Skip to content

MCP Integration

Connect Converra to your AI coding assistant in 30 seconds.

Quick Install

Choose your platform:

bash
claude mcp add converra https://converra.ai/api/mcp --header "Authorization: Bearer YOUR_API_KEY"
json
// Add to .cursor/mcp.json
{
  "mcpServers": {
    "converra": {
      "url": "https://converra.ai/api/mcp",
      "headers": { "Authorization": "Bearer YOUR_API_KEY" }
    }
  }
}
json
// Add to ~/.gemini/antigravity/mcp_config.json
{
  "mcpServers": {
    "converra": {
      "url": "https://converra.ai/api/mcp",
      "headers": { "Authorization": "Bearer YOUR_API_KEY" }
    }
  }
}
json
// Add to claude_desktop_config.json
{
  "mcpServers": {
    "converra": {
      "url": "https://converra.ai/api/mcp",
      "headers": { "Authorization": "Bearer YOUR_API_KEY" }
    }
  }
}
json
{
  "mcpServers": {
    "converra": {
      "serverType": "sse",
      "url": "https://converra.ai/api/mcp",
      "headers": { "Authorization": "Bearer YOUR_API_KEY" }
    }
  }
}

Get your API key: converra.ai/settings

One-Click Install (Cursor)

Add to Cursor

After clicking, replace YOUR_API_KEY in Cursor settings with your actual key from converra.ai/settings.

What Can You Do?

After setup, just talk to your AI naturally:

Just SayWhat Happens
"Here's my prompt, it's not working well"Uploads to Converra and analyzes issues
"What's wrong with this prompt?"Identifies weaknesses and improvement areas
"Test this against difficult users"Runs optimization with simulated conversations
"How's the optimization going?"Shows progress, variants being tested, early results
"What changed in the winning version?"Explains the differences and improvements
"Apply it"Deploys the optimized version
"Show me how my prompts are performing"Displays metrics across all your prompts

Quick Example

Here's a real conversation - bringing your existing prompt to Converra:

You: Here's the prompt I use for my support bot. It's not working well -
     customers keep getting confused.
     [pastes existing prompt]

AI: I've uploaded your prompt to Converra. Looking at it, I see a few issues -
    it's too vague about when to escalate, and doesn't handle frustrated users well.

    Want me to run an optimization to find better versions?

You: Yes, test it against difficult customers

AI: Started optimization. I'm simulating conversations with frustrated users,
    confused customers, and edge cases...

    Results are in! Variant B improved task completion by 23% - it adds
    clarifying questions before responding. Want me to apply it?

You: What exactly changed?

AI: The main change: instead of jumping to solutions, Variant B asks 1-2
    clarifying questions first. This reduced misunderstandings from 34% to 11%.

You: Apply it

AI: Done! Your prompt is now updated with the improved version.

Try These Prompts

Copy any of these to get started:

"Here's my prompt - can you analyze what's wrong with it?" [paste your prompt]

"This prompt gets confused when users ask follow-up questions" [paste your prompt]

"Test my prompt against frustrated and impatient users"

"Here are some conversation logs - what's going wrong?" [paste your logs]

"Show me how my prompts are performing"

Next Steps