Converra

io.github.converraPublished by GitHub account converrav1.0.0Updated Oct 24, 2026

Fix production agent behavior with tested changes and a production verdict on every fix.

VerifiedStreamable HTTPWeb executableData & AnalyticsAI & ML

Overview

AI-generated overview

Converra is a hosted MCP server that lets an assistant diagnose production AI agent failures, generate bounded fixes, test them in simulation, and check a post-

What you can do
Inspect account and agent status, and list agents to start a session. Diagnose production failures with insights and step-level run diagnosis. Generate and compare bounded prompt or configuration fixes, with optimization and variant details. Test changes before deployment through simulation, regression tests and simulated A/B tests. Check a shipped fix on live traffic with deployment impact. Add real user and assistant turns and review run insights.
When to use it
Useful when you operate a production AI agent and want an assistant to trace failures to the step where they happened, propose bounded fixes, compare them against the current agent in simulation, and report whether a shipped fix was verified, not fixed, or confounded.
Requirements
A remote streamable HTTP endpoint at converra.ai; no local package. Authentication is required via OAuth (clients discover it automatically) or a least-privilege API key sent as an Authorization bearer header. A Converra account and tenant are needed, and the tenant shown in consent should be confirmed.
Before you install
The Authorization header carries a secret OAuth token or API key; keep the real key in local secret storage, never in a tracked configuration. Some calls trigger audits, generation, paid inference, settings changes or deployment, so they should only run with the user's authority. A merge or simulation result does not establish a production verdict. Calls add and read production conversation data.

Installation

In SourceWeft

  1. Open Converra in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.converra%2Fconverra/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "converra": {
      "type": "http",
      "url": "https://converra.ai/api/mcp"
    }
  }
}

README

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

bash
claude mcp add --transport http converra https://converra.ai/api/mcp

Open /mcp and complete OAuth. Confirm the tenant shown in consent.

Codex

bash
codex mcp add converra --url https://converra.ai/api/mcpcodex mcp login converra

Cursor

Create .cursor/mcp.json locally using a least-privilege API key from account settings:

json
{  "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

JobTools
Diagnose a production failureget_agent_status, get_insights, get_run_step_diagnosis
Generate and compare bounded fixestrigger_optimization, get_optimization_details, get_variant_details
Test before deploymentsimulate_agent, regression_test, simulate_ab_test
Check a shipped fix on live trafficget_deployment_impact
Add real user and assistant turnscreate_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.

Source: README.md at commit 734f032

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v1.0.0LatestOct 14, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.