Jam MCP connector
The Jam connector brings your bug recordings, console logs, network requests, comments and folders into Claude, ChatGPT and Cursor, so anyone can ask about a jam and get an answer from the actual recording.
-
How it connects. Connects over OAuth. The credential goes into a vault nobody reads back.
-
One address. https://api.elaichi.ai/mcp, the same for every user.
-
Their own access. An agent never gets more than the person it acts for.
How to connect
How to connect Jam to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Jam once
-
Open Connections, choose Add connection, and pick Jam.
-
Optionally set Share with to give a team access, then press Connect.
-
Approve it in Jam. Jam's own window opens. Whoever approves it decides what this connection can reach.
The credential is vaulted. Nobody reads it back, not even the AI.
Add connection
Choose a connector.
In your AI client
Point it at one endpoint
Everyone in the organization uses the same address, and each person only ever reaches what their own account allows.
Jam MCP connector for Claude
-
1
Open Customize, then Connectors.
-
2
Press Add.
-
3
Name it, paste the MCP server URL, then Continue.
https://api.elaichi.ai/mcp -
4
Sign in and approve.
On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.
Jam MCP connector for ChatGPT
-
1
Open Plugins, then press the + button.
-
2
Name it and paste the endpoint into Server URL.
https://api.elaichi.ai/mcp -
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.
Jam MCP connector for Cursor
-
1
Open
~/.cursor/mcp.json. -
2
Add the endpoint under
mcpServers.https://api.elaichi.ai/mcp -
3
Reload Cursor, then sign in and approve.
~/.cursor/mcp.json
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
Set up per machine, so repeat it on each computer you work from.
Connect Jam to any MCP client
-
1
Add the endpoint as a remote MCP server.
https://api.elaichi.ai/mcp -
2
Sign in and approve.
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
The Elaichi Agent already has these tools, with nothing to set up.
Use cases
What teams do with Jam through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Engineering
Read the console logs before opening the video
Ask what errors fired during a jam and which network requests failed, then get the stack of events in order without scrubbing through the recording.
-
Support
Turn a customer's jam into a clear ticket
Pull the transcript, the steps the user took and the browser details from a jam, and draft the ticket in the words an engineer needs.
-
QA
Find every jam that shows the same bug
Search jams across folders for a failing request or an error message and see whether the regression is new or has been reported before.
-
Product
Summarize what the week's jams are about
Ask for the themes across the jams in a folder, with chapters and transcripts summarized, so the Friday review starts with the real picture.
-
Design
Pull the frames that show the broken screen
Get the screenshots and frames from a jam where the layout breaks, and leave a comment pointing at the exact moment.
-
Customer Success
Keep the jam updated after the call
After talking to a customer, add a comment with what they said, react to the fix when it lands, and move the jam into the right folder.
Try asking
- “Summarize the console errors in the checkout crash jam from yesterday.”
- “Which jams in the Mobile folder mention a failed network request?”
- “Draft a comment on the login bug jam with the repro steps.”
Compare
Elaichi vs Zapier MCP vs Composio for Jam
All three can connect Jam 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.
https://api.elaichi.ai/mcp
|
A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over Jam tools | Allow or restrict single Jam 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 Jam 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, security, usage; Composio docs, gateway, enterprise, pricing. Checked September 2026.
Longer take: Zapier MCP alternative and when you don't need an MCP gateway.
AI tools
Jam tools for your AI agents
31 tools are ready to call through Elaichi's MCP endpoint the moment you connect Jam, governed by the same roles, restrictions, and audit log as everything else in Elaichi. Jam builds and runs these tools.
No tools match your search.
See it in Elaichi
What connecting Jam gets you
6 screens from the product, each doing one job for your Jam account.
The agent
Ask what broke and the jam answers.
Plain questions, answered from live console logs, network requests and comments in Jam.
- jams
- comments
- folders
- console logs
Ask Elaichi to work across your apps.
Summarize the console errors in the checkout crash jam from yesterday.
Which jams in the Mobile folder mention a failed network request?
Draft a comment on the login bug jam with the repro steps.
Also runs in Claude, ChatGPT or Cursor
MCP clients
One endpoint brings Jam to every client.
