Skip to content
Scalekit Docs
Talk to an Engineer Dashboard

Connect AI agents to the LogRocket MCP server

Vendor MCP
Open markdown

The LogRocket MCP connector routes your AI agent's tool calls to LogRocket's own MCP server through Scalekit. Each user signs in to LogRocket once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 9 tools.

Tools
9
What they doRead · write · destructive
9 · 0 · 09 read0 write0 destructive
Users sign in with
OAuth app
Scalekit's or your own

Setup

  1. Install the SDK

    Terminal window
    npm install @scalekit-sdk/node dotenv

  2. Set your credentials

    Add your Scalekit credentials to your .env file. Find values in app.scalekit.com > Developers > API Credentials.

    .env
    SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
    SCALEKIT_CLIENT_ID=<your-client-id>
    SCALEKIT_CLIENT_SECRET=<your-client-secret>

  3. Create the LogRocket MCP connection

    In AgentKit > Connections, create a LogRocket MCP connection. The name you give it is the connection_name your code passes. See Configure connections.

    Scalekit credentials are available for LogRocket MCP server, so you don't need to register an OAuth app.

  4. Authorize a user and make your first call

    quickstart.mts
    import { ScalekitClient } from '@scalekit-sdk/node'
    import 'dotenv/config'
    import { createInterface } from 'node:readline/promises'
    

    const scalekit = new ScalekitClient(
      process.env.SCALEKIT_ENVIRONMENT_URL,
      process.env.SCALEKIT_CLIENT_ID,
      process.env.SCALEKIT_CLIENT_SECRET,
    )
    const actions = scalekit.actions
    

    const connector = 'logrocketmcp'
    const identifier = 'user_123'
    

    // Generate an authorization link for the user
    const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
    console.log('Authorize LogRocket MCP:', link)
    const rl = createInterface({ input: process.stdin, output: process.stdout })
    await rl.question('Press Enter after authorizing...')
    rl.close()
    

    // Make your first call
    const result = await actions.executeTool({
      connector,
      identifier,
      toolName: 'logrocketmcp_list_organizations',
      toolInput: {},
    })
    console.log(result)
    Terminal window
    npx tsx quickstart.mts

    Each user signs in once. See Authorize a user for the full flow and statuses.

Tools

Pass the exact name to execute_tool
Try in PlaygroundRequest a tool
  • logrocketmcp_build_metricUse this to query LogRocket analytics data.Read-only

    Build Metric

    Use this to query LogRocket analytics data. This tool translates your natural language query into a LogRocket metric (e.g., timeseries, table, conversion funnel) that is then used to find relevant data. It's best used for performing aggregate analysis (e.g., session totals over time, browser or country breakdowns, conversion rates between steps). Returns an object with a `metricDefinition` field indicating the LogRocket metric that was used to find the data and a `metricQueryResult` field containing the corresponding analytics data.

    Inputs

    organizationIDstringrequired
    The organization ID to run the query against. If not provided by the user, discover options using the list_organizations tool.
    projectIDstringrequired
    The project ID to run the query against. If not provided by the user, discover options using the list_projects tool.
    querystringrequired
    Natural language query describing the analytics data you want to retrieve.
    limitinteger
    Maximum number of rows/buckets returned in metricQueryResult for top-N or table-style metrics (e.g., top countries, top pages, top users). Defaults to 20. This does not control sessionDefinitions and may be ignored for metric types that do not return ranked row buckets.
    timezonestring
    Optional IANA timezone (e.g., 'America/New_York'). Time buckets align to this timezone's calendar (e.g., daily buckets break at its midnight). When omitted, they align to UTC.
  • logrocketmcp_find_issuesUse this to list a LogRocket project's issues.Read-only

    Find Issues

    Use this to list a LogRocket project's issues. This includes error signals detected in session recordings, specifically JavaScript exceptions, network errors, rage clicks, dead clicks, frustrating network requests, error states, and mobile crash reports. Issues can be filtered by severity, triage status, issue type, and time range, and optionally refined with a natural language query. Returns an object with an `issues` field listing matching issues, each with its issue type, platform, event count, first/last seen dates, `triageStatus`, a `url` linking to the issue's detail page in the LogRocket dashboard, and an AI-generated `issueDescription` when one exists.

