mcpField
D
Discover Exceptional MCP Servers

Discover Exceptional MCP Servers

Local
github.com/johnnyclemDeveloper Tools0Updated 81w ago
Repository

About Discover Exceptional MCP Servers

MCPSvr is a community directory for discovering and sharing MCP server configurations, created as a 5ire spin-off. Its centralized registry and contribution process let MCP clients install and run listed servers.

Key features

  1. 01Browse a community server directory
  2. 02Submit server entries through GitHub pull requests
  3. 03Store configurations in a central registry
  4. 04Support interactive configuration parameters

Use cases

  1. 01Discover servers for an MCP client
  2. 02Publish a server configuration
  3. 03Specify parameters required at server setup

MCP support

The directory provides server configurations that MCP clients such as 5ire can install and run. Entries specify runtime commands, arguments, and optional environment variables.

#mcp#server#community#directory

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "souls-mcp-srv": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem"
      ]
    }
  }
}
Run commandnpx -y @modelcontextprotocol/server-filesystem

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@modelcontextprotocol/server-filesystem

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README
mcpsvr logo

Discover Exceptional MCP Servers

Chinese Version

MCPSvr is an innovative spin-off project from 5ire designed to host a community-driven directory of MCP servers. This platform empowers developers to discover exceptional tools while offering a streamlined process for sharing their own MCP server creations.

🚀 The servers here enable MCP clients like 5ire to install and run directly.

https://github.com/user-attachments/assets/3d1ec8db-2041-4f2d-b72c-eb8ae17ab31c

Contribution Guidelines

All registered MCP servers are maintained in the centralized repository located at /public/servers.json. Developers can submit new server configurations through GitHub pull requests (PRs).

Configuration Schema
{
  "name": "Server Identifier",
  "key": "Unique alphanumeric identifier",
  "description": "Concise implementation overview",
  "command": "Execution environment specifier (e.g., uvx, npx, python, node)",
  "args": [
    "Required runtime arguments"
  ],
  "env": {
    "ENVIRONMENT_VARIABLE": "Value assignment"
  },
  "homepage": "Official documentation URL"
}
Best Practices
  1. Field Organization: Maintain alphabetical ordering for configuration keys
  2. Identifier Requirements:
    • Must be a unique alphanumeric string starting with a letter
    • Strictly prohibits numeric prefixes
  3. Metadata Handling:
    • Optional name field defaults to key display value
    • Environment variables and homepage URLs are supplementary fields
User-Defined Parameters

For interactive parameter requirements, adhere to the standardized format:

{{paramName@paramType::paramDescription}}

This convention enables parameter extraction and presentation in client applications.

Example Implementation:

{
  "name": "File System Access Control",
  "key": "FileSystem",
  "command": "npx",
  "description": "Enforces directory-level operation restrictions through specified arguments",
  "args": [
    "-y",
    "@modelcontextprotocol/server-filesystem",
    "{{dirs@list::directories you about to access. Include trailing slash}}"
  ],
  "homepage": "https://github.com/modelcontextprotocol/servers"
}

Parameter Extraction:

{
  "name": "dirs",
  "type": "list",
  "description": "Directories you about to access. Include trailing slash"
}

Field Constraints:

  • paramName must be unique within the server configuration
  • Supported data types include string,list and number,make sure to use the right type!
  • Descriptive text remains optional

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.