MCP Server Cards
Generates, validates, and discovers standardized MCP server cards for automatic agent discovery.
README
MCP Server Cards
An MCP server for generating, validating, and discovering MCP server cards — a standardized way to describe MCP servers so AI agents can automatically find and understand them.
What are Server Cards?
Server Cards are machine-readable JSON files that describe an MCP server's capabilities, similar to how robots.txt describes crawling rules or manifest.json describes web apps. They live at .well-known/mcp-server-card.json and contain:
- Name & Description — What the server does
- Tools — List of available tools with descriptions
- Author & Repository — Who built it, where to find the source
- Categories — Tags for discovery and search
- Pricing — Whether it's free, freemium, or paid
- Transport — Whether it uses stdio, HTTP, or both
- Auth — Whether authentication is required
Why Server Cards?
As the MCP ecosystem grows, agents need a way to discover and evaluate servers automatically. Server Cards solve this by providing:
- Automatic Discovery — Agents can check
.well-known/mcp-server-card.jsonon any domain - Standardized Metadata — Consistent format for comparing servers
- Capability Description — Agents know what tools are available before connecting
- Trust Signals — Author, repository, and pricing information
Installation
pip install agent-server-card-mcp
Usage
As MCP Server
{
"mcpServers": {
"server-cards": {
"command": "server-card-server"
}
}
}
With uvx
{
"mcpServers": {
"server-cards": {
"command": "uvx",
"args": ["agent-server-card-mcp"]
}
}
}
Available Tools
| Tool | Description |
|---|---|
generate_card |
Generate a .well-known/mcp-server-card.json for any MCP server |
validate_card |
Validate a server card against the JSON schema |
discover |
Try to discover a server card from a URL via .well-known |
search |
Search indexed server cards by keyword |
register |
Register a server card in the local index |
schema |
Get the full JSON schema for server cards |
Server Card Example
{
"name": "weather-mcp-server",
"description": "Provides real-time weather data and forecasts",
"version": "1.0.0",
"author": "WeatherCorp",
"repository": "https://github.com/example/weather-mcp",
"tools": [
{
"name": "get_weather",
"description": "Get current weather for a location"
},
{
"name": "get_forecast",
"description": "Get 7-day weather forecast"
}
],
"categories": ["weather", "climate", "data"],
"pricing": "free",
"auth_required": false,
"transport": "stdio"
}
Server Card Schema
Required fields:
name— Unique server namedescription— What the server doesversion— Semantic versiontools— Array of{name, description}objects
Optional but recommended:
author— Author or organizationrepository— Source code URLcategories— Tags for searchabilitypricing—free|freemium|paid|open-sourceauth_required— Booleantransport—stdio|http|both
How Discovery Works
- An agent wants to find MCP servers on
example.com - It requests
https://example.com/.well-known/mcp-server-card.json - If the file exists, the agent parses it and learns about available tools
- The agent can then decide whether to connect based on the metadata
This follows the same pattern as .well-known/openid-configuration for OAuth or .well-known/ai-plugin.json for ChatGPT plugins.
More MCP Servers by AiAgentKarl
| Category | Servers |
|---|---|
| 🔗 Blockchain | Solana |
| 🌍 Data | Weather · Germany · Agriculture · Space · Aviation · EU Companies |
| 🔒 Security | Cybersecurity · Policy Gateway · Audit Trail |
| 🤖 Agent Infra | Memory · Directory · Hub · Reputation |
| 🔬 Research | Academic · LLM Benchmark · Legal |
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.