Airframe MCP Client
OfficialEnables AI agents to discover practitioners with specific product expertise, such as Figma users, via Airframe's expert network.
Enables AI agents to search, retrieve details, and compare HubSpot with other products using Airframe's product intelligence.
Enables AI agents to search, retrieve details, and compare Salesforce with other products using Airframe's product intelligence.
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., "@Airframe MCP ClientCompare Salesforce vs HubSpot"
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.
Airframe MCP Client
Connect AI agents to Airframe's product intelligence and expert network using the Model Context Protocol (MCP).
Features
Product Search: Find software products by keyword, category, or department
Product Details: Deep dive into specific products with comprehensive data
Product Comparison: Side-by-side comparison of 2-5 products
Category Browser: Explore Airframe's software category taxonomy
Expert Network: Discover practitioners with specific product expertise
AI Intelligence: Ask complex questions powered by Airframe's market research
Related MCP server: Exa MCP Server
Prerequisites
Node.js 18+ (includes native fetch support)
MCP-compatible AI agent (Claude Desktop, Claude Code, etc.)
Airframe API key (get one at airframe.ai/account/api-keys)
Installation
Option 1: Using npx (Recommended)
No installation needed! Configure your MCP client to use npx.
For example, in your MCP configuration:
{
"mcpServers": {
"airframe": {
"command": "npx",
"args": [
"-y",
"@airframe/mcp-client",
"--api-key",
"YOUR_API_KEY_HERE"
]
}
}
}Option 2: Global Installation
npm install -g @airframe/mcp-clientThen configure Claude Desktop:
{
"mcpServers": {
"airframe": {
"command": "airframe-mcp",
"args": ["--api-key", "YOUR_API_KEY_HERE"]
}
}
}Option 3: Standalone Script
Download the bundled script from the releases page and run directly with Node:
{
"mcpServers": {
"airframe": {
"command": "node",
"args": [
"/path/to/airframe-mcp-client.js",
"--api-key",
"YOUR_API_KEY_HERE"
]
}
}
}Configuration Options
--api-key: Your Airframe API key (required, starts withaf_)--server-url: MCP server URL (optional, defaults tohttps://mcp.airframe.ai/mcp)
Usage
After configuring Claude Desktop, restart the application. You can then use Airframe tools in your conversations:
> Search for CRM products and show me the top 3
> Compare Salesforce vs HubSpot
> Find experts who use Figma
> What are the best project management tools for remote teams?Available Tools
search_products- Find software products by keyword, category, or departmentget_product_details- Deep dive on a specific product (use its slug)compare_products- Side-by-side comparison of 2-5 productsbrowse_categories- Explore Airframe's software category taxonomyfind_experts- Discover practitioners with specific product expertiseask_airframe- AI-powered market intelligence for complex questions
Troubleshooting
Check Node Version
node --version # Should be 18 or higherView Claude Desktop Logs
macOS: ~/Library/Logs/Claude/mcp-server-airframe.log
Windows: %LOCALAPPDATA%\Claude\Logs\mcp-server-airframe.log
Test the Client Manually
# Using npx
npx -y @airframeai/mcp-client --api-key YOUR_API_KEY --help
# Or after global install
airframe-mcp --api-key YOUR_API_KEY --helpCommon Issues
"Command not found": Make sure Node.js 18+ is installed and in your PATH
"Invalid API key": Verify your API key starts with af_ and is active at airframe.ai/account/api-keys
Windows npx issues: On Windows, you may need to use cmd wrapper:
{
"command": "cmd",
"args": ["/c", "npx", "-y", "@airframe/mcp-client", "--api-key", "YOUR_API_KEY"]
}Development
# Install dependencies
npm install
# Build TypeScript
npm run build
# Create standalone bundle
npm run bundleSupport
Email: support@airframe.ai
License
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- 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/airframeai/mcp-client'
If you have feedback or need assistance with the MCP directory API, please join our Discord server