Your agents hit walls. Now you’ll hear why.

Collect the bugs, missing features, and confusing docs that block agents using your API, MCP server, or CLI, and hear from the people in your web app too. Read it all in one inbox, or hand it to your coding agent.
Create a free inbox
Free to start. Works with your existing tools.
The Agentback inbox: reports from agents, each with a status dot, its category, source and agent.
One report open: its status control, the agent’s message, what it was trying to do, and its agent, model, account and request ID.

More than “something broke.”

Written by the agent
What it was trying to do, what it expected and what happened instead, the tool involved, whether it was blocked, worked around it or got there with friction, what would have helped, and its name and model.
Added by your integration
Where it came from, your product’s version and, if you choose, a verified account.
Forwarded from your backend
The failed request too.

A small setup. A much clearer picture.

Connect once. Hear what is getting in the way. Decide what comes next.
  1. Connect your product

    Create a project and add the agentback package, or let your coding agent do the setup from one prompt.
    Your project's addresshttps://agentback.app/f/af_9c2e...
  2. Agents speak up when blocked

    A blocked agent sends what went wrong and what it was trying to do.
    json
    {
    "message": "PDF links return 415",
    "category": "docs"
    }
  3. You triage in one inbox

    Each report arrives sorted. Move it from new to resolved, or let your coding agent do it.
    New
    In progress
    Resolved

Four ways in. A few lines each.

Pick the surface agents or people already use. The agentback package tells agents when to report, gives people a feedback panel, and your backend can forward reports with the secret key to attach the account and request context.
A send_feedback tool next to yours.
typescript
import { Agentback } from 'agentback';
import { attachToMcp } from 'agentback/mcp';
​
const agentback = new Agentback({ projectKey: 'af_...' });
​
// Adds a send_feedback tool next to your own tools.
attachToMcp(server, agentback, { product: 'Search1API' });
Read the MCP server guide
Or paste one prompt into your coding agent and let it do the setup.

Then hand the inbox to your coding agent.

Agentback is an MCP server too. Add it to your coding agent and ask it to sum up the week, find the tools reported most, or fix what blocked agents and mark it resolved.
Claude Code — bash
claude mcp add \
--transport http agentback \
https://mcp.agentback.app/mcp
# Then /mcp → agentback → Authenticate, and sign in.
Sign in, no token
Claude Code, Cursor, VS Code, Codex or any MCP client with OAuth. Add the URL, sign in to Agentback in the browser and allow it.
It triages, and nothing else
It reads reports and changes their status, in every project. It cannot touch projects, keys or settings, and revoking it takes effect on its next request.
Report text stays data
Reports come from the public, so Agentback tells your agent to quote them and never to follow instructions in them.
Read the inbox guide
Go through this week’s blocked reports and fix what you can.
Completelist_reportsagentbackoutcome: blocked0.4s
12 blocked reports this week. 7 say quoted queries to search return zero results, and 3 ask for a published date. I fixed the quote handling in the query parser and added a test.
Completeeditsrc/search/parse.ts+14-3
Completebashnpm test6.1s
Completeupdate_report_statusagentback7 reports → resolved0.3s
The 7 search reports are resolved. The date requests need a product decision, so I left them new.

Built for feedback. Easy to make yours.

A few lines, or none

The agentback package adds a feedback tool to your MCP server or a feedback command to your CLI. Anything else sends one HTTP POST from any language.

Secrets stay on your server

The project key can only submit reports, so it ships safely inside MCP servers and CLIs. The secret key stays on your backend and never reaches a prompt.

Scoped and rate limited

Every report is validated, size-limited, redacted, and rate limited per project. Nothing is logged raw.

Start free. Talk to us when you need more.

Free

$0Everything you need to hear from your agents and users.
  • One project
  • MCP server, CLI, HTTP API and web app
  • An inbox for each project, with statuses
  • Triage by your coding agent over MCP
  • Instant, daily and weekly report emails
  • Verified accounts on reports
  • Setup by your coding agent

Enterprise

CustomTell us what you need and we’ll set up a plan that fits.
  • More projects
  • Self-hosted deployment
  • Help with your integration

Give your product an ear.

Free to start. Create a project, hand the setup to your coding agent, and start reading what your agents have been trying to tell you.Create a free inbox