mcp-easy-installer
Provides workaround to update MCP server connections for VS Code GitHub Copilot via Claude Desktop's MCP servers.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-easy-installersearch for a MCP server that can scrape websites"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Easy Installer
MCP easy installer is a robust mcp server with tools to search, install, configure, repair and uninstall MCP servers.
Install & Repair Tools for MCP servers
MCP easy installer is a robust tool to search, install, configure, repair and uninstall MCP servers (Model Context Protocol). This utility is designed for developers and non-developers and end users, making it easy to set up and maintain MCP servers without technical expertise. Developers and system integrators can also use it to speed up their workflow and automate repetitive tasks. The tool streamlines setup, automates repairs, and ensures your MCP environment is always healthy. This tool will automatically install and update all the necessary JSON configuration files for a wide range of applications, including Claude Desktop, Windsurf, Cursor, Roo Code, Cline, *GitHub Copilot, and more. It ensures seamless integration and up-to-date settings across your AI and developer tools ecosystem.
Related MCP server: Coyote MCP Server
Features
Search & Discovery: Find available MCP servers for installation.
Automated Installation: Quickly install MCP servers from GitHub or local sources.
Repair Utility: Detects and fixes common MCP server issues.
TypeScript Support: Built with TypeScript for reliability and maintainability.
Comprehensive Logging: Clear logs for every operation.
Cross-Platform: Works on Windows, Linux, and Mac.
Important Installation Note
MCP easy intaller do not use npx to install MCP servers with Node.js.
Instead, it manually install all MCP servers in the following directory:
Windows:
C:\Users\USERNAME\Documents\Flowvibe\MCP\Linux/Mac:
/home/USERNAME/Documents/Flowvibe/MCP/
Replace USERNAME with your actual user name on your system.
VS Code - GitHub Copilot Integration Notes
GitHub Copilot for VS Code is not directly supported by this tool.
GitHub Copilot implements MCP in its own way with significant differences from other implementations. Due to these differences, GitHub Copilot is not included in this tool's supported applications.
Workaround: If you want to update MCP server connections for VS Code GitHub Copilot, install Claude Desktop, as GitHub Copilot connects to Claude Desktop's MCP servers. This provides an indirect way to enhance GitHub Copilot's capabilities through MCP.
Python Integration Notes
Python integration with MCP has some limitations.
While this tool aims to provide seamless integration across multiple platforms and languages, Python support is currently imperfect and may require manual intervention in certain scenarios. Due to the diversity of Python environments, package managers, and project structures, automated installation and configuration may not work optimally in all cases.
We welcome community contributions:
If you encounter issues with Python integration, please share your solutions in the issues section
Consider forking this repository to implement improvements specific to Python environments
Pull requests with enhancements to Python support are greatly appreciated
Our goal is to improve Python integration through collaborative development and user feedback.
Installation
Clone the repository and install dependencies:
Option 1: Install with Git
# Clone the repository
git clone https://github.com/onigetoc/mcp-easy-installer.git
# Navigate to the directory
cd mcp-easy-installer
# Install dependencies
npm install
# Build the project
npm run build
# Test tools
npm run test-toolsOption 2: Download and Install
Download the latest release from https://github.com/onigetoc/mcp-easy-installer
Extract the files to your preferred location
Open a terminal in the extracted directory
Run
npm installto install dependenciesRun
npm run buildto compile the application for use with MCP clients
Configuration
Configure your MCP servers in your settings file (The Github token is optional to search mcp server: Prevents rate limiting):
By default, the tool searches for repositories in TypeScript (ts), JavaScript (js), and HTML. You can customize this or add other languages (like Python 'py' or Shell 'sh') using the --langcode argument. For example, to search also for Python and Shell repositories, you would add "--langcode=ts,js,html,py,sh" to the args list below. For the easiest setup, it's recommended to omit the --langcode argument to use the defaults.
{
"mcpServers": {
"mcp-easy-installer": {
"command": "node",
"args": ["path-to\\mcp-easy-installer\\build\\index.js"],
"env": {
"GITHUB_TOKEN": "your_github_token"
}
}
}
}Example: Configuration with all supported languages
If you want to customize the languages used for searching, here's an example of the args array that includes all supported language codes. withour this line, default are javascript, typescript and html:
"args": [
"path-to\\mcp-easy-installer\\build\\index.js",
"--langcode=ts,js,html,py,sh"
]
// this will also work
"--langcode=typescript,javascript,HTML,python,shell" // Your can add more according to the Github search filterGet your personal GitHub Token then click Generate new token (You may have to login or create a Githhub account before).