    Inputs

    organizationIDstringrequired
    The organization ID to run the query against. If not provided by the user, discover options using the list_organizations tool.
    projectIDstringrequired
    The project ID to run the query against. If not provided by the user, discover options using the list_projects tool.
    endDatestring
    Optional ISO 8601 datetime for the end of the time range to search. Defaults to now.
    issueTypesarray
    Optional list of issue types to include. "exception" covers JavaScript exceptions and mobile errors, "networkError" failed network requests, "mobileCrash" mobile app crash reports, "rageClick" repeated frustrated clicks, "deadClick" clicks with no visible effect, "frustratingNetworkRequest" impatient user actions during slow requests, and "errorState" error pages and modals users encounter. Defaults to all issue types.
    limitinteger
    Maximum number of issues to fetch, applied before any natural language relevance filtering. Defaults to 30.
    querystring
    Optional natural language query used to refine results (e.g., "checkout errors affecting Chrome users"). When provided, additional filters are parsed from the query and results are filtered to those relevant to it. Omit to list issues using only the structured parameters.
    severitystring
    Optional severity filter. "severe" returns only issues where LogRocket detected significant user impact and generated an issue description; "notSevere" returns only issues without one; "any" returns both. Defaults to "severe".one of severenotSevereany
    startDatestring
    Optional ISO 8601 datetime for the start of the time range to search. Defaults to a lookback of one week. Issues data is only retained for 30 days: start dates older than that are clamped to 30 days ago, and time ranges ending more than 30 days ago return no issues.
    triageStatusesarray
    Optional list of triage statuses to include. Issues start as "untriaged" and can be triaged by users to "highImpact", "lowImpact", or "ignored". Defaults to ["untriaged"], matching the default dashboard issues view.
  • logrocketmcp_find_sessionsUse this to find LogRocket sessions matching a natural language query.Read-only

    Find Sessions

    Use this to find LogRocket sessions matching a natural language query. This tool translates your natural language query into LogRocket filters that are then used to find relevant sessions. It's best used for filtering sessions based on user ID or email, custom user traits, visited page or URL, custom events, text inputs, clicked on text or CSS selector, network errors, IP address, user location (e.g., country), and/or other basic metadata, in addition to over a specific date range (e.g., last week). Returns an object with a list of relevant sessions in the `sessionDefinitions` field, each with recording ID, session ID, session URL, date of recording as a Unix timestamp in milliseconds, and other basic metadata. The returned object will also include a `metricDefinition` field indicating which LogRocket filters were used to find the sessions.

    Inputs

    organizationIDstringrequired
    The organization ID to run the query against. Should be inferred from user input if a slash-separated identifier of the form `<organizationID>/<projectID>` or a link to a LogRocket resource is provided. For example, a LogRocket session URL has the structure `https://app.logrocket.com/<organizationID>/<projectID>/s/<recordingID>/<sessionID>`. Similarly, links to other LogRocket resources (e.g., issues, metrics) will contain the organization ID as the first path segment. If not provided by the user, discover options using the list_organizations tool. If multiple organizations are found, ask the user which one(s) they want to use before proceeding.
    projectIDstringrequired
    The project ID to run the query against. Should be inferred from user input if a slash-separated identifier of the form `<organizationID>/<projectID>` or a link to a LogRocket resource is provided. For example, a LogRocket session URL has the structure `https://app.logrocket.com/<organizationID>/<projectID>/s/<recordingID>/<sessionID>`. Similarly, links to other LogRocket resources (e.g., issues, metrics) will contain the project ID as the second path segment. If not provided by the user, discover options using the list_projects tool. If multiple projects are found, ask the user which one(s) they want to use before proceeding.
    querystringrequired
    Natural language query describing the sessions you want to find.
    limitinteger
    Maximum number of sessions to return. Defaults to 10.
    userTraitsarray
    Names of custom user traits to include for each session (e.g., ["plan", "deviceId"]). Values come from the session's latest identify call, preferring identified users over anonymous ones, not the user's current traits. Names match case-insensitively; traits that identify call did not set are omitted. Returned in each session's `userTraits` field.
  • logrocketmcp_get_metricUse this to fetch the data for an existing, saved LogRocket metric (timeseries, funnel, table, retention, or session count) over a specific time range.Read-only

