SSE · 服务端推送 远程部署 有 2026-05-18
Everything Claude Code 未标注 stdio · 本地进程 本地部署 有 2026-05-17
Openmemory 557e1585 未标注 stdio · 本地进程 本地部署 有 2026-05-17

服务器档案

AI代理
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fkesheh上游标注的维护方 fkesheh
分类AI代理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API Key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 · Python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

36.1 KB
来自项目仓库与上游目录的原文,未做删改

Skill Management MCP Server

A Model Context Protocol (MCP) server that enables Claude to manage skills stored in ~/.skill-mcp/skills. This system allows Claude to create, edit, run, and manage skills programmatically, including execution of skill scripts with environment variables.

Quick Status

Status: ✅ Production Ready
Test Coverage: 86% (145/145 tests passing)
Deployed: October 18, 2025
Architecture: 22-module modular Python package with unified CRUD architecture

Overview

TL;DR: Write Python code that unifies multiple skills in one execution - follows Anthropic's MCP pattern for 98.7% more efficient agents.

This project consists of two main components:

  1. MCP Server (src/skill_mcp/server.py) - A Python package providing 5 unified CRUD tools for skill management
  2. Skills Directory (~/.skill-mcp/skills/) - Where you store and manage your skills

Key Advantages

🚀 Unified Multi-Skill Execution (Code Execution with MCP)

Build once, compose everywhere - Execute Python code that seamlessly combines multiple skills in a single run:```python

One execution, multiple skills unified!

Imports from calculator, data-processor, and weather skills

from math_utils import calculate_average # calculator skill
from json_fetcher import fetch_json # data-processor skill
from weather_api import get_forecast # weather skill

Fetch weather data

weather = fetch_json('https://api.weather.com/cities')

Calculate averages using calculator utilities

temps = [city['temp'] for city in weather['cities']]
avg_temp = calculate_average(temps)

Get detailed forecast

forecast = get_forecast('London')
print(f"Average temperature: {avg_temp}°F")
print(f"London forecast: {forecast}")


**What makes this powerful:**
- ✅ **Context-efficient** - Dependencies and env vars auto-aggregated from all referenced skills
- ✅ **Composable** - Mix and match utilities from any skill like building blocks
- ✅ **No redundancy** - Declare PEP 723 dependencies once in library skills, reuse everywhere
- ✅ **Progressive disclosure** - Load only the skills you need, when you need them
- ✅ **Follows Anthropic's MCP pattern** - Code execution with MCP for efficient agents

**Efficiency gains:**
- 📉 **98.7% fewer tokens** when discovering tools progressively vs loading all upfront
- 🔄 **Intermediate results stay in code** - Process large datasets without bloating context
- ⚡ **Single execution** - Complex multi-step workflows in one code block instead of chained tool calls

This aligns with Anthropic's research showing agents scale better by writing code to call tools rather than making direct tool calls for each operation.

### 🔓 Not Locked to Claude UI

Unlike the Claude interface, this system uses the **Model Context Protocol (MCP)**, which is:

- ✅ **Universal** - Works with Claude Desktop, claude.ai, Cursor, and any MCP-compatible client
- ✅ **Not tied to Claude** - Same skills work everywhere MCP is supported
- ✅ **Future-proof** - Not dependent on Claude's ecosystem or policy changes
- ✅ **Local-first** - Full control over your skills and data

### 🎯 Use Skills Everywhere

Your skills can run in:
- **Cursor** - IDE integration with MCP support
- **Claude Desktop** - Native app with MCP access
- **claude.ai** - Web interface with MCP support
- **Any MCP client** - Growing ecosystem of compatible applications

### 📦 Independent & Modular

- ✅ Each skill is self-contained with its own files, scripts, and environment
- ✅ No dependency on proprietary Claude features
- ✅ Can be versioned, shared, and reused across projects
- ✅ Standard MCP protocol ensures compatibility

### 🔄 Share Skills Across All MCP Clients

- ✅ **One skill directory, multiple clients** - Create once, use everywhere
- ✅ **Same skills in Cursor and Claude** - No duplication needed
- ✅ **Seamless switching** - Move between tools without reconfiguring
- ✅ **Consistent experience** - Skills work identically across all MCP clients
- ✅ **Centralized management** - Update skills in one place, available everywhere

