> ## Documentation Index
> Fetch the complete documentation index at: https://docs.squasher.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Set up Squasher with a coding agent

> Have an AI coding agent install Squasher in your app: copy the project prompt, install the Squasher skills and MCP server, and verify one event.

Use this page when you want an AI coding agent to install Squasher in your app. The agent maps the
runtimes in your repo, picks the matching SDK, log drain, OTLP, or Agent SDK path, and sends one
verification event.

## Copy the prompt from your project

For telemetry installation, use the prompt on the project's **Setup** page. Open **Setup → Connect**
in the target project and choose the **Coding agent** tab. It copies a project-scoped install prompt
that includes the project id, data region, and collector URL, but it does not copy an ingest key.
The prompt asks the agent to read the key from the project's existing secret store, to install the
Squasher skills and MCP tools when they are missing, and to send a test signal.

Keep `SQUASHER_API_KEY` in the project's secret store. Do not paste the key into the prompt, source
code, or logs.

## Install the Squasher skills and MCP tools

The installer command shown in the dashboard is:

```sh theme={null}
bash <(curl -fsSL https://squasher.ai/install.sh) --agents -y
```

It installs the Squasher agent skills and configures MCP for supported coding agents. See
[Agent Skills](/integrations/agent-skills) and [MCP](/integrations/mcp) for manual setup. The CLI
can also be used for project-scoped workflows; see [CLI Integration Setup](/integrations/cli-oauth).

## Agent setup brief

Use this when you are asking an AI coding agent to install Squasher:

```text theme={null}
Install Squasher for this project. If Squasher skills or MCP are not configured in this agent environment, run `bash <(curl -fsSL https://squasher.ai/install.sh) --agents -y`. Then read https://skills.squasher.ai/squasher-onboard/SKILL.md, map every runnable app/service/worker/frontend/agent in the repo, choose the matching Squasher SDK, log drain, OTLP, or Agent SDK path, initialize with SQUASHER_API_KEY and SQUASHER_PROJECT_ID from environment variables, send one real verification event, and report the files changed plus the verification step. Do not hardcode or reveal real API keys.
```

## After setup

* For live project inspection, use [MCP](/integrations/mcp).
* For terminal setup or verification, use [CLI Integration Setup](/integrations/cli-oauth).
* For custom ingestion, use the [API reference](/api-reference/introduction).
* For agent operating rules and other agent workflows, see [Squasher for AI agents](/agents).
* If the verification event does not appear, see [Troubleshooting](/troubleshooting).