    Get Metric

    Use this to fetch the data for an existing, saved LogRocket metric (timeseries, funnel, table, retention, or session count) over a specific time range. Unlike build_metric, this runs the saved metric's own definition rather than generating one from a natural language query, so results are deterministic. Prefer this tool whenever the user provides a link to a saved metric. Heatmap and path analysis metrics are not supported. Returns an object with: - `metricDefinition`: the saved metric's configuration (name, type, filters, grouping, time interval, and, for funnels, the ordered steps in `funnel.steps`), with its time range replaced by the requested one. - `metricQueryResult`: the metric's data. Timeseries return `buckets` keyed by time bucket (and `fullRangeValues` or `fullRangeUniqueUsers` when values can't be summed across buckets). Funnels return `sessionCountTotal` and `funnelStepSessionCounts`, one count per step in `funnel.steps` order (users rather than sessions for cross-session funnels), or `groupedFunnelStepSessionCounts` when the funnel is grouped. Tables return ranked `buckets` with `totalBucketCount`. Retention returns `buckets` per retention interval. Session metrics return `sessionCountTotal`. - `sessionDefinitions`: when `sessionLimit` is set, a sample of sessions behind the metric, each with a `sessionURL` linking to its replay. For timeseries and session count metrics these are sessions matching the metric's filters; for funnels they are sessions in the cohort selected by `funnelStep` and `funnelSessions`. Always null for table and retention metrics, and when `sessionLimit` is omitted.

    Inputs

    endDatestringrequired
    ISO 8601 datetime for the end of the time range to query. Must be after startDate. Dates without a time or offset are interpreted as UTC.
    metricURLstringrequired
    Link to the saved metric in the LogRocket dashboard (e.g., `https://app.logrocket.com/<organizationID>/<projectID>/funnels/<metricID>` or `https://app.logrocket.com/<organizationID>/<projectID>/metrics/<dashboardID>/metric/<metricID>`). The organization and project are read from the link.
    startDatestringrequired
    ISO 8601 datetime for the start of the time range to query (e.g., "2026-10-01T00:00:00Z"). Dates without a time or offset are interpreted as UTC.
    funnelSessionsstring
    Funnels only. `DROPPED_OFF` (default) returns sessions that completed `funnelStep` but not the next step. `REACHED` returns sessions that completed at least `funnelStep`. The last step has no drop-offs.one of DROPPED_OFFREACHED
    funnelStepinteger
    Funnels only. Zero-based index into `funnel.steps`, matching the order of `funnelStepSessionCounts`, used to select which sessions to return. Omit to select drop-offs from any step (with `DROPPED_OFF`) or sessions that completed the whole funnel (with `REACHED`).
    limitinteger
    Maximum number of rows returned for table metrics. Defaults to 20. Ignored for other metric types.
    sessionLimitinteger
    Number of example sessions to return in `sessionDefinitions`. Omit unless the user wants to see or watch sessions, since it adds a query.
    timezonestring
    Optional IANA timezone (e.g., 'America/New_York'). Time buckets align to this timezone's calendar (e.g., daily buckets break at its midnight). When omitted, they align to UTC. Pass the timezone the user asks for, or otherwise the timezone they are working in when known. If unknown, omit it; a UTC offset alone doesn't identify a timezone, so a guessed value may be silently wrong.
  • logrocketmcp_get_network_entriesUse this to retrieve raw network request and response pairs recorded during a single LogRocket session, identified by its recording ID and session ID, as a HAR 1.2 document.Read-only

    Get Network Entries

    Use this to retrieve raw network request and response pairs recorded during a single LogRocket session, identified by its recording ID and session ID, as a HAR 1.2 document. Prefer this tool over watch_sessions when you only need network data. The response is an object with `total`, `offset`, `limit`, and `har`; entries are sorted by request start time and paginated, so if `offset + limit < total`, call the tool again with a higher offset to fetch the next page.