Example Phrases
Community Question: GitHub Search Integration
We are considering whether to integrate a GitHub search feature directly into this tool. If integrated, providing a GitHub API token could be optional—without it, the Github search feature will not work (or may be restricted and limited), but all other tools and features will continue to function normally.
We invite feedback from the community: Would you like to see GitHub search built in? Please share your thoughts and use cases in the issues or discussions section of this repository.
You can use natural language commands like:
Search for the fetch mcp server. (follow up prompt: install the third one)May work with Brave or any others search tools with the Github or npmjs link.Search Github mcp server "wikipedia server"Install this mcp server: https://www.npmjs.com/package/@modelcontextprotocol/server-brave-search(NPMjs or Github repo url) or use InstallInstall this mcp server tavily-ai/tavily-mcpInstall mcp server with a Brave Github link search result.Repair the brave mcp server.Update all installed mcp servers.Not working yetUninstall BraveWill work and find it even if the name is "server-brave-search"
Note: Depending on LLM and the tool functions, it is perhaps preferable to often use these two words to trigger the MCP. Install, repair, fix, search mcp servers.
Platform Testing
This tool has been primarily developed and tested on Windows to fix problematic NPX installation . While it's designed to be cross-platform, we have limited ability to test on all operating systems.
Mac and Linux Testing: We need feedback from Mac and Linux users to ensure compatibility across all platforms. If you're using this tool on macOS or Linux distributions:
Please report any issues you encounter in the GitHub Issues
Specify your operating system version and environment details
Suggestions for platform-specific improvements are welcome
Consider contributing platform-specific fixes if you have the expertise
Your feedback is invaluable in making this tool work seamlessly across all operating systems.
Optimized MCP Server Usage with LLMs
Through extensive testing with various MCP servers, we've discovered an optimal approach for LLMs to interact with MCP servers, even for smaller models using Function calls. Here's the recommended context to add to your MCP client for better results:
Every time you use a MCP server (Model Context Protocol), you must give the complete information. If, for example, you are asked to do a search on anything (YouTube, Wikipedia, Internet, BRAVE, etc.), you must give as much information as possible on the title, description and links. The links are very important in the answer because it can be used later in the conversation, for follow-up interactions with the MCP Client or others MCP servers.
At the beginning of each answer but only if it's a complex question, make a bullet list to summarize what you are going to do between 5 and 10 points of what you will do next.
After your answer, if it's a complex question, always write a resume and a plan to follow at the end of the answer.
Use MCP server tools to go deeper when it's a structured work to do according the the complexity of the task.
For example, if the user asks something very simple like, "hello, how are you?" You don't have to do deep research and just answer normally, without task, without going deeper. Just answer directly.For a complete example of this implementation, see this Github Gist.
Installation Flow
graph TD
A[Parse User Input] --> B{URL Type?}
B -->|GitHub shorthand| C[Construct full URL]
B -->|Full URL| D[Clone Repository]
C --> D
D --> E[Install Dependencies]
E --> F[Build Project]
F --> G[Locate index.js]
G --> H[Generate MCP Config]
H --> I[Update Settings]Contributing
Fork the repository.
Create a new branch.
Make your changes.
Submit a pull request.
Or only send suggestions and help from issues section.
License
MIT
Available Tools
4 toolsinstall_mcp_serverA
Install a new MCP server from a GitHub repository URL OR link this: "https://github.com/overstarry/qweather-mcp" OR https://github.com/modelcontextprotocol/servers/tree/main/src/brave-search or npm package
| Name | Required | Description | Default |
|---|---|---|---|
| repo_url | Yes | GitHub URL, shorthand (owner/repo), or npm URL (https://www.npmjs.com/package/@modelcontextprotocol/server-name) |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. Description does not disclose side effects (e.g., network calls, config changes, permissions). It only states 'Install' without explaining what happens if server already exists or what dependencies are installed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is a single sentence with examples, but the phrasing 'OR link this:' is informal. Could be more structured (e.g., list formats) without increasing length significantly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema or annotations. Description lacks details on return values, success/failure indications, and operational steps (e.g., cloning, dependency installation, config updates). Incomplete for a installation tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers 100% of parameters with description. Description adds concrete examples and clarifies acceptable formats (GitHub URL, shorthand, npm URL), providing value beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool installs a new MCP server from a GitHub URL or npm package. It distinguishes from sibling tools (repair, search, uninstall) by specifying installation as the action.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Description mentions acceptable input formats (GitHub URL, shorthand, npm URL) and provides examples, but does not explicitly state when not to use or prerequisites (e.g., whether Node.js is required). Sibling names imply clear context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
repair_mcp_serverA
Repair an MCP server by uninstalling and reinstalling it. Requires the keyword to find the server and the original installation URL.
