cli
by mcpgod
Fine-grained control over model context protocol (MCP) clients, servers, and tools. Context is God.
117stars
10forks
TypeScript
Added 12/27/2025
View on GitHubDownload ZIPScan for vulnerabilities
Requires a passing catalog security scan. Resolve the flagged issues and resubmit to enable featuring.
Installation
# Add to your Claude Code skills
git clone https://github.com/mcpgod/cliGetting Started
Guides for using mcp servers skills like cli.
- Best MCP Servers in 2026Category-by-category picks: databases, dev tools, productivity, browser automation.
- What is an AI Skills Marketplace?Definitions, how marketplaces work, and how to choose between them in 2026.
- Getting Started with AI SkillsFirst-time install walkthrough for Claude Code, Codex CLI, and ChatGPT.
Security ReportIssues
Last scanned: 5/30/2026
{
"issues": [
{
"type": "npm-audit",
"message": "@aws-sdk/client-cloudfront: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "@aws-sdk/client-s3: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "@aws-sdk/client-sso: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "@aws-sdk/core: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "@aws-sdk/credential-provider-env: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "@aws-sdk/credential-provider-http: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "@aws-sdk/credential-provider-ini: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "@aws-sdk/credential-provider-node: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "@aws-sdk/credential-provider-process: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "@aws-sdk/credential-provider-sso: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "@aws-sdk/credential-provider-web-identity: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "@aws-sdk/middleware-flexible-checksums: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "@aws-sdk/middleware-sdk-s3: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "@aws-sdk/middleware-user-agent: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "@aws-sdk/nested-clients: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "@aws-sdk/signature-v4-multi-region: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "@aws-sdk/token-providers: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "@aws-sdk/util-user-agent-node: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "@eslint/plugin-kit: @eslint/plugin-kit is vulnerable to Regular Expression Denial of Service attacks through ConfigCommentParser",
"severity": "low"
},
{
"type": "npm-audit",
"message": "@inquirer/editor: Vulnerability found",
"severity": "low"
},
{
"type": "npm-audit",
"message": "@modelcontextprotocol/sdk: Anthropic's MCP TypeScript SDK has a ReDoS vulnerability",
"severity": "high"
},
{
"type": "npm-audit",
"message": "@smithy/config-resolver: AWS SDK for JavaScript v3 adopted defense in depth enhancement for region parameter value",
"severity": "low"
},
{
"type": "npm-audit",
"message": "@smithy/middleware-retry: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "ajv: ajv has ReDoS when using `$data` option",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "brace-expansion: brace-expansion: Zero-step sequence causes process hang and memory exhaustion",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "diff: jsdiff has a Denial of Service vulnerability in parsePatch and applyPatch",
"severity": "low"
},
{
"type": "npm-audit",
"message": "eslint: Vulnerability found",
"severity": "low"
},
{
"type": "npm-audit",
"message": "express: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "external-editor: Vulnerability found",
"severity": "low"
},
{
"type": "npm-audit",
"message": "fast-xml-parser: fast-xml-parser has an entity encoding bypass via regex injection in DOCTYPE entity names",
"severity": "critical"
},
{
"type": "npm-audit",
"message": "flatted: flatted vulnerable to unbounded recursion DoS in parse() revive phase",
"severity": "high"
},
{
"type": "npm-audit",
"message": "glob: glob CLI: Command injection via -c/--cmd executes matches with shell:true",
"severity": "high"
},
{
"type": "npm-audit",
"message": "js-yaml: js-yaml has prototype pollution in merge (<<)",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "lodash: Lodash has Prototype Pollution Vulnerability in `_.unset` and `_.omit` functions",
"severity": "high"
},
{
"type": "npm-audit",
"message": "minimatch: minimatch has a ReDoS via repeated wildcards with non-matching literal in pattern",
"severity": "high"
},
{
"type": "npm-audit",
"message": "mocha: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "path-to-regexp: path-to-regexp vulnerable to Denial of Service via sequential optional groups",
"severity": "high"
},
{
"type": "npm-audit",
"message": "picomatch: Picomatch: Method Injection in POSIX Character Classes causes incorrect Glob Matching",
"severity": "high"
},
{
"type": "npm-audit",
"message": "qs: qs's arrayLimit bypass in comma parsing allows denial of service",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "serialize-javascript: Serialize JavaScript is Vulnerable to RCE via RegExp.flags and Date.prototype.toISOString()",
"severity": "high"
},
{
"type": "npm-audit",
"message": "tmp: tmp allows arbitrary temporary file / directory write via symbolic link `dir` parameter",
"severity": "high"
},
{
"type": "npm-audit",
"message": "uuid: uuid: Missing buffer bounds check in v3/v5/v6 when buf is provided",
"severity": "medium"
}
],
"status": "FAILED",
"scannedAt": "2026-05-30T16:31:38.412Z",
"npmAuditRan": true,
"pipAuditRan": true
}MCPGod
Fine-grained control over model context protocol (MCP) clients, servers, and tools. Context is God.
Overview
MCPGod is a CLI tool designed to help developers manage MCP servers with speed and ease. Whether you need to add, run, list, or remove servers—or even interact with server tools—MCPGod provides a streamlined interface to handle all these tasks on Windows, macOS, or Linux.
Features
- Client Management
Add, remove, and list MCP servers for specific clients. - Tool Discovery List every tool on any MCP server.