    Inputs

    organizationIDstringrequired
    The organization ID to run the query against. If not provided by the user, discover options using the list_organizations tool.
    projectIDstringrequired
    The project ID to run the query against. If not provided by the user, discover options using the list_projects tool.
    recordingIDstringrequired
    The recording ID of the session.
    sessionIDintegerrequired
    The session ID of the session. Provide this as an integer.
    endTimestring
    Optional ISO 8601 datetime. Only entries whose request started at or before this time are returned. Defaults to the end of the session.
    limitinteger
    Maximum number of entries to return per call. Defaults to 100.
    maxStatusinteger
    Optional inclusive upper bound on the response status code.
    methodsarray
    Optional list of HTTP methods (e.g., ["POST", "PUT"]). Only entries whose request used one of these methods are returned. Matching is case-insensitive.
    minStatusinteger
    Optional inclusive lower bound on the response status code. Combine with maxStatus to select a range (e.g., 500 and 599 for server errors) or use both with the same value to select one code (e.g., 404).
    offsetinteger
    Number of matching entries to skip, for pagination. Defaults to 0.
    startTimestring
    Optional ISO 8601 datetime. Only entries whose request started at or after this time are returned. Defaults to the start of the session.
    urlFilterstring
    Optional case-insensitive substring filter applied to request URLs (e.g., "/api/cart" or "subdomain.example.com"). Only entries whose URL contains this substring are returned.
  • logrocketmcp_list_organizationsList all LogRocket organizations the authenticated user has access to.Read-only

    List Organizations

    List all LogRocket organizations the authenticated user has access to. Use this first to discover available organizations before querying projects or sessions.

    Inputs

    This tool takes no inputs.

  • logrocketmcp_list_projectsList all projects within a LogRocket organization.Read-only

    List Projects

    List all projects within a LogRocket organization. Use this to identify accessible projects before querying sessions, metrics, or issues.

    Inputs

    organizationIDstringrequired
    The organization ID to list projects for. All projects belong to an organization. If not provided by the user, options should be discovered using the list_organizations tool.
  • logrocketmcp_use_logrocketProcess a natural language query against LogRocket data — sessions, metrics, and issues.Read-only

    Use LogRocket

    Process a natural language query against LogRocket data — sessions, metrics, and issues. Use this to investigate user-reported bugs, understand behavior patterns, analyze performance metrics, and detect regressions by correlating code changes with LogRocket data.

    Inputs

    organizationIDstringrequired
    The organization ID to run the query against. Should be inferred from user input if a slash-separated identifier of the form `<organizationID>/<projectID>` or a link to a LogRocket resource is provided. For example, a LogRocket session URL has the structure `https://app.logrocket.com/<organizationID>/<projectID>/s/<recordingID>/<sessionID>`. Similarly, links to other LogRocket resources (e.g., issues, metrics) will contain the organization ID as the first path segment. If not provided by the user, discover options using the list_organizations tool. If multiple organizations are found, ask the user which one(s) they want to use before proceeding.
    projectIDstringrequired
    The project ID to run the query against. Should be inferred from user input if a slash-separated identifier of the form `<organizationID>/<projectID>` or a link to a LogRocket resource is provided. For example, a LogRocket session URL has the structure `https://app.logrocket.com/<organizationID>/<projectID>/s/<recordingID>/<sessionID>`. Similarly, links to other LogRocket resources (e.g., issues, metrics) will contain the project ID as the second path segment. If not provided by the user, discover options using the list_projects tool. If multiple projects are found, ask the user which one(s) they want to use before proceeding.
    querystringrequired
    The natural language query to run against LogRocket. Not required when polling for a result.
    chatIDstring
    The chatID from a previous response. Must be provided to continue an existing conversation (e.g., follow-up questions) or poll for a result. Omit to start a new conversation.
    pollForResultboolean
    Set to true to poll for completion of a query that previously had status: thinking. Omit in all other cases.
    timezonestring
    Optional IANA timezone (e.g., 'America/New_York'). Time buckets align to this timezone's calendar (e.g., daily buckets break at its midnight). When omitted, they align to UTC. Pass the timezone the user asks for, or otherwise the timezone they are working in when known. If unknown, omit it; a UTC offset alone doesn't identify a timezone, so a guessed value may be silently wrong.
All 124 in Analytics