Claude, ChatGPT and Cursor reach Jam through one governed endpoint, no SDK, no shared key.
Copy the endpoint
Tool catalog
31 Jam tools, ready without writing code.
Jams, console logs, network requests, screenshots, comments and folders, covered with no custom code.
- Get details
- Get console logs
- Get network requests
- Get user events
Toolboxes
Every team gets its own Jam toolbox.
Engineering, Support and QA each work from a toolbox scoped to their part of Jam.
- Engineering
- Support
- QA
- Product
Shared connections
Share one Jam connection, never a credential.
One person connects Jam, teams and members work through it without seeing a secret.
- Web platform
- Mobile
- Support
- QA
Audit log
Every Jam action is logged with a name.
When, who, what happened and which jam, in an append-only log you can answer from.
- When
- Who
- What happened
- Type
Launching soon
From answering questions to doing the work
A person no longer has to ask. A trigger starts the work, inside the same permissions and the same audit log as everything else. Automations and live dashboards are launching soon, on the Black plan.
Automations
A schedule starts the Jam triage, you approve.
New jams are fetched, grouped and drafted into a digest, approved, then posted back to Jam.
Jam digest
Run 418 · started 2 minutes ago · on behalf of Emily Carter
-
✓
Schedule
Every weekday at 8:00 AM
0.2s -
✓
Fetch jams
Jam
1.4s -
✓
Group by owner
Transform
0.1s -
✓
Draft the digest
Agent step
Ran with 4 tools, returned a structured summary
6.2s -
Approve the digest
Needs approval
Assigned to Michael Brennan
Approve Deny -
Post the digest
Jam
Queued
Collections and dashboards
Jam health numbers arrive before anyone asks.
Jams created over 14 days, by team, computed from Jam records with no model involved.
Jam health
Refreshed 4 minutes ago · every 15 minutes · from the jams collection
Jams
1,284 ↓ 12%
Comments
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Jams created
Last 14 days
By team
Share of activity
Web platform 34%
Mobile 27%
Support 21%
QA 18%
FAQ
Frequently asked questions
How do I connect Jam to Claude?
In Elaichi, choose Jam and connect it. Jam's own sign-in opens in your browser, you approve access, and you are done, with no client ID or secret to generate. Then in Claude go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Claude can now work with your jams, console logs and comments as you.
Does Jam work with ChatGPT and Cursor as well as Claude?
Yes. Once Jam 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 Jam once and every client you use picks it up.
What can an AI agent actually do with my Jam data?
It can read a jam's details, console logs, network requests, user events, screenshots, frames, transcript and chapters, and analyze the video to explain what went wrong. It can search jams, list folders and members, add or edit comments, add reactions, update or move jams, and create or tidy folders. Short, specific asks like "what errors fired in this jam" work better than long sentences.
Does connecting Jam give the AI access to every jam in my workspace?
No. The AI acts as the person who signed in to Jam, so it only sees the jams, folders and comments that person can already open. Elaichi can narrow that further with roles and restrictions, but it can never widen access beyond what Jam already allows that person.
Can I stop an agent from deleting or changing things in Jam?
Yes. Restrictions in Elaichi work per action, so you can allow reading jams and console logs while blocking deleting a jam, removing a comment or deleting a folder. A restricted action is never shown to the AI client at all, so no prompt can reach it.
What happens to a Jam connection when someone leaves?
When you offboard a person in Elaichi, their access to Jam through every client ends at once. If Jam was connected through a shared connection, it keeps working for everyone else on the team. If you disconnect Jam once in Elaichi, it disappears from Claude, ChatGPT, Cursor and every other client together.
Does the Jam MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. Jam 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 Jam?
Yes. Both let Claude, ChatGPT or Cursor use Jam. 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 Jam call.
How is Elaichi different from Composio for Jam?
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 Jam: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.
Put Jam in front of your team
14 days on Gold, no credit card. Connect it once and pick what each team can call.
- Works with
-
and any other MCP client, or the Elaichi Agent.
- When the trial ends
- Nothing is deleted. Connections, roles and the audit log stay where they are, so subscribing picks up exactly where you left off.