# LogRocket MCP connector

The LogRocket connector brings session replays, issues, network requests and metrics into Claude, ChatGPT, Cursor and the Elaichi Agent, so your team can ask about what users actually saw and did.

Source: https://elaichi.ai/connectors/logrocket/

## Facts

| | |
| --- | --- |
| Application | LogRocket |
| Category | Observability |
| AI tools | 8 |
| Authentication | Connects over OAuth |
| Bring your own OAuth app | No |
| Native MCP | Yes. LogRocket builds and runs this MCP server. Elaichi adds sign-in, access controls and an audit log on top |
| Support for its tools | logrocket.com/contact |
| MCP endpoint | https://api.elaichi.ai/mcp |
| Works with | Claude, ChatGPT, Cursor, any MCP client, and the Elaichi Agent |
| Tools advertised by name | No. Connected tools are never listed one by one, however few there are. The endpoint advertises `search_tools` and `execute_tool` instead |

## What you can ask once LogRocket is connected

- Find sessions from acme.com this week that hit a checkout error
- Which issues in the web app project are new since Monday?
- Show the failed network requests in the session from ticket 4821

## Connect LogRocket in Elaichi

This happens once for the organization, before any client is involved.

1. Open Connections, choose Add connection, and pick LogRocket.
2. Optionally set Share with, then press Connect.
3. Approve it in LogRocket. LogRocket's own window opens. Whoever approves it decides what this connection can reach.

Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which LogRocket tools are exposed, rename them, or freeze arguments before anyone points a client at it.

## LogRocket MCP connector for Claude

Endpoint: https://api.elaichi.ai/mcp

1. Open Customize, then Connectors.
2. Press Add.
3. Name it, paste the MCP server URL, then Continue.
4. Sign in and approve.

On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.

## LogRocket MCP connector for ChatGPT

Endpoint: https://api.elaichi.ai/mcp

1. Open Plugins, then press the + button.
2. Name it and paste the endpoint into Server URL.
3. Leave Authentication on OAuth, then tick the risk acknowledgement.
4. Press Create, then sign in and approve.

Works on the web today. The plugin directory lives at chatgpt.com/plugins.

## LogRocket MCP connector for Cursor

Endpoint: https://api.elaichi.ai/mcp

1. Open `~/.cursor/mcp.json`.
2. Add the endpoint under `mcpServers`.
3. Reload Cursor, then sign in and approve.

Set up per machine, so repeat it on each computer you work from.

## Connect LogRocket to any MCP client

Endpoint: https://api.elaichi.ai/mcp

1. Add the endpoint as a remote MCP server.
2. Sign in and approve.

The Elaichi Agent already has these tools, with nothing to set up.

## What the consent screen decides

Only Read is granted by default, which is not enough to call a LogRocket tool. Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Grant Read and Run tools. Think hard before granting Delete, which reaches into connected apps and cannot be undone.

## What teams do with LogRocket through Elaichi

### Find the session behind a ticket

Support. A customer says checkout broke on Tuesday. Ask for their sessions from that day, open the one with the error, and watch exactly what they saw before writing back.

### Check whether a new issue is spreading

Product. Ask which issues in the web app project appeared this week and how many sessions each one touched, then decide what goes into the next sprint.

### Trace a failed request without leaving the editor

Engineering. From Cursor, ask for the network entries in a broken session and see which request failed, what it returned, and how long it took.

### Confirm a bug is really fixed after release

QA. After a deploy, ask for sessions on the new version that hit the old error. An empty answer is the sign-off you were looking for.

### Prepare for a renewal call with real usage

Customer success. Ask for recent sessions from the account, see which parts of the product they visit and where they get stuck, and walk into the call knowing what to raise.

### See where people stall in a new flow

Design. Build a metric for how many sessions reach the last step of onboarding versus drop off, and watch a few of the sessions that gave up.

## Elaichi vs Zapier MCP vs Composio for LogRocket

All three can connect LogRocket to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.

| What to check | Elaichi | Zapier MCP | Composio |
| --- | --- | --- | --- |
| Where the AI connects | One address for the whole organization. Endpoint: https://api.elaichi.ai/mcp | A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over LogRocket tools | Allow or restrict single LogRocket tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per LogRocket call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | $15 per user per month. | 2 tasks per successful call. | Billed per tool call. |

Sources: Zapier MCP [docs](https://docs.zapier.com/mcp/get-started/quickstart), [security](https://docs.zapier.com/mcp/manage/security), [usage](https://docs.zapier.com/mcp/features/usage); Composio [docs](https://docs.composio.dev/docs/composio-connect), [gateway](https://composio.dev/mcp-gateway), [enterprise](https://composio.dev/enterprise), [pricing](https://composio.dev/pricing). Checked September 2026.

