Skip to content
Agents tracked: 502 Releases (7d): 762 Agent status: no reported issuesSince last limit reset: Claude 11d · Codex 9d For AI agents: Markdown Updated Nov 22, 2026

Measure

by measure-sh

debug mobile app crashes from your coding assistant.

OtherOfficialRemote

GitHubWebsite

1. Made by

“&mcpsdk.Implementation{Name: "Measure", Version: "1.0.0"},”

The server code is in the vendor's own repository (measure-sh/measure, backend/agent), the docs on measure.sh describe it, and the endpoint is agent.measure.sh on the vendor's domain.

github.com/measure-sh/measure/blob/3141abe428514e943d980cc8350097c9a7c2b526/backend/agent/mcp/mcp.go

Checked against its repository at one commit, on Nov 10, 2026. Tap a verdict to see its source.How we checkedReport an error

What Measure does

Measure records crashes, errors, slow screens and user sessions from your Android, iOS, Flutter or React Native app. Its MCP server lets a coding assistant such as Claude Code, Codex or Cursor look that data up while it fixes your code.

What people use it for

Fix a crash with its stack trace

Ask your assistant for the top crash of the latest version. It reads the error and its stack trace, then opens the right file in your project.

Which phones a bug hits

Find out whether a crash happens on one OS version, device model or country, so you can test on the right phone.

Ask about app health in plain words

Ask questions like how many sessions had slow launches yesterday, and get an answer with numbers. Measure's own agent works it out from your data.

Find where sign-ups drop off

For a sign-up or checkout flow, see which errors, slow requests or network calls users met between two steps before they gave up.

Slow or failing server calls

List the server addresses your app calls that are slowest or fail most, then compare a version before and after your fix.

Close bug reports after a fix

Users send bug reports by shaking the phone. Once the fix ships, the assistant marks those reports as closed.

Measure popularity

1,447
GitHub stars, measure-sh/measure
0
public agent projects connect it
Measure: GitHub starsmeasure-sh/measure 1,447

Tools it gives your agent (63)

What it sends and its license

Sends

crash details, stack traces, sessions, device and network data the tools return

To your coding assistant and the company running its model; on every tool call. Opt out: none for the tools; keep personal data out of what the app records.

Sends

the question and the app data Measure Agent reads to answer it

To a language model; on self-hosted copies through OpenRouter, with the models you choose; ask_question calls. Opt out: do not use ask_question; on self-hosted copies leave AGENT_ENABLED off.

Sends

a usage event per tool call (user id, tool name, duration, success)

To Measure's product analytics (PostHog); every tool call. Opt out: none stated for Measure Cloud.

Measure is open source under the Apache-2.0 license, so you can run it yourself for free, also in paid products. Measure Cloud has a free plan with the MCP server and a paid Pro plan.

In a paid app
Yes

Apache-2.0 allows commercial use, including running your own copy.

“Measure is fully open source and is available under the [Apache 2.0 license](./LICENSE)” source

Pass on its files
With conditions

Copies must carry the Apache-2.0 license and keep its notices.

“You must give any other recipients of the Work or Derivative Works a copy of this License” source

Is it alive

Latest version

1.0.0 in the registry, updated Sep 7, 2026

Last release

v0.14.0 (2026-11-05, GitHub releases; ios-v0.15.0 on 2026-11-06)

Remote endpoint
yes: an unauthenticated HEAD to https://agent.measure.sh/mcp answered HTTP 404 on 2026-11-10; the host is up, and the code routes only GET, POST and DELETE on /mcp, behind sign-in

Alternatives

Measure This page

1,447 starsRemote

io-github-tester-army-e2e

Pick it if you want the assistant to open and try live app screens, not read recorded crash data

Local

sentry

Pick it if your errors come mainly from a website or server, not a mobile app

Local

All other servers

Get started

Tell your AI assistant

“Connect the Measure MCP server (claude mcp add --transport http measure https://agent.measure.sh/mcp), find the most frequent crash in our latest Android build, show which devices it hits and the screens users visited before it, then propose a fix in our code.”

Connect it

claude mcp add --transport http measure https://agent.measure.sh/mcp

Mistakes to avoid

writing a filter_expr from guessed key names
call get_filter_keys for that kind of data first, then get_filter_values for a key's values

The keys and their operators differ per kind of data.

a follow-up ask_question such as "and on iOS?"
repeat the app ids, the earlier findings and numbers, and the answer's Method line in the new question

Each ask_question call starts fresh and remembers nothing from the last one.

asking ask_question to create a funnel or close a bug report
create_funnel, update_funnel or update_bug_report_status

The agent behind ask_question only reads data.

"url" or "httpUrl" in the Antigravity config
"serverUrl": "https://agent.measure.sh/mcp"

Antigravity reads only serverUrl for remote servers.

Questions

Does my assistant need a key?

No. On the first tool call your client opens a browser window to sign in to Measure; later calls work on their own.

Is the MCP server on the free plan?

Yes. The free plan includes the MCP server; the Pro plan adds Measure Agent, which answers plain questions.

Which assistants does it work with?

The docs show setups for Claude Code, Codex, Cursor, VS Code, Claude Desktop, Android Studio, Antigravity, Zed and opencode; any client with remote servers over streamable HTTP can connect.

Which app platforms does Measure cover?

Android, iOS and iPadOS, Kotlin Multiplatform, Flutter and React Native.