About Converra
Converra is a hosted service documented here for diagnosing production agent failures and developing tested prompt or configuration fixes. It is for teams improving agent behavior, with simulations, regression checks, and a production verdict for each fix.
Key features
- 01Diagnose production failures by run step
- 02Generate bounded prompt or config fixes
- 03Compare changes in simulation
- 04Run regression and A/B tests
- 05Check shipped fixes against live traffic
Use cases
- 01Trace a failure in a production conversation
- 02Compare a proposed agent change with the current version
- 03Test a fix before deployment
- 04Review a shipped fix's production impact
MCP support
Provides a remote MCP server at https://converra.ai/api/mcp for coding-agent clients including Claude Code, Codex, and Cursor. Its tools cover diagnosis, optimization, simulation, testing, and deployment impact; actions require user authorization.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://converra.ai/api/mcpclaude mcp add --transport http converra-converra https://converra.ai/api/mcp{"mcpServers":{"converra-converra":{"type":"http","url":"https://converra.ai/api/mcp"}}}Open in Cursor{"servers":{"converra-converra":{"type":"http","url":"https://converra.ai/api/mcp"}}}Open in VS Code{"mcpServers":{"converra-converra":{"type":"http","url":"https://converra.ai/api/mcp"}}}{"mcpServers":{"converra-converra":{"serverUrl":"https://converra.ai/api/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
https://converra.ai/api/mcpAuth requiredTools
Details
From the project READMEConverra 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/mcp
Open /mcp and complete OAuth. Confirm the tenant shown in consent.
Codex
codex mcp add converra --url https://converra.ai/api/mcp
codex mcp login converra
Cursor
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.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.