Longer take: [Zapier MCP alternative](/blog/zapier-mcp-alternative/) and [when you don't need an MCP gateway](/blog/when-you-dont-need-an-mcp-gateway/).

## Frequently asked questions

### How do I connect LogRocket to Claude?

Connect LogRocket in Elaichi first: pick it from the catalog and sign in to LogRocket over OAuth, the same way you sign in to the LogRocket website. There is no OAuth application to register and no client ID or secret to generate. Then open Claude, go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp as the endpoint. Claude asks you to sign in to Elaichi once and LogRocket is available from then on.

### Does LogRocket work with ChatGPT and Cursor as well as Claude?

Yes. Once LogRocket is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client, and the Elaichi Agent. You connect LogRocket once and every client picks it up.

### What can an AI agent actually do with my LogRocket data?

With LogRocket connected, an agent can list your organizations and projects, find sessions for a user, an account or a date range, watch what happened in a session, pull the network requests behind it, look up issues, and build a metric across sessions. In practice that means asking things like "show me the sessions from acme.com that hit an error this week" and getting back real LogRocket results. Short, specific asks work better than long paragraphs.

### Does connecting LogRocket give the AI access to every project?

No. Every call to LogRocket runs as the person who signed in, so the AI sees only the organizations and projects that person can already open in LogRocket. Elaichi can narrow that further, for example to a single project or to read-only work, but it can never widen it beyond what the person has in LogRocket.

### Can my team share one LogRocket connection?

Yes. One person connects LogRocket in Elaichi and shares the connection with a team, and nobody else on the team ever handles a credential. Each person still signs in to Elaichi as themselves, so every LogRocket session they open or issue they look up is logged under their own name.

### Can I stop an agent from changing things in LogRocket?

Yes. Restrictions in Elaichi apply per action, so you can allow finding and watching LogRocket sessions while blocking anything you do not want an agent to touch. A restricted action is never advertised to Claude, ChatGPT or Cursor at all, so no prompt, however clever, can reach it.

### What happens to a LogRocket connection when someone leaves?

Offboarding a person in Elaichi ends their access to LogRocket through every client at once, with nothing to revoke in Claude, ChatGPT or Cursor separately. A LogRocket connection shared with a team keeps working for everyone else. If you want LogRocket gone entirely, disconnecting it once in Elaichi removes it from every client.

### Does the LogRocket MCP connector work with Gemini, Codex, Claude Code or other MCP clients?

Yes. LogRocket is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.

### Is Elaichi an alternative to Zapier MCP for LogRocket?

Yes. Both let Claude, ChatGPT or Cursor use LogRocket. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every LogRocket call.

### How is Elaichi different from Composio for LogRocket?

Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to LogRocket: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.

## All 8 LogRocket tools

Every tool below is callable through https://api.elaichi.ai/mcp once LogRocket is connected, subject to the toolbox it is in and the restrictions on the caller.

- **List organizations** (List). For listing the LogRocket organizations you can access. Hidden when scoping to a specific organization (e.g., https://mcp.logrocket.com/mcp/<your_organization_id>).
- **List projects** (List). For listing the LogRocket projects you can access within a given organization. Hidden when scoping to a specific project (e.g., https://mcp.logrocket.com/mcp/<your_organization_id>/<your_project_id>).
- **Use LogRocket** (Action). For running natural language queries against your LogRocket data (e.g., sessions, metrics, and issues). Queries are handled by Ask Galileo which chains tool calls internally.
- **Find sessions** (Action). For filtering LogRocket sessions.
- **Watch sessions** (Action). For analyzing and/or extracting additional information about one or more sessions.
- **Get network entries** (Get). For retrieving the network requests and responses recorded during a single session, as a HAR document. Supports filtering by URL, HTTP method, response status, and time range.
- **Build metric** (Action). For querying LogRocket analytics data.
- **Find issues** (Action). For querying LogRocket issues data. Includes issue analyses when they exist.