{
 "kind": "mcp",
 "slug": "sh-measure-measure",
 "path": "mcp/servers/sh-measure-measure/",
 "name": "Measure",
 "maker": "measure-sh",
 "density": "full",
 "crumbs": [
  [
   "MCP servers",
   "mcp/"
  ],
  [
   "Other",
   "mcp/other/"
  ]
 ],
 "lead": "debug mobile app crashes from your coding assistant.",
 "chips": [
  {
   "label": "Other",
   "path": "mcp/other/"
  },
  {
   "label": "Official"
  },
  {
   "label": "Remote"
  }
 ],
 "primary": {
  "label": "Copy connect command",
  "copy": "claude mcp add --transport http measure https://agent.measure.sh/mcp"
 },
 "links": [
  {
   "label": "GitHub",
   "href": "https://github.com/measure-sh/measure"
  },
  {
   "label": "Website",
   "href": "https://measure.sh/docs/mcp"
  }
 ],
 "track": "New versions and outages of the remote endpoint on your dashboard",
 "verdicts": [
  {
   "key": "official",
   "label": "Made by",
   "value": "The service itself",
   "status": "yes",
   "sub": "Official server",
   "quote": "&mcpsdk.Implementation{Name: \"Measure\", Version: \"1.0.0\"},",
   "note": "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.",
   "src": "https://github.com/measure-sh/measure/blob/3141abe428514e943d980cc8350097c9a7c2b526/backend/agent/mcp/mcp.go"
  },
  {
   "key": "secrets",
   "label": "Keys",
   "value": "No key needed",
   "status": "yes",
   "sub": "No account",
   "quote": "codex mcp add measure --url https://agent.measure.sh/mcp",
   "note": null,
   "src": "https://github.com/measure-sh/measure/blob/3141abe428514e943d980cc8350097c9a7c2b526/frontend/dashboard/content/docs/mcp.mdx"
  },
  {
   "key": "where",
   "label": "Runs",
   "value": "Remote",
   "status": "yes",
   "sub": "Nothing runs on your machine",
   "note": "Endpoint: https://agent.measure.sh/mcp. Checked: 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.",
   "src": "https://agent.measure.sh/mcp"
  },
  {
   "key": "license",
   "label": "Commercial use",
   "value": "Allowed",
   "status": "yes",
   "sub": "Apache-2.0 license",
   "quote": "Measure is fully open source and is available under the [Apache 2.0 license](./LICENSE)",
   "note": "Apache-2.0 allows commercial use, including running your own copy.",
   "src": "https://github.com/measure-sh/measure/blob/3141abe428514e943d980cc8350097c9a7c2b526/README.md"
  }
 ],
 "vfoot": "Checked against its repository at one commit, on Nov 10, 2026.",
 "blocks": [
  {
   "id": "overview",
   "nav": "Overview",
   "h2": "What Measure does",
   "parts": [
    {
     "t": "prose",
     "text": "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."
    },
    {
     "t": "h3",
     "text": "What people use it for"
    },
    {
     "t": "uses",
     "items": [
      {
       "title": "Fix a crash with its stack trace",
       "text": "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.",
       "idea": false
      },
      {
       "title": "Which phones a bug hits",
       "text": "Find out whether a crash happens on one OS version, device model or country, so you can test on the right phone.",
       "idea": false
      },
      {
       "title": "Ask about app health in plain words",
       "text": "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.",
       "idea": false
      },
      {
       "title": "Find where sign-ups drop off",
       "text": "For a sign-up or checkout flow, see which errors, slow requests or network calls users met between two steps before they gave up.",
       "idea": false
      },
      {
       "title": "Slow or failing server calls",
       "text": "List the server addresses your app calls that are slowest or fail most, then compare a version before and after your fix.",
       "idea": false
      },
      {
       "title": "Close bug reports after a fix",
       "text": "Users send bug reports by shaking the phone. Once the fix ships, the assistant marks those reports as closed.",
       "idea": false
      }
     ]
    }
   ]
  },
  {
   "id": "popularity",
   "nav": "Popularity",
   "h2": "Measure popularity",
   "parts": [
    {
     "t": "stats",
     "items": [
      {
       "n": "1,447",
       "l": "GitHub stars, measure-sh/measure"
      },
      {
       "n": "0",
       "l": "public agent projects connect it"
      }
     ]
    }
   ]
  },
  {
   "id": "tools",
   "nav": "Tools",
   "h2": "Tools it gives your agent (63)",
   "parts": [
    {
     "t": "tools",
     "items": [
      {
       "name": "ask_question",
       "text": "Asks Measure Agent a plain-language question about your app's data; it works out the answer (uses a language model)"
      },
      {
       "name": "list_apps",
       "text": "Lists the apps you can access"
      },
      {
       "name": "get_filter_keys",
       "text": "Lists the filter keys you can use for one kind of data"
      },
      {
       "name": "get_filter_values",
       "text": "Lists the values a filter key can take for an app"
      },
      {
       "name": "get_metrics",