### 🤖 LLM-Managed Skills (No Manual Copy-Paste)

Instead of manually copying, zipping, and uploading files:```
❌ OLD WAY: Manual process
   1. Create skill files locally
   2. Zip the skill folder
   3. Upload to Claude interface
   4. Wait for processing
   5. Can't easily modify or version

✅ NEW WAY: LLM-managed programmatically
   1. Tell Claude: "Create a new skill called 'data-processor'"
   2. Claude creates the skill directory and SKILL.md
   3. Tell Claude: "Add a Python script to process CSVs"
   4. Claude creates and tests the script
   5. Tell Claude: "Set the API key for this skill"
   6. Claude updates the .env file
   7. Tell Claude: "Run the script with this data"
   8. Claude executes it and shows results - all instantly!

Key Benefits:
- ✅ No manual file operations - LLM handles creation, editing, deletion
- ✅ Instant changes - No upload/download/reload cycles
- ✅ Full version control - Skills are regular files, can use git
- ✅ Easy modification - LLM can edit scripts on the fly
- ✅ Testable - LLM can create and run scripts immediately
- ✅ Collaborative - Teams can develop skills together via MCP

Features

Skill Management

  • ✅ List all available skills
  • ✅ Browse skill files and directory structure
  • ✅ Read skill files (SKILL.md, scripts, references, assets)
  • ✅ Create new skill files and directories
  • ✅ Update existing skill files
  • ✅ Delete skill files

Script Execution

  • ✅ Run Python, Bash, and other executable scripts
  • ✅ Automatic dependency management for Python scripts using uv inline metadata (PEP 723)
  • ✅ Automatic environment variable injection from secrets
  • ✅ Command-line argument support
  • ✅ Custom working directory support
  • ✅ Capture stdout and stderr
  • ✅ 30-second timeout for safety

Direct Python Execution - Multi-Skill Unification 🚀

  • ✅ UNIFY MULTIPLE SKILLS in one execution - Combine utilities from different skills seamlessly
  • ✅ Execute Python code directly without creating script files
  • ✅ Cross-skill imports - Import modules from ANY skill as reusable libraries
  • ✅ Automatic dependency aggregation - Dependencies from ALL imported skills auto-merged
  • ✅ Environment variable loading - .env files from ALL referenced skills auto-loaded
  • ✅ PEP 723 support - Inline dependency declarations in code
  • ✅ 98.7% more efficient - Follows Anthropic's recommended MCP pattern for scalable agents
  • ✅ Perfect for multi-skill workflows, quick experiments, data analysis, and complex pipelines

Environment Variables

  • ✅ List environment variable keys (secure - no values shown)
  • ✅ Set or update environment variables per skill
  • ✅ Persistent storage in per-skill .env files
  • ✅ Automatic injection into script execution

Directory Structure```

~/.skill-mcp/
└── skills/ # Your skills directory
├── example-skill/
│ ├── SKILL.md # Required: skill definition
│ ├── .env # Optional: skill-specific environment variables
│ ├── scripts/ # Optional: executable scripts
│ ├── references/ # Optional: documentation
│ └── assets/ # Optional: templates, files
└── another-skill/
├── SKILL.md
└── .env


**Note:** The MCP server is installed via `uvx` from PyPI and runs automatically. No local server file needed!

## Quick Start

### 1. Install uv

This project uses uv for fast, reliable Python package management.```bash
# Install uv (includes uvx)
curl -LsSf https://astral.sh/uv/install.sh | sh

2. Configure Your MCP Client

Add the MCP server to your configuration. The server will be automatically downloaded and run via uvx from PyPI.

Claude Desktop - Edit the config file:
- macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
- Windows: %APPDATA%\Claude\claude_desktop_config.json
- Linux: ~/.config/Claude/claude_desktop_config.json

Cursor - Edit the config file:
- macOS: ~/.cursor/mcp.json
- Windows: %USERPROFILE%\.cursor\mcp.json
- Linux: `~/.cursor/mcp.json````json
{
"mcpServers": {
"skill-mcp": {
"command": "uvx",
"args": [
"--from",
"skill-mcp",
"skill-mcp-server"
]
}
}
}


That's it! No installation needed - `uvx` will automatically download and run the latest version from PyPI.

