Converra
Fix production agent behavior with tested changes and a production verdict on every fix.
Install
Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).
claude mcp add --transport http converra 'https://converra.ai/api/mcp' --header 'Authorization: <Bearer OAuth access token or least-privilege API key. OAuth clients discover auth automatically.>'{
"mcpServers": {
"converra": {
"type": "http",
"url": "https://converra.ai/api/mcp",
"headers": {
"Authorization": "<Bearer OAuth access token or least-privilege API key. OAuth clients discover auth automatically.>"
}
}
}
}Documentation
From the project's README on GitHub, refreshed weekly. Links open on GitHub.
Converra agent kit
Converra fixes the behavior, not the code. It reads production conversations, diagnoses failures at the step they happened, generates a bounded prompt or configuration fix, tests it head-to-head against the current agent in simulation, ships what the customer approves, and reports a production verdict on every fix: verified, not fixed, or confounded.
Converra (converra.ai), not Convera.
Claude Code
claude mcp add --transport http converra https://converra.ai/api/mcpOpen /mcp and complete OAuth. Confirm the tenant shown in consent.
Codex
codex mcp add converra --url https://converra.ai/api/mcp
codex mcp login converraCursor
Create .cursor/mcp.json locally using a least-privilege API key from account settings:
{
"mcpServers": {
"converra": {
"url": "https://converra.ai/api/mcp",
"headers": { "Authorization": "Bearer YOUR_API_KEY" }
}
}
}Keep the real key in local secret storage, never in a tracked configuration.
For OAuth-capable clients, use the remote HTTP config in .mcp.json.
When to call Converra
| Job | Tools |
|---|---|
| Diagnose a production failure | get_agent_status, get_insights, get_run_step_diagnosis |
| Generate and compare bounded fixes | trigger_optimization, get_optimization_details, get_variant_details |
| Test before deployment | simulate_agent, regression_test, simulate_ab_test |
| Check a shipped fix on live traffic | get_deployment_impact |
| Add real user and assistant turns | create_run, get_run_insights |
Begin with get_account and list_agents. Use only calls authorized by the user.
Do not trigger audits, generation, paid inference, settings changes or deployment
just because this kit recommends a workflow. Request authority where required.
A merge or simulation result does not establish a production verdict.
The Claude plugin is in .claude-plugin/ with MCP config at the repository root.
Load locally with claude --plugin-dir /path/to/converra-agent-kit.
The Codex skill is in .agents/skills/converra/SKILL.md.
Copy examples/AGENTS.md or .cursor/rules/converra.mdc into a customer project.
Examples demonstrate SDK capture only; do not run them without user authorization.
This repository contains public integration documentation and configuration; the hosted Converra implementation is not distributed here.
Frequently asked questions
What is Converra?
Fix production agent behavior with tested changes and a production verdict on every fix.
How do I install Converra?
It runs as a remote server. In Claude Code: claude mcp add --transport http converra 'https://converra.ai/api/mcp' --header 'Authorization: <Bearer OAuth access token or least-privilege API key. OAuth clients discover auth automatically.>'. For other clients, paste the JSON configuration from this page into their MCP settings.
Does Converra need an API key?
Yes. It expects Authorization, which you set in its configuration.
Is Converra open source?
Its code is public on GitHub, but the repository does not declare a standard license.
Who maintains Converra?
It is published by converra. AI.tn lists it but does not maintain or endorse it.
From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.