       "text": "Reads app health numbers: adoption, crash-free sessions, launch times"
      },
      {
       "name": "get_app_health_over_time",
       "text": "Reads sessions, crashes, ANRs and app hangs over time"
      },
      {
       "name": "get_errors",
       "text": "Lists error groups (crashes, exceptions, ANRs)"
      },
      {
       "name": "get_error",
       "text": "Reads individual events of one error group"
      },
      {
       "name": "get_errors_over_time",
       "text": "Counts errors over time"
      },
      {
       "name": "get_error_over_time",
       "text": "Counts one error group over time"
      },
      {
       "name": "get_error_distribution",
       "text": "Shows which OS, device, version or country one error hits"
      },
      {
       "name": "get_error_common_path",
       "text": "Shows the usual screens users went through before an error"
      },
      {
       "name": "get_sessions",
       "text": "Lists recent user sessions"
      },
      {
       "name": "get_sessions_over_time",
       "text": "Counts sessions over time"
      },
      {
       "name": "get_session",
       "text": "Reads one full session with all its events"
      },
      {
       "name": "get_memory_usage_over_time",
       "text": "Reads memory use over time by version"
      },
      {
       "name": "get_memory_usage_by_device_tier",
       "text": "Breaks memory use down by device memory size"
      },
      {
       "name": "get_high_memory_sessions",
       "text": "Lists sessions with high memory use"
      },
      {
       "name": "get_device_sessions_over_time",
       "text": "Counts sessions over time for the top five devices"
      },
      {
       "name": "get_devices_by_sessions",
       "text": "Ranks device models by sessions"
      },
      {
       "name": "get_devices_by_errors",
       "text": "Ranks device models by errors"
      },
      {
       "name": "get_devices_by_launch_time",
       "text": "Ranks device models by app launch time"
      },
      {
       "name": "get_devices_by_span_duration",
       "text": "Ranks device models by the duration of traced work"
      },
      {
       "name": "get_devices_by_memory_usage",
       "text": "Ranks device models by memory use"
      },
      {
       "name": "get_bug_reports",
       "text": "Lists recent bug reports"
      },
      {
       "name": "get_bug_reports_over_time",
       "text": "Counts bug reports over time"
      },
      {
       "name": "get_bug_report",
       "text": "Reads one bug report in full"
      },
      {
       "name": "update_bug_report_status",
       "text": "Opens or closes a bug report (WRITE)"
      },
      {
       "name": "get_builds",
       "text": "Lists uploaded app builds"
      },
      {
       "name": "get_profiles",
       "text": "Lists captured performance profiles"
      },
      {
       "name": "get_root_span_names",
       "text": "Lists the names of traced operations"
      },
      {
       "name": "get_span_instances",
       "text": "Lists runs of one traced operation"
      },
      {
       "name": "get_span_metrics_over_time",
       "text": "Reads how long one traced operation takes over time"
      },
      {
       "name": "get_trace",
       "text": "Reads one full trace"
      },
      {
       "name": "get_alerts",
       "text": "Lists recent alerts"
      },
      {
       "name": "get_journey",
       "text": "Reads how users move between screens, as a graph"
      },
      {
       "name": "get_journey_nodes",
       "text": "Lists the screens and events in that graph"
      },
      {
       "name": "get_journey_path_users",
       "text": "Counts users who took one path"
      },
      {
       "name": "get_journey_errors",
       "text": "Lists errors users hit on a screen or path"
      },
      {
       "name": "get_journey_traces",
       "text": "Lists traced work on a screen or path"
      },
      {
       "name": "get_journey_network",
       "text": "Lists network requests on a screen or path"
      },
      {
       "name": "get_journey_sessions",
       "text": "Lists sessions that went through a screen or path"
      },
      {
       "name": "get_funnels",
       "text": "Lists the app's funnels"
      },
      {
       "name": "get_pinned_funnels",
       "text": "Lists pinned funnels in order"
      },
      {
       "name": "get_funnel",
       "text": "Reads one funnel with its steps"
      },
      {
       "name": "get_funnel_event_names",
       "text": "Lists the event names funnel steps can use"
      },
      {
       "name": "get_funnel_conversion",
       "text": "Counts users reaching each funnel step"
      },
      {
       "name": "get_funnel_trend",
       "text": "Reads funnel conversion by day, week or month"
      },
      {
       "name": "get_funnel_cadence",
       "text": "Shows funnel entries and conversions by hour of the week"
      },
      {