### 3. Restart Your MCP Client

Restart Claude Desktop or Cursor to load the MCP server.

### 4. Test It

In a new conversation:```
List all available skills

Claude should use the skill-mcp tools to show skills in ~/.skill-mcp/skills/.

Common uv Commands

For development in this repository:```bash
uv sync # Install/update dependencies
uv run python script.py # Run Python with project environment
uv add package-name # Add a new dependency
uv pip list # Show installed packages
uv run pytest tests/ -v # Run tests


**Note:** uv automatically creates and manages `.venv/` - no need to manually create virtual environments!

## Script Dependencies (PEP 723)

**✅ BOTH `run_skill_script` AND `execute_python_code` support PEP 723!**

Python scripts and code can declare their own dependencies using uv's inline metadata. The server automatically detects this and uses `uv run` to handle dependencies:```python
#!/usr/bin/env python3
# /// script
# dependencies = [
#   "requests>=2.31.0",
#   "pandas>=2.0.0",
# ]
# ///

import requests
import pandas as pd

# Your script code here - dependencies are automatically installed!
response = requests.get("https://api.example.com/data")
df = pd.DataFrame(response.json())
print(df.head())

Benefits:
- ✅ No manual dependency installation needed
- ✅ Each script/code execution has isolated dependencies
- ✅ Works automatically with both run_skill_script and execute_python_code
- ✅ Version pinning ensures reproducibility
- ✅ execute_python_code ALSO aggregates dependencies from skill imports!

How it works with run_skill_script:
1. You add inline metadata to your Python script file
2. When the script runs via run_skill_script, the server detects the metadata
3. uv automatically creates an isolated environment and installs dependencies
4. The script runs with access to those dependencies
5. No manual pip install or virtual environment management needed!

How it works with execute_python_code:
1. Include PEP 723 metadata directly in your code string
2. The server automatically detects the metadata
3. uv creates an isolated environment and installs dependencies
4. Your code runs with access to those dependencies
5. BONUS: If you import from skill files, their PEP 723 dependencies are automatically aggregated too!

Example: See example-skill/scripts/fetch_data.py for a working example.

Testing locally:```bash

Scripts with dependencies just work!

uv run example-skill/scripts/fetch_data.py


## Direct Python Code Execution - Unify Multiple Skills in One Run

The `execute_python_code` tool allows you to run Python code that **combines multiple skills in a single execution**. This is perfect for:
- 🔄 **Multi-skill workflows** - Import and compose utilities from different skills
- 🧪 **Quick experiments** - Test code without creating files
- 📊 **Data analysis** - Process data using libraries from multiple skills
- 🏗️ **Building on reusable skill libraries** - Create specialized utilities once, use everywhere

**Key insight from Anthropic's research:** Agents scale better by writing code to call tools instead of making direct tool calls. This approach reduces context usage by up to 98.7% and enables more efficient workflows.

### Basic Usage```python
# Simple inline execution with dependencies
# /// script
# dependencies = [
#   "requests>=2.31.0",
# ]
# ///

import requests
response = requests.get("https://api.example.com/data")
print(response.json())

Cross-Skill Imports - Unifying Multiple Skills

The power of composition - Create utility skills once and combine them in endless ways:

Real-world example: Process sales data by unifying calculator, data-processor, and CRM skills:

Step 1: Create a calculator skill with reusable modules```python

calculator:math_utils.py

def add(a, b):
return a + b

def multiply(a, b):
return a * b


**Step 2: Create data-processor skill utilities**```python
# data-processor:csv_parser.py
# /// script
# dependencies = ["pandas>=2.0.0"]
# ///
import pandas as pd

def parse_csv_url(url):
    return pd.read_csv(url)

def filter_by_status(df, status):
    return df[df['status'] == status]

Step 3: Unify both skills in one execution!```python

Execute with skill_references: ["calculator:math_utils.py", "data-processor:csv_parser.py"]

from math_utils import calculate_average
from csv_parser import parse_csv_url, filter_by_status

Get sales data

sales_df = parse_csv_url('https://example.com/sales.csv')

Filter active deals

active_deals = filter_by_status(sales_df, 'active')

