This MCP (Model Context Protocol) server is an experimental implementation that allows AI Agents to access various standardized operations like search, browse URLs, write/execute code, and more. It integrates with Anthropic's Claude models and provides contextual information for enhanced AI interactions.
You can install and set up the MCP server using the following steps:
git clone https://github.com/username/abell-mcp.git
cd abell-mcp
npm install
.env
file in the root directory with your Anthropic API key:echo "ANTHROPIC_API_KEY=your_api_key_here" > .env
npm start
The server will start running on http://localhost:3000
by default.
The server supports various operations that can be used by AI agents. Here's how to configure and use them:
To connect to the MCP server from your application:
const MCP_URL = "http://localhost:3000";
// Example API call
async function callMCPServer(operation, params) {
const response = await fetch(`${MCP_URL}/mcp/${operation}`, {
method: "POST",
headers: {
"Content-Type": "application/json",
},
body: JSON.stringify(params),
});
return await response.json();
}
The server provides several operations that can be used by AI agents:
Perform web searches:
const searchResults = await callMCPServer("search", {
query: "latest AI research papers"
});
Browse and extract content from URLs:
const webContent = await callMCPServer("browser", {
url: "https://example.com/article"
});
Write and run code in various languages:
const codeResults = await callMCPServer("code", {
language: "python",
code: "print('Hello, World!')"
});
All MCP operations are accessible through the /mcp/:operation
endpoint, where :operation
is the name of the operation you want to perform.
curl -X POST http://localhost:3000/mcp/search \
-H "Content-Type: application/json" \
-d '{"query": "latest AI research papers"}'
{
"type": "search_results",
"results": [
{
"title": "Recent Advances in AI Research",
"url": "https://example.com/ai-research",
"snippet": "A comprehensive overview of the latest developments in AI..."
},
// Additional results...
]
}
If you encounter issues with the MCP server:
.env
fileFor rate limiting issues, consider implementing backoff strategies in your client application.
To add this MCP server to Claude Code, run this command in your terminal:
claude mcp add-json "abell-mcp" '{"command":"npx","args":["-y","abell-mcp"]}'
See the official Claude Code MCP documentation for more details.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"abell-mcp": {
"command": "npx",
"args": [
"-y",
"abell-mcp"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.
To add this MCP server to Claude Desktop:
1. Find your configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json
%APPDATA%\Claude\claude_desktop_config.json
~/.config/Claude/claude_desktop_config.json
2. Add this to your configuration file:
{
"mcpServers": {
"abell-mcp": {
"command": "npx",
"args": [
"-y",
"abell-mcp"
]
}
}
}
3. Restart Claude Desktop for the changes to take effect