       "name": "get_funnel_step_errors",
       "text": "Lists errors between two funnel steps"
      },
      {
       "name": "get_funnel_step_traces",
       "text": "Lists traced work between two funnel steps"
      },
      {
       "name": "get_funnel_step_network",
       "text": "Lists network requests between two funnel steps"
      },
      {
       "name": "get_funnel_step_sessions",
       "text": "Lists sessions of users who converted or dropped off"
      },
      {
       "name": "create_funnel",
       "text": "Creates a funnel for the whole team (WRITE)"
      },
      {
       "name": "update_funnel",
       "text": "Changes a funnel for the whole team (WRITE)"
      },
      {
       "name": "delete_funnel",
       "text": "Deletes a funnel for the whole team (DELETE)"
      },
      {
       "name": "set_funnel_pinned",
       "text": "Pins or unpins a funnel (WRITE)"
      },
      {
       "name": "reorder_pinned_funnels",
       "text": "Changes the order of pinned funnels (WRITE)"
      },
      {
       "name": "get_network_metrics_trends",
       "text": "Lists the slowest, most failing and busiest network endpoints"
      },
      {
       "name": "get_network_status_codes_over_time",
       "text": "Counts 2xx to 5xx responses over time"
      },
      {
       "name": "get_network_endpoint_status_codes_over_time",
       "text": "Counts exact status codes for one endpoint over time"
      },
      {
       "name": "get_network_latency_over_time",
       "text": "Reads network latency over time"
      },
      {
       "name": "get_network_timeline",
       "text": "Reads requests per session by time since the session started"
      }
     ]
    }
   ]
  },
  {
   "id": "data",
   "nav": "Data and license",
   "h2": "What it sends and its license",
   "parts": [
    {
     "t": "rows",
     "rows": [
      {
       "l": "Sends",
       "v": "crash details, stack traces, sessions, device and network data the tools return",
       "sub": "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."
      },
      {
       "l": "Sends",
       "v": "the question and the app data Measure Agent reads to answer it",
       "sub": "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."
      },
      {
       "l": "Sends",
       "v": "a usage event per tool call (user id, tool name, duration, success)",
       "sub": "To Measure's product analytics (PostHog); every tool call. Opt out: none stated for Measure Cloud."
      }
     ]
    },
    {
     "t": "prose",
     "text": "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."
    },
    {
     "t": "rows",
     "rows": [
      {
       "l": "In a paid app",
       "v": "Yes",
       "status": "yes",
       "sub": "Apache-2.0 allows commercial use, including running your own copy.",
       "quote": "Measure is fully open source and is available under the [Apache 2.0 license](./LICENSE)",
       "src": "https://github.com/measure-sh/measure/blob/3141abe428514e943d980cc8350097c9a7c2b526/README.md"
      },
      {
       "l": "Pass on its files",
       "v": "With conditions",
       "status": "cond",
       "sub": "Copies must carry the Apache-2.0 license and keep its notices.",
       "quote": "You must give any other recipients of the Work or Derivative Works a copy of this License",
       "src": "https://github.com/measure-sh/measure/blob/3141abe428514e943d980cc8350097c9a7c2b526/LICENSE"
      }
     ]
    }
   ]
  },
  {
   "id": "alive",
   "nav": null,
   "spy_as": "data",
   "h2": "Is it alive",
   "parts": [
    {
     "t": "rows",
     "rows": [
      {
       "l": "Latest version",
       "v": "1.0.0 in the registry, updated Sep 7, 2026"
      },
      {
       "l": "Last release",
       "v": "v0.14.0 (2026-11-05, GitHub releases; ios-v0.15.0 on 2026-11-06)"
      },
      {
       "l": "Remote endpoint",
       "v": "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",
       "status": "yes"
      }
     ]
    }
   ]
  },
  {
   "id": "alternatives",
   "nav": "Alternatives",
   "h2": "Alternatives",
   "parts": [
    {
     "t": "alts",
     "items": [
      {
       "name": "Measure",
       "me": true,
       "facts": [
        "1,447 stars",
        "Remote"
       ]
      },
      {
       "name": "io-github-tester-army-e2e",
       "why": "Pick it if you want the assistant to open and try live app screens, not read recorded crash data",
       "path": null,
       "facts": [
        "Local"
       ]
      },
      {
       "name": "sentry",
       "why": "Pick it if your errors come mainly from a website or server, not a mobile app",
       "path": null,
       "facts": [
        "Local"
       ]
      }
     ],
     "more": "All other servers",
     "more_path": "mcp/other/"
    }
   ]
  },
  {
   "id": "start",
   "nav": "Get started",
   "h2": "Get started",
   "parts": [
    {
     "t": "prompt",
     "text": "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."
