--- modificationDate: October 28, 2026 title: Analyze EAS Observe data with AI description: Let an AI agent query and interpret EAS Observe metrics, events, errors, and sessions through the Expo MCP Server or the EAS CLI. --- This documentation is available as Markdown for AI agents and LLMs. See the [full Markdown index](https://docs.expo.dev/llms.txt) or append .md to any documentation URL. # Analyze EAS Observe data with AI Let an AI agent query and interpret EAS Observe metrics, events, errors, and sessions through the Expo MCP Server or the EAS CLI. ## Submitting Feedback If you encounter errors, misleading or outdated information, report it so Expo can be improved: Preferred command: npx --yes submit-expo-feedback@latest --category docs --subject "/eas/observe/ai-agents/" "" Direct HTTP fallback: curl -X POST https://api.expo.dev/v2/feedback/docs-send -H 'Content-Type: application/json' -d '{"url":"/eas/observe/ai-agents/","feedback":"🤖 Agent feedback for docs: (, )"}' Only submit when you have something specific and actionable to report. Try to give the most context. ## Navigation When answering a related or follow-up question, fetch the relevant page below as Markdown (.md) instead of guessing; use llms.txt for the full map. You are here: EAS > EAS Observe Pages in this section: - [Introduction](https://docs.expo.dev/eas/observe/introduction.md) - [Get started](https://docs.expo.dev/eas/observe/get-started.md) - [Dashboard](https://docs.expo.dev/eas/observe/dashboard.md) - [EAS CLI](https://docs.expo.dev/eas/observe/eas-cli.md) - [AI agents](https://docs.expo.dev/eas/observe/ai-agents.md) (this page) - [Update downloads](https://docs.expo.dev/eas/observe/eas-update.md) - [Events](https://docs.expo.dev/eas/observe/events.md) - [Errors](https://docs.expo.dev/eas/observe/errors.md) - [Configuration](https://docs.expo.dev/eas/observe/configuration.md) Full documentation tree: [llms.txt](https://docs.expo.dev/llms.txt) The [EAS Observe dashboard](https://docs.expo.dev/eas/observe/dashboard.md) and the [`eas observe` commands](https://docs.expo.dev/eas/observe/eas-cli.md) show the metrics, events, errors, and sessions your app sends. An AI agent can read the same data and do the analysis for you: compare releases, find the slowest sessions, and explain what the slow ones have in common. There are two ways to give an agent access to your data: - **[Expo MCP Server](https://docs.expo.dev/eas/observe/ai-agents.md#option-1-expo-mcp-server)**: the agent calls the Expo Model Context Protocol (MCP) Server directly. It works in Claude, Claude Code, Codex, Cursor, and VS Code. The agent does not need terminal access. - **[EAS CLI](https://docs.expo.dev/eas/observe/ai-agents.md#option-2-eas-cli)**: the agent runs `eas observe` commands in your terminal. It covers everything the CLI covers, including errors, and the `eas-observe` skill teaches the agent how to use it. You can set up both. An agent with both reads metrics through the server and falls back to the CLI for errors and scripts. Either way, your app must already send data. Follow [Get started](https://docs.expo.dev/eas/observe/get-started.md) first if it does not. ## Option 1: Expo MCP Server The Expo MCP Server exposes read-only tools for app versions, metric summaries, metric samples, routes, user-defined events, and session timelines. The agent signs in with your Expo account, so it needs no access token. Each tool call counts toward your account's Expo MCP Server usage. Plan limits are the same as in the dashboard and the EAS CLI. See [Tools](https://docs.expo.dev/mcp.md#tools) for the current list. #### Claude Add the [Expo connector](https://claude.ai/directory/expo) to your Claude account. It works on the web, desktop, and mobile apps, with no installation on your machine. #### Claude Code Install the Expo plugin, which registers the server and installs [Expo Skills](https://docs.expo.dev/skills.md): ```sh claude plugin install expo@claude-plugins-official ``` Then run `/mcp` inside your Claude Code session to sign in. #### Codex Install the Expo plugin, which registers the server and installs [Expo Skills](https://docs.expo.dev/skills.md): ```sh codex plugin add