Calculate average deal size using calculator skill

deal_values = active_deals['amount'].tolist()
avg_deal = calculate_average(deal_values)

print(f"Active deals: {len(active_deals)}")
print(f"Average deal size: ${avg_deal:,.2f}")


**What just happened:**
- ✅ **Two skills unified** - calculator + data-processor in one execution
- ✅ **Zero redundancy** - pandas dependency declared once in csv_parser.py, auto-included
- ✅ **Composable** - Mix and match any skills like LEGO blocks
- ✅ **Context-efficient** - Only loaded the specific modules needed

### Automatic Dependency Aggregation

When you import from skill modules that have PEP 723 dependencies, they're automatically included:

**Library skill with dependencies:**```python
# data-processor:json_fetcher.py
# /// script
# dependencies = ["requests>=2.31.0"]
# ///
import requests
def fetch_json(url):
    return requests.get(url).json()

Your code - NO need to redeclare requests!```python

Execute with skill_references: ["data-processor:json_fetcher.py"]

from json_fetcher import fetch_json
data = fetch_json('https://api.example.com')
print(data)

Dependencies from json_fetcher.py are automatically aggregated!


### Environment Variables from Referenced Skills

When you import from a skill, its environment variables are **automatically loaded**:

**Skill with API credentials:**```bash
# weather-skill/.env
API_KEY=your-secret-api-key
API_URL=https://api.weatherapi.com

Your code - env vars automatically available:```python

Execute with skill_references: ["weather-skill:api_client.py"]

from api_client import fetch_weather

api_client.py can access API_KEY and API_URL from its .env file

data = fetch_weather('London')
print(data)


**Benefits:**
- ✅ No need to manually load .env files
- ✅ Each skill's secrets stay isolated
- ✅ Multiple skills' env vars are merged automatically
- ✅ Later skills override earlier ones if there are conflicts

### Use Cases

- 🔄 **Multi-skill workflows** - **THE KILLER FEATURE** - Unify utilities from multiple skills in one execution
  - Example: Combine API client + data parser + analytics calculator in single run
  - Example: Chain together scraper + NLP processor + notification sender
  - Example: Merge CRM data + payment processor + reporting tools
- ✅ **Quick data analysis** - Run pandas/numpy code without creating files
- ✅ **API testing** - Test HTTP requests with inline dependencies
- ✅ **Reusable libraries** - Build once, import everywhere
- ✅ **Rapid prototyping** - Experiment with code before committing to files
- ✅ **Complex pipelines** - Build multi-stage data processing in one code block

### Comparison: `run_skill_script` vs `execute_python_code`

Both tools support PEP 723, but have different use cases:

| Feature | `run_skill_script` | `execute_python_code` |
|---------|-------------------|----------------------|
| **PEP 723 Support** | ✅ YES | ✅ YES |
| **Requires file** | ✅ Yes - executes existing script files | ❌ No - runs code directly |
| **Languages supported** | Python, JavaScript, Bash, any executable | Python only |
| **Cross-skill imports** | ❌ No - single skill only | ✅ YES - **UNIFY MULTIPLE SKILLS** |
| **Dependency aggregation** | ❌ No | ✅ YES - **auto-merges deps from all imported skills** |
| **Environment loading** | Loads skill's .env only | **Loads .env from ALL referenced skills** |
| **Context efficiency** | Standard | **98.7% token reduction** (Anthropic research) |
| **Best for** | Running complete scripts, batch jobs | **Multi-skill workflows**, quick experiments |
| **Example use case** | `python data_processor.py --input data.csv` | **`from skill1 import x; from skill2 import y; combined()`** |

**Key Insight:**
- Use `run_skill_script` when you have a script file ready to execute
- Use `execute_python_code` when you want to **UNIFY MULTIPLE SKILLS in one execution** - This is the recommended approach per Anthropic's MCP research for building efficient, scalable agents

## Usage Examples

### Creating a New Skill```
User: "Create a new skill called 'pdf-processor' that can rotate and merge PDFs"

Claude will:
1. Create the skill directory and SKILL.md
2. Add any necessary scripts
3. Test the scripts
4. Guide you through setting up any needed dependencies

Managing Environment Variables```

User: "I need to set up a GitHub API token for my GitHub skills"