- Tool Calling Run any tool on any MCP server directly from the command line.
- Tool/Client Permissions Allow or block specific tools for specific clients.
- Detailed Logging Log every server run from every client, with timestamps and clean output for easy debugging.
Installation
Install mcpgod globally using npm:
npm install -g mcpgod
Verify the installation:
mcpgod --version
Or run directly with npx.
npx -y mcpgod
Usage
Access the CLI with the mcpgod command (or npx -y mcpgod). Below are some common examples:
-
Add a Server to a Client
Add an MCP server to a client (e.g., Claude) with
mcpgod add <SERVER> -c <CLIENT>:mcpgod add @modelcontextprotocol/server-everything -c claude -
Only Add Specific Tools to a Client
Only add specific tools to a client with
mcpgod add <SERVER> -c <CLIENT> --tools=<COMMA_DELIMITED_LIST>:mcpgod add @modelcontextprotocol/server-everything -c claude --tools=echo,add -
List Servers for a Client
List all configured servers for a specific client with
mcpgod list -c <CLIENT>:mcpgod list -c claude -
Remove a Server
Remove an MCP server from your client's configuration with
mcpgod remove <SERVER> -c <CLIENT>:mcpgod remove @modelcontextprotocol/server-everything -c claude -
Run a Server
Run a server process with detailed logging with
mcpgod run <SERVER>:mcpgod run @modelcontextprotocol/server-everything mcpgod run ./mcp-server.py mcpgod run ./mcp-server-node.mjs -
List Available Tools for a Server
Display the list of tools available on a server with
mcpgod tools <SERVER>:mcpgod tools @modelcontextprotocol/server-everything mcpgod tools ./mcp-server.py mcpgod tools ./mcp-server-node.mjs -
Call a Specific Tool on a Server
Interact with a tool by passing key-value properties with
mcpgod tool <SERVER> <TOOL> [optional parameters]:mcpgod tool @modelcontextprotocol/server-everything add a=59 b=40 mcpgod tool ./mcp-server.py echo message=hi mcpgod tool ./mcp-server-node.mjs echo message=hi
For a complete list of commands and options, simply run:
mcpgod --help
Logging
When running a server, mcpgod logs output to:
~/mcpgod/logs
Each log file is organized by server name and timestamped to help you trace and debug any issues that arise.
Development
mcpgod is built with the Oclif framework and uses the Model Context Protocol SDK for robust interactions with MCP servers.
Clone the repository to get started with development:
git clone https://github.com/mcpgod/cli.git
cd mcpgod
npm install
Run the CLI in development mode:
./bin/dev
Publishing
Automatic publishing is handled by the version, tag and github release workflow. A new npm version is published whenever a version bump is merged into the main branch. The workflow can also be triggered manually from the Actions tab.
To enable publishing, set the following repository secrets:
NPM_TOKEN– authentication token for npm.GH_EMAILandGH_USERNAME– used by the README update step.
Once the secrets are configured, pushing a new version or running the workflow manually will build the project, create a GitHub release and publish the package to npm.
Linting workflows
Before committing changes to workflows, you can lint them locally:
npm run lint:workflows
Contributing
Contributions are always welcome! To contribute:
- Fork the repository.
- Create a branch:
git checkout -b feature/your-feature - Make your changes, and commit them:
git commit -am 'Add new feature' - Push your branch:
git push origin feature/your-feature - Open a Pull Request on GitHub.
License
This project is licensed under the MIT License.
Additional Resources
Frequently Asked Questions
What is cli?
cli is an open-source mcp servers skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by mcpgod. Fine-grained control over model context protocol (MCP) clients, servers, and tools. Context is God. It has 117 GitHub stars.
Is cli safe to use?
cli failed SkillsLLM's automated security scan, which flagged one or more high-severity issues. Review the Security Report section carefully before using it.
How do I install cli?
Clone the repository with "git clone https://github.com/mcpgod/cli" and add it to your Claude Code skills directory (see the Installation section above).
What programming language is cli written in?
cli is primarily written in TypeScript. It is open-source under mcpgod on GitHub, so you can review or fork the full source.
Are there alternatives to cli?
Yes. SkillsLLM lists many other MCP Servers skills you can browse and compare side by side. Open the MCP Servers category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh cli against similar tools.
Comments (0)
to leave a comment.
No comments yet. Be the first to share your thoughts!
Related Skills
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
228,318
35,019
JavaScript
AI Agentsai-agentsanthropic
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
196,003
59,243
TypeScript
MCP Serversaiapis
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
185,940
28,768
JavaScript
AI Agentsai-agentsanthropic
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
115,756
7,746
Rust
AI Agentsai-toolsclaude-code
An open-source AI agent that brings the power of Gemini directly into your terminal.
105,903
14,240
TypeScript
AI Agentsaiai-agents
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!
69,067
6,832
Python
MCP Serversaiai-scraping
Popular in MCP Servers
Top skills in this category by stars
⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载，你的 AI 舆情监控助手与热点筛选工具！聚合多平台热点 + RSS 订阅，支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机，也支持接入 MCP 架构，赋能 AI 自然语言对话分析、情感洞察与趋势预测等。支持 Docker ，数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 等渠道智能推送。
60,453
24,783
Python
MCP Serversaibark