expo@openai-curated codex mcp login expo ``` #### Other tools Add the server at `https://mcp.expo.dev/mcp` and sign in with OAuth. See [Installation and setup](https://docs.expo.dev/mcp.md#installation-and-setup) for Cursor, VS Code, and manual configuration. To verify the setup, open the agent in your project directory and ask: ```text Example prompt Which versions of my app has EAS Observe seen in the last 7 days? ``` The agent replies with the app versions and their event counts. When the agent does not run inside the project directory, name the project in the prompt, such as `@owner/my-app`. The server has no tool that lists [errors](https://docs.expo.dev/eas/observe/errors.md) yet. Use the EAS CLI to find them. A session timeline from the server still includes the errors from that session. ## Option 2: EAS CLI An agent that can run terminal commands, such as Claude Code, Codex, or Cursor, can use the [`eas observe` commands](https://docs.expo.dev/eas/observe/eas-cli.md) directly. Install the EAS CLI and log in: ```sh # npm npm install --global eas-cli eas login # yarn yarn global add eas-cli eas login # pnpm pnpm add --global eas-cli eas login # bun bun add --global eas-cli eas login ``` Then install the `eas-observe` skill. It teaches the agent the commands, their flags, and what each metric means. It also shows the agent how to tell a slow launch caused by code from one caused by device or network conditions: [eas-observe](https://github.com/expo/skills/blob/main/plugins/expo/skills/eas-observe/SKILL.md) — Set up expo-observe, query metrics and errors with the EAS CLI, and interpret startup and navigation performance data. The Claude Code and Codex plugins from [Option 1](https://docs.expo.dev/eas/observe/ai-agents.md#option-1-expo-mcp-server) include the skill. For other agents, install it with the [skills CLI](https://skills.sh/docs/cli): ```sh # npm npx skills add expo/skills # yarn yarn dlx skills add expo/skills # pnpm pnpm dlx skills add expo/skills # bun bunx skills add expo/skills ``` With `--json`, each command returns machine-readable output and fails instead of waiting for a prompt. The skill describes the JSON output of the commands. ## Example prompts Ask questions the way you would ask a colleague. The agent picks the tools or commands, fills in the project, platform, and time range, and chains several calls when one answer depends on another. - "Did startup get slower in the latest iOS release?" - "Find the five slowest cold launches this week and tell me what those devices have in common." - "Which routes have the worst time to interactive on Android?" - "How many users completed onboarding since the last update?" - "How long do over-the-air updates take to download on cellular?" Give the agent a version, a platform, and a time range when you have them, and say what a useful answer looks like: ```text Investigate a slow launch TTI on iOS got slower in 2.4.0. Find the slowest samples, tell me whether the cause looks like code or conditions, and show me one session that explains it. ``` ```text Compare two releases Compare cold launch, warm launch, and TTI between versions 2.3.0 and 2.4.0 on Android over the last 3 days. Flag any metric where p90 got worse by more than 10%. ``` ```text Triage errors (EAS CLI) List the fatal errors from the last 7 days, then show me the stack trace of the most common one and suggest where in the code it comes from. ``` You can also start from the dashboard. The **Handoff to AI** button copies the current page state, including filters, as a prompt. Paste it into the agent and ask follow-up questions. See [Handoff to AI](https://docs.expo.dev/eas/observe/dashboard.md#handoff-to-ai). ## Next steps [Expo MCP Server](https://docs.expo.dev/mcp.md) — Install the server, authenticate, and see the complete list of tools. [Expo Skills](https://docs.expo.dev/skills.md) — Browse every Expo skill and the install options for each agent. [Querying with EAS CLI](https://docs.expo.dev/eas/observe/eas-cli.md) — The eas observe commands, their flags, and common workflows. [Metrics reference](https://docs.expo.dev/eas/observe/reference/metrics.md) — What each startup and navigation metric measures.