Claude will:
1. Guide you to add it to the skill's .env file
2. Use read_skill_env to list available keys
3. Confirm it's available for scripts to use via os.environ


### Running Skill Scripts```
User: "Run the data processing script from my analytics skill"

Claude will:
1. List available skills and scripts
2. Execute the script with environment variables
3. Show you the output and any errors

Modifying Existing Skills```

User: "Add a new reference document about our API schema to the company-knowledge skill"

Claude will:
1. Read the existing skill structure
2. Create the new reference file
3. Update SKILL.md if needed to reference it


## Available MCP Tools

The server provides these unified CRUD tools to Claude:

| Tool              | Purpose | PEP 723 Support |
|-------------------|---------|-----------------|
| `skill_crud`      | Unified skill operations: list, get, create, delete, validate, list_templates | N/A |
| `skill_files_crud` | Unified file operations: read, create, update, delete (supports bulk operations) | N/A |
| `skill_env_crud`  | Unified environment variable operations: read, set, delete, clear | N/A |
| `run_skill_script` | Execute scripts (.py, .js, .sh) with automatic dependency detection | ✅ YES - Auto-detects PEP 723 in Python scripts |
| `execute_python_code` | Execute Python code directly without files (cross-skill imports) | ✅ YES - PEP 723 PLUS dependency aggregation |

**Key Benefits of CRUD Architecture:**
- ✅ **Reduced context window usage** - 5 tools instead of 9+
- ✅ **Consistent operation patterns** - All tools follow the same CRUD model
- ✅ **Bulk operations** - Create/update/delete multiple files atomically
- ✅ **Better error handling** - Unified error responses across all operations

## Security Features

### Path Validation
- All file paths are validated to prevent directory traversal attacks
- Paths with ".." or starting with "/" are rejected
- All operations are confined to the skill directory

### Environment Variables
- Variable values are never exposed when listing
- Stored in per-skill `.env` files
- File permissions should be restricted (chmod 600 on each .env)

### Script Execution
- 30-second timeout prevents infinite loops
- Scripts run with user's permissions (not elevated)
- Output size limits prevent memory issues
- Capture both stdout and stderr for debugging

## Troubleshooting

### "MCP server not found"
- Check that `uv` is in your PATH: `which uv` (or `where uv` on Windows)
- Verify the path to `.skill-mcp` directory is correct and absolute
- Test dependencies: `cd ~/.skill-mcp && uv run python -c "import mcp; print('OK')"`
- Ensure `pyproject.toml` exists in `~/.skill-mcp/`

### "Permission denied" errors```bash
chmod +x ~/.skill-mcp/skill_mcp_server.py
chmod 755 ~/.skill-mcp
chmod 755 ~/.skill-mcp/skills
find ~/.skill-mcp/skills -name ".env" -exec chmod 600 {} \;

Scripts failing to execute

  • Check script has execute permissions
  • Verify interpreter (python3, bash) is in PATH
  • Use list_env_keys to check required variables are set
  • Check stderr output from run_skill_script

Environment variables not working

  • Verify they're set: use read_skill_env for the skill
  • Check the .env file exists: cat ~/.skill-mcp/skills//.env
  • Ensure your script is reading from os.environ

Advanced: CRUD Tool Operations

All MCP tools follow a unified CRUD architecture with detailed descriptions:

skill_crud Operations

  • list - List all skills with descriptions, paths, and validation status (supports text/regex search)
  • get - Get comprehensive skill information: SKILL.md content, all files, scripts, environment variables
  • create - Create new skill from template (basic, python, bash, nodejs)
  • delete - Delete a skill directory (requires confirmation)
  • validate - Validate skill structure and get diagnostics
  • list_templates - List all available skill templates with descriptions

skill_files_crud Operations

  • read - Read one or multiple files in a skill directory (supports bulk reads)
  • create - Create one or more files (auto-creates parent directories, supports atomic bulk creation)
  • update - Update one or more existing files (supports bulk updates)
  • delete - Delete a file permanently (path-traversal protected, SKILL.md cannot be deleted)

skill_env_crud Operations

  • read - List environment variable keys for a skill (values hidden for security)
  • set - Set one or more environment variables (merges with existing)
  • delete - Delete one or more environment variables
  • clear - Clear all environment variables for a skill

Script Execution

  • run_skill_script - Execute scripts with automatic PEP 723 dependency detection and environment variable injection
  • execute_python_code - Execute Python code directly without files (supports PEP 723 dependencies and cross-skill imports)

Advanced Configuration

Custom Skills Directory

The skills directory can be customized using the SKILL_MCP_DIR environment variable. If not set, it defaults to ~/.skill-mcp/skills.

