Converra — Cursor app

Fix production agent behavior with tested changes and a production verdict on every fix. Converra fixes the behavior, not the code. It reads production conversations, diagnoses fai

Converra

Fix production agent behavior with tested changes and a production verdict on every fix. 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. Remote endpoint: https://converra.ai/api/mcp Transport: Streamable HTTP Authentication: OAuth for interactive clients; Authorization: Bearer API_KEY for unattended clients. Confirm the tenant during OAuth and use a least-privilege API key. Docs: https://converra.ai/docs/mcp/coding-agents Repository: https://github.com/converra/converra-agent-kit Install Claude Code: claude mcp add --transport http converra https://converra.ai/api/mcp; then /mcp for OAuth. Install Codex: codex mcp add converra --url https://converra.ai/api/mcp; codex mcp login converra. Cursor .cursor/mcp.json: {"mcpServers":{"converra":{"url":"https://converra.ai/api/mcp","headers":{"Authorization":"Bearer YOUR_API_KEY"}}}}. Keep real keys out of tracked files. Tools: `list_agents`, `create_agent`, `update_agent`, `get_agent_status`, `trigger_optimization`, `get_optimization_details`, `list_optimizations`, `get_variant_details`, `apply_variant`, `stop_optimization`, `get_insights`, `get_run_insights`, `regenerate_run_insights`, `batch_regenerate_insights`, `refresh_agent_analysis`, `refresh_agent_insights`, `list_runs`, `get_run`, `create_run`, `list_personas`, `create_persona`, `simulate_agent`, `analyze_agent`, `simulate_ab_test`, `regression_test`, `get_account`, `get_settings`, `update_settings`, `list_integrations`, `sync_runs`, `list_webhooks`, `create_webhook`, `delete_webhook`, `get_integration_guide`, `verify_integration`, `get_deployment_impact`, `get_run_step_diagnosis`, `get_step_failure_aggregation`, `get_regression_suite` Tool availability and permission depend on account and key scope. This catalog is public documentation, not a live audit of tools.

Store

cursor

Publisher

Not reported

First observed

2026-10-14T21:09:04+00:00

Open the interactive profile to explore rank history, metrics, tools and listing versions.

Data as of 2026-10-14T21:09:04+00:00.

OpenApps records store listings and observed changes. Store ranks are not download counts; launch dates may be derived or use the first observation. Coverage gaps are shown in the interactive catalog.

REST API specification · Guide for AI clients · Manage API keys and MCP connections · Pricing · Privacy policy · Terms of service · Support