LogRocket MCP connector for AI agents

CALL ANY TOOL

Query sessions, investigate reported issues, and detect regressions across the user's projects.

logrocketmcp_list_projects

List projects

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

Parameters

Name

Type

Required

Description

organizationSlug

string

Required

The slug of the LogRocket organization. Use the list_organizations tool to find available organization slugs.

logrocketmcp_get_network_entries

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.

Parameters

Name

Type

Required

Description

organizationID

string

Required

The organization ID to run the query against. If not provided by the user, discover options using the list_organizations tool.

projectID

string

Required

The project ID to run the query against. If not provided by the user, discover options using the list_projects tool.

recordingID

string

Required

The recording ID of the session.

sessionID

integer

Required

The session ID of the session. Provide this as an integer.

endTime

string

Optional

Optional ISO 8601 datetime. Only entries whose request started at or before this time are returned. Defaults to the end of the session.

limit

integer

Optional

Maximum number of entries to return per call. Defaults to 100.

maxStatus

integer

Optional

Optional inclusive upper bound on the response status code.

methods

array

Optional

Optional list of HTTP methods (e.g., ["POST", "PUT"]). Only entries whose request used one of these methods are returned. Matching is case-insensitive.

minStatus

integer

Optional

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).

offset

integer

Optional

Number of matching entries to skip, for pagination. Defaults to 0.

startTime

string

Optional

Optional ISO 8601 datetime. Only entries whose request started at or after this time are returned. Defaults to the start of the session.

urlFilter

string

Optional

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_organizations

List organizations

logrocketmcp_find_issues

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.

Parameters

Name

Type

Required

Description

organizationID

string

Required

The organization ID to run the query against. If not provided by the user, discover options using the list_organizations tool.

projectID

string

Required

The project ID to run the query against. If not provided by the user, discover options using the list_projects tool.

endDate

string

Optional

Optional ISO 8601 datetime for the end of the time range to search. Defaults to now.

issueTypes

array

Optional

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.

limit

integer

Optional

Maximum number of issues to fetch, applied before any natural language relevance filtering. Defaults to 30.

query

string

Optional

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.

severity

string

Optional

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".

startDate

string

Optional

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.

triageStatuses

array

Optional

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_build_metric

Build metric

logrocketmcp_find_sessions

Find sessions

logrocketmcp_use_logrocket

Use logrocket

logrocketmcp_watch_sessions

Watch sessions

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

from langchain_mcp_adapters.client import MultiServerMCPClient
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="logrocketmcp")

mcp = MultiServerMCPClient({
    "logrocketmcp": {
        "url": "https://mcp.scalekit.com/logrocketmcp",
        "headers": {"Authorization": "Bearer " + token}
    }
})
tools = await mcp.get_tools()

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "logrocketmcp" });

const openai = new OpenAI();
// Connect to MCP at https://mcp.scalekit.com/logrocketmcp
// Pass: Authorization: Bearer + token

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "logrocketmcp" });

const anthropic = new Anthropic();
// Connect to MCP at https://mcp.scalekit.com/logrocketmcp
// Pass: Authorization: Bearer + token

from google.adk.agents import LlmAgent
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="logrocketmcp")
# Connect to MCP at https://mcp.scalekit.com/logrocketmcp
# Pass: Authorization: Bearer + token

Try these prompts

Copy any prompt into your agent. Each maps directly to a LogRocket tool. Click to copy, paste into your agent, done.

Get started

Copy the prompt

Copied

Process a natural language query against LogRocket data — sessions, metrics, and issues?

Copy the prompt

Copied

List all projects within a LogRocket organization?

Advanced

Copy the prompt

Copied

Process a natural language query against LogRocket data — sessions, metrics, and issues?

Copy the prompt

Copied

List all projects within a LogRocket organization?

SEE HOW AUTH WORKS

Your users connect once. Their LogRocket credentials stay vaulted, every call is scope-checked, and every action is logged.

1

Authorize

Your user connects

LogRocket MCP

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

2

Store

Their

LogRocket MCP

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

3

Resolve

When your agent calls a

LogRocket MCP

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

4

Audit

Every

LogRocket MCP

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other connectors.

GTM and RevOps Teams

Revenue forecast commentary

Pulls open pipeline from Salesforce and HubSpot, calculates coverage against quota, flags at-risk stages, posts commentary to Slack, and logs every snapshot to Google Sheets.

GTM and RevOps Teams

Deal intelligence agent

Pulls recent Gong calls, scores deal risk with an LLM, cross-references the record in Attio, and DMs each owner their at-risk deals in Slack. Every read is scoped to that rep's own access.

Engineering Teams

Engineering standup agent

Pulls commits from GitHub and GitLab, tracks issue movement in Jira, and posts a per-engineer standup brief to Slack. Each engineer's activity is read on their own delegated OAuth.

GTM and RevOps Teams

Competitive intelligence briefing agent

Scans Gong calls for competitor mentions, matches each one to its Notion battlecard, and DMs every affected rep a single Slack digest per cycle. Every call runs as the PMM who owns the briefing, never a shared bot.

Test other agents

See the same per-user auth pattern across other connectors.

SALES

Deal intelligence agent

Score Gong call risk with an LLM, cross-reference the Attio record, and DM each owner their at-risk deals in Slack.

ENGINEERING

Engineering standup agent

Pull commits from GitHub and GitLab, track Jira issue movement, and post a per-engineer standup brief to Slack.

GTM

Revenue forecast agent

Score pipeline coverage against quota across Salesforce and HubSpot, post forecast commentary to Slack, log snapshots to Sheets.

GTM

Competitive intelligence briefing agent

Scan Gong calls for competitor mentions, match each one to its Notion battlecard, and DM every affected rep a single Slack digest.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential.

// shared token
 audit → bot_service_account

 // scalekit
 audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

One connector today. Ten tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access LogRocket as the user or as a shared key?
As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the LogRocket OAuth token stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in LogRocket?
Yes. Pass a tool name filter to listScopedTools so the analytics agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches LogRocket.

What happens when a user revokes LogRocket access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Which session recordings can the agent investigate?
Only projects the authorizing user can access in LogRocket. Session queries and regression checks follow organization membership, keeping user session data inside the right team.

LogRocket MCP

Tools your agent reaches for on LogRocket, scoped per user.