Setting via environment variable (recommended):```bash

Temporarily for current session

export SKILL_MCP_DIR="/custom/path/to/skills"

Permanently in your shell config (~/.bashrc, ~/.zshrc, etc.)

echo 'export SKILL_MCP_DIR="/custom/path/to/skills"' >> ~/.zshrc


**In MCP client configuration:**

For Claude Desktop or Cursor, add the environment variable to your MCP config:```json
{
  "mcpServers": {
    "skill-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "skill-mcp",
        "skill-mcp-server"
      ],
      "env": {
        "SKILL_MCP_DIR": "/custom/path/to/skills"
      }
    }
  }
}

Notes:
- The directory will be created automatically if it doesn't exist
- Use absolute paths for the custom directory
- All skills will be stored in the configured directory
- No global secrets file; env vars are per-skill .env files

Resource Limits

Resource limits are defined in src/skill_mcp/core/config.py:```python
MAX_FILE_SIZE = 1_000_000 # File read limit (1MB)
MAX_OUTPUT_SIZE = 100_000 # Script output limit (100KB)
SCRIPT_TIMEOUT_SECONDS = 30 # Script execution timeout


To modify these limits, you'll need to fork the repository and adjust the constants in the config file.

## Architecture & Implementation

### Package Structure```
src/skill_mcp/
├── server.py              # MCP server entry point
├── models.py              # Pydantic input/output models (backward compat)
├── models_crud.py         # Unified CRUD input models
├── core/
│   ├── config.py          # Configuration constants
│   └── exceptions.py      # Custom exception types
├── services/
│   ├── env_service.py     # Environment variable CRUD
│   ├── file_service.py    # File CRUD operations
│   ├── skill_service.py   # Skill discovery & metadata
│   ├── script_service.py  # Script execution & PEP 723
│   └── template_service.py # Template management
├── utils/
│   ├── path_utils.py      # Secure path validation
│   ├── yaml_parser.py     # YAML frontmatter parsing
│   └── script_detector.py # Script capability detection
└── tools/
    ├── skill_crud.py      # Unified skill CRUD tool
    ├── skill_files_crud.py # Unified file CRUD tool
    ├── skill_env_crud.py  # Unified env CRUD tool
    └── script_tools.py    # Script execution tools

tests/
├── conftest.py            # Pytest fixtures
└── 20+ test modules       # 145 tests (86% coverage passing)

What's New

Unified CRUD Architecture:
- ✅ 3 unified CRUD tools instead of 9+ individual tools (skill_crud, skill_files_crud, skill_env_crud)
- ✅ Bulk operations - Create/update/delete multiple files atomically
- ✅ Consistent patterns - All tools follow the same operation-based model
- ✅ Better error handling - Unified error responses across all operations

Direct Python Execution (Multi-Skill Unification):
- 🚀 execute_python_code - UNIFY MULTIPLE SKILLS in one execution (Anthropic's recommended MCP pattern)
- ✅ Cross-skill imports - Import modules from ANY skill as reusable libraries
- ✅ Automatic dependency aggregation - Dependencies from ALL imported skills auto-merged
- ✅ Automatic environment loading - .env files from ALL referenced skills auto-loaded
- ✅ PEP 723 support - Inline dependency declarations
- 📉 98.7% token reduction - Load skills progressively instead of all upfront

Enhanced Features:
- ✅ Skill templates - Create skills from templates (basic, python, bash, nodejs)
- ✅ Template discovery - List all available templates with descriptions
- ✅ Skill validation - Validate skill structure and get diagnostics
- ✅ Search capabilities - Search skills by name/description with text or regex
- ✅ Namespaced paths - File paths shown as "skill_name:file.py" for clarity
- ✅ Configurable skills directory - Use SKILL_MCP_DIR environment variable

