# Stacktrace

> Stacktrace sees what your agents are doing, controls what they are allowed to do and intervenes when behavior drifts from intent.

Stacktrace reads the session files AI coding agents write and checks each session against detection rules. Findings go to a local console, to Slack and into the running Claude Code session. It supports Claude Code today, in local and cloud sessions. Devin and Codex are in preview.

## See

Know what actually ran. See each tool call your agents make, what came back, and which skill, MCP server, plugin or hook made it.

Stacktrace knows a component wherever it runs. When one causes trouble, you see every other environment and agent that uses it.

## Control

Set the limits ahead of time. One policy for every agent allows or blocks MCP servers, plugins and skills. Write it once and enforce it across local and remote agents. Requiring approval before a consequential action is coming soon.

## Intervene

Real-time alerts. A finding reaches Slack or Claude Code while the agent is still running, with the evidence and the fix. Steering a running agent is coming soon.

## Stacktrace Personal Agent Gateway

For the personal agents your customers bring. Stacktrace Personal Agent Gateway sits in front of a company's MCP server for the personal agents its customers arrive with: identity grading, consent, scopes, confirm-before-perform, and a masked session record. Details: https://stacktrace.ai/gateway/

## Privacy

Sessions are analyzed in your environment. Transcripts never go to a Team fleet. Data handling: https://stacktrace.ai/privacy/#cli

## Start with your next session

To install Stacktrace locally, paste this prompt into Claude Code:

> Read https://stacktrace.ai/setup/individual.md and follow it to set up Stacktrace in this environment.

To connect a team, sign up at https://app.stacktrace.ai.

## Pages

- [Stacktrace Fleet](https://stacktrace.ai/fleet/) ([Markdown](https://stacktrace.ai/fleet.md)): See and stop what coding agents do, in every environment.
- [Personal Agent Gateway](https://stacktrace.ai/gateway/) ([Markdown](https://stacktrace.ai/gateway.md)): Protect your product from the personal agents your customers bring. Verify each one; hold risky actions for the customer.
- [Stacktrace Playground](https://stacktrace.ai/playground/): Developers judge agents on real tasks. Their calls train every Stacktrace product.
- [In-browser sandbox](https://stacktrace.ai/try-now/): check a Claude Code session in your browser. Nothing is uploaded.
- [Pricing](https://stacktrace.ai/pricing/) ([Markdown](https://stacktrace.ai/pricing.md))
- [About](https://stacktrace.ai/about/) ([Markdown](https://stacktrace.ai/about.md))
- [llms.txt](https://stacktrace.ai/llms.txt) and [llms-full.txt](https://stacktrace.ai/llms-full.txt)