| Name | Required | Description | Default |
|---|---|---|---|
| repo_url | Yes | The original GitHub URL or npm URL used to install the server | |
| server_keyword | Yes | Keyword or name to find the server to repair (case-insensitive, partial match) |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, and the description does not disclose potential side effects (e.g., data loss from uninstall) or permissions needed. For a destructive action, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence is concise, but slightly more structure (e.g., separating action from requirements) could improve readability. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with 2 params and no output schema, the description covers core functionality. However, it lacks mention of failure conditions or prerequisites, making it slightly incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions. The description adds useful detail: server_keyword is case-insensitive and partial match, which schema omits. Adds value beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool repairs an MCP server by uninstalling and reinstalling it, with specific requirements. It distinguishes itself from siblings (install, search, uninstall).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for repairing a broken server but does not explicitly state when to use vs alternative approaches like manual uninstall+install. No exclusions or alternatives provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_mcp_serverA
Search for MCP servers on GitHub. Uses GITHUB_TOKEN from server config.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search query for GitHub repositories (e.g. "mcp-server", "language:typescript mcp") |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must carry full burden. Only mentions token usage; lacks details about rate limits, pagination, result format, or any side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with purpose, no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Simple tool with one parameter and no output schema; description is mostly complete but could mention the nature of the return value (e.g., list of repositories).
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with a clear description of the 'query' parameter. Tool description adds no extra semantic value beyond the parameter's schema definition.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it searches for MCP servers on GitHub using a specific verb+resource. Distinguishes from sibling tools (repair, install, uninstall) which are different actions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implied usage as a search tool vs siblings is clear, but no explicit when-to-use or when-not-to-use guidance beyond mentioning the GITHUB_TOKEN dependency.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
uninstall_mcp_serverB
Uninstall an MCP server
| Name | Required | Description | Default |
|---|---|---|---|
| server_name | Yes | Name of the server to uninstall |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description carries full burden. It fails to disclose that uninstallation is destructive, irreversible, or may require permissions. The description is too brief for a potentially high-impact operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no wasted words. Front-loaded and directly to the point.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with no output schema, the description lacks critical context about destructiveness, success/failure behavior, and prerequisites. It is not sufficiently informative for an agent to use safely.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the schema already documents the parameter. The description adds no additional meaning beyond the schema, but baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states exactly what the tool does: 'Uninstall an MCP server'. It uses a specific verb and resource, and clearly distinguishes from siblings like install, repair, or search.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives, no prerequisites or side effects mentioned. The description is minimal and provides no context for tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
4 tool updates
v1.0.0- First observed
install_mcp_server - First observed
repair_mcp_server - First observed
search_mcp_server - First observed
uninstall_mcp_server
TDQS
Each tool has a distinct and clear purpose: install, uninstall, repair, and search. There is no overlap or ambiguity between them.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., install_mcp_server, uninstall_mcp_server), making them predictable and easy to understand.
With only 4 tools, the server is well-scoped for an installer. Each tool serves a necessary function without unnecessary bloat.
The tool set covers the core lifecycle: install, uninstall, repair, and search. While a 'list installed servers' tool might be useful, it is not a critical gap given the current scope.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Search and install 4,000+ security-scanned MCP servers from inside any MCP-aware AI client.
MCP server for building and testing AI agents with multi-model experimentation and insights.
Personal assistant MCP server with search, execute, packages, jobs, secrets, and integrations.
MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.
Related MCP Servers
- AlicenseBqualityCmaintenanceAn MCP server that supercharges AI assistants with powerful tools for software development, enabling research, planning, code generation, and project scaffolding through natural language interaction.1167101MIT
- FlicenseBqualityDmaintenanceAn MCP server that provides easy setup and configuration for multiple AI development environments including Claude Desktop, VS Code, and Windsurf. Offers automated installation scripts and manual configuration options for seamless integration across different MCP-compatible clients.18-
- FlicenseNot gradedqualityDmaintenanceA modular MCP server that provides tools for file operations, regex-based code searching, and structural analysis of functions and classes across multiple programming languages. It also includes AI-powered features for intelligently updating files according to architectural changes.-

onion-mcp-serverofficial
AlicenseAqualityDmaintenanceA feature-rich MCP server offering 30 tools across AI, code, text, data, web, and system categories, enabling tasks like chat, translation, code review, web scraping, and text processing.30MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/onigetoc/mcp-easy-installer'
If you have feedback or need assistance with the MCP directory API, please join our Discord server