Test Results

Unit Tests: 145/145 Passing ✅

Coverage: 86% (959/1120 statements covered)

Comprehensive test coverage across all modules:

Module Coverage Key Areas
Core Config 100% All configuration constants
Models & CRUD Models 100% Input/Output validation
Exception Handling 100% All exception types
YAML Parser 90% Frontmatter parsing
Skill Service 90% Skill discovery & metadata
Template Service 96% Template management
File Service 83% File CRUD operations
Environment Service 85% Environment variable CRUD
Skill CRUD Tool 91% Unified skill operations
Skill Files CRUD Tool 88% Unified file operations
Skill Env CRUD Tool 96% Unified env operations
Script Detector 85% Script capability detection
Path Utils 86% Path validation & security
Server 76% MCP tool registration
Script Service 78% Script execution & PEP 723
Script Tools 29% Script execution tools

Test Organization:
- ✅ CRUD operations: Comprehensive tests for all operations (create, read, update, delete)
- ✅ Bulk operations: Atomic transaction tests for file operations
- ✅ Template system: Template discovery, validation, and creation
- ✅ Path security: Directory traversal prevention and validation
- ✅ PEP 723 support: Dependency detection and aggregation
- ✅ Integration tests: Full MCP server workflow testing

Manual Tests: All Passed ✅

  • ✅ List skills with YAML descriptions and search functionality
  • ✅ Get comprehensive skill details with SKILL.md content
  • ✅ Create skills from templates (basic, python, bash, nodejs)
  • ✅ Read/create/update/delete files (single and bulk)
  • ✅ Read/set/delete/clear environment variables
  • ✅ Execute scripts with auto-dependencies (PEP 723)
  • ✅ Execute Python code directly with cross-skill imports
  • ✅ Dependency aggregation from imported skill modules
  • ✅ Environment variable loading from referenced skills

Verification Checklist

  • ✅ Server imports successfully
  • ✅ All 5 unified CRUD tools registered and callable
  • ✅ 145/145 unit tests passing (86% coverage)
  • ✅ All manual tests passing
  • ✅ MCP client configuration working (Claude Desktop, Cursor)
  • ✅ Package deployed to PyPI and active
  • ✅ Scripts execute successfully with PEP 723 dependencies
  • ✅ File operations working (including bulk operations)
  • ✅ Environment variables working (CRUD operations)
  • ✅ Template system working (create, list, validate)
  • ✅ Direct Python execution working with cross-skill imports
  • ✅ Backward compatible with existing skills

Best Practices

Skill Development

  • Follow the standard skill structure (SKILL.md, scripts/, references/, assets/)
  • Keep SKILL.md concise and focused
  • Use progressive disclosure (split large docs into references)
  • Test scripts immediately after creation

Environment Variables

  • Use descriptive names (API_KEY, DATABASE_URL)
  • Never log or print sensitive values
  • Set permissions on .env files: chmod 600 ~/.skill-mcp/skills//.env

Script Development

  • Use meaningful exit codes (0 = success)
  • Print helpful messages to stdout
  • Print errors to stderr
  • Include error handling
  • For Python scripts with dependencies: Use inline metadata (PEP 723)python # /// script # dependencies = [ # "package-name>=version", # ] # ///
  • Scripts without metadata use the system Python interpreter

…(正文过长,页面只展示前面部分,完整内容见仓库)

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
Skill Management MCP Server 怎么安装?

在客户端按下面的安装命令接入:uv run python script.py # Run Python with project environment。装完在客户端配置里引用同一个包或端点。

Skill Management MCP Server 怎么在 Claude Desktop、Claude、Cursor 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。

Skill Management MCP Server 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。

Skill Management MCP Server 需要 API Key 吗?

资料标注需要API Key认证,使用前准备好对应凭据,并按最小权限配置。

Skill Management MCP Server 支持哪些客户端?

资料标注支持 Claude Desktop、Claude、Cursor;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。

Skill Management MCP Server 能提供哪些能力?

资料显示约 9 个工具;能力标签包括 技能管理、代码执行、Python、Claude。具体工具清单以官方文档为准。

Skill Management MCP Server 需要什么运行环境?

运行时为 Python;属于本地进程,需要在本机装好运行环境。

Skill Management MCP Server 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。