    },
    {
     "t": "h3",
     "text": "Connect it"
    },
    {
     "t": "tabs",
     "label": "Connect by client",
     "items": [
      {
       "tab": "Claude Code",
       "code": "claude mcp add --transport http measure https://agent.measure.sh/mcp"
      },
      {
       "tab": "Cursor",
       "code": "{\n  \"mcpServers\": {\n    \"measure\": {\n      \"url\": \"https://agent.measure.sh/mcp\"\n    }\n  }\n}\n"
      },
      {
       "tab": "Any client (JSON)",
       "code": "{\n  \"mcpServers\": {\n    \"measure\": {\n      \"url\": \"https://agent.measure.sh/mcp\"\n    }\n  }\n}"
      }
     ]
    },
    {
     "t": "h3",
     "text": "Mistakes to avoid"
    },
    {
     "t": "mistakes",
     "items": [
      {
       "dont": "writing a filter_expr from guessed key names",
       "fix": "call get_filter_keys for that kind of data first, then get_filter_values for a key's values",
       "why": "The keys and their operators differ per kind of data."
      },
      {
       "dont": "a follow-up ask_question such as \"and on iOS?\"",
       "fix": "repeat the app ids, the earlier findings and numbers, and the answer's Method line in the new question",
       "why": "Each ask_question call starts fresh and remembers nothing from the last one."
      },
      {
       "dont": "asking ask_question to create a funnel or close a bug report",
       "fix": "create_funnel, update_funnel or update_bug_report_status",
       "why": "The agent behind ask_question only reads data."
      },
      {
       "dont": "\"url\" or \"httpUrl\" in the Antigravity config",
       "fix": "\"serverUrl\": \"https://agent.measure.sh/mcp\"",
       "why": "Antigravity reads only serverUrl for remote servers."
      }
     ]
    }
   ]
  },
  {
   "id": "faq",
   "nav": "Questions",
   "h2": "Questions",
   "parts": [
    {
     "t": "faq",
     "items": [
      {
       "q": "Does my assistant need a key?",
       "a": "No. On the first tool call your client opens a browser window to sign in to Measure; later calls work on their own.",
       "evidence": {
        "url": "https://github.com/measure-sh/measure/blob/3141abe428514e943d980cc8350097c9a7c2b526/frontend/dashboard/content/docs/mcp.mdx",
        "quote": "When you first use a Measure tool, your client opens a browser window for you to sign in to Measure."
       }
      },
      {
       "q": "Is the MCP server on the free plan?",
       "a": "Yes. The free plan includes the MCP server; the Pro plan adds Measure Agent, which answers plain questions.",
       "evidence": {
        "url": "https://measure.sh/pricing",
        "quote": "Free $0 per month 5 GB of data 30 days retention MCP server No credit card needed"
       }
      },
      {
       "q": "Which assistants does it work with?",
       "a": "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.",
       "evidence": {
        "url": "https://github.com/measure-sh/measure/blob/3141abe428514e943d980cc8350097c9a7c2b526/frontend/dashboard/content/docs/mcp.mdx",
        "quote": "Any client that supports remote MCP servers over streamable HTTP can connect by pointing at `https://agent.measure.sh/mcp`."
       }
      },
      {
       "q": "Which app platforms does Measure cover?",
       "a": "Android, iOS and iPadOS, Kotlin Multiplatform, Flutter and React Native.",
       "evidence": {
        "url": "https://measure.sh/pricing",
        "quote": "Platforms Android iOS iPadOS Kotlin Multiplatform Flutter React Native"
       }
      }
     ]
    }
   ]
  }
 ],
 "glance": [
  [
   "Registry name",
   "sh.measure/measure"
  ],
  [
   "Category",
   "Other"
  ],
  [
   "Version",
   "1.0.0"
  ],
  [
   "Remote endpoint",
   "https://agent.measure.sh/mcp"
  ],
  [
   "License",
   "Apache-2.0"
  ],
  [
   "GitHub",
   "measure-sh/measure"
  ],
  [
   "In the registry since",
   "Sep 7, 2026"
  ],
  [
   "Works with",
   "Claude Code, OpenAI Codex, OpenCode, LangChain, n8n, LangGraph"
  ]
 ],
 "good": [
  "The tools only find what your app sends. Your app needs the Measure library and a Measure account, hosted or your own.",
  "On Measure Cloud the plain-question tool belongs to the Pro plan and is billed at the model provider's token price plus a markup.",
  "Changes to funnels apply to the whole team and need a role that may edit funnels. Bug report status can also be changed."
 ],
 "checked_line": "Read by AgentGid from 14 pages and files at one commit, checked Nov 10, 2026; stars update daily.",
 "logo": "https://agentgid.com/media/avatars/measure-sh.png"
}