Manufact MCP connector
The Manufact connector brings your organizations, servers, deployments and server analytics to Claude, ChatGPT, Cursor and the Elaichi Agent, so your team can deploy, check logs and read usage inside their own Manufact access.
-
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.
22 tools
How to connect
How to connect Manufact to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Manufact once
-
Open Connections, choose Add connection, and pick Manufact.
-
Optionally set Share with to give a team access, then press Connect.
-
Approve it in Manufact. Manufact'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.
Manufact 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.
Manufact 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.
Manufact 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 Manufact 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 Manufact through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Engineering
Ship a deployment and watch the build
Ask for a deploy of a server, then follow the build logs and runtime logs in the same conversation. If the build fails, the agent reads back the lines that matter instead of making you dig through the console.
-
Platform
Find out why a server is throwing errors
Pull the health summary and the error runtime logs for a Manufact server in one ask. Redeploy or stop the deployment from the same place once you know what went wrong.
-
Support
Check deployment logs when a customer reports trouble
When a ticket says a tool stopped responding, ask for the latest deployment of that server and its runtime logs. You get an answer for the customer without waiting on an engineer.
-
Product
See which clients and tools people actually use
Ask for the client breakdown and tool breakdown on any Manufact server to learn whether traffic comes from Claude, Cursor or elsewhere, and which tools carry the load.
-
Leadership
Get a weekly picture of usage by country
Request the analytics summary and requests by country across your Manufact organizations, and have the agent turn it into a short readout for the Monday meeting.
-
Operations
Invite a teammate and tidy pending invitations
Invite a new member to a Manufact organization, list who has not accepted yet, and cancel invitations that went to the wrong address, all without opening the admin screen.
Try asking
- “Show build logs for the latest billing server deployment”
- “Which tools on the docs server got the most requests this week?”
- “Redeploy the staging server and tell me when it is healthy”
Compare
Elaichi vs Zapier MCP vs Composio for Manufact
All three can connect Manufact 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 Manufact tools | Allow or restrict single Manufact 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 Manufact 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
Manufact tools for your AI agents
22 tools are ready to call through Elaichi's MCP endpoint the moment you connect Manufact, governed by the same roles, restrictions, and audit log as everything else in Elaichi. Manufact builds and runs these tools.
No tools match your search.
See it in Elaichi
What connecting Manufact gets you
6 screens from the product, each doing one job for your Manufact account.
The agent
Ask about your Manufact servers in plain language.
Deployments, build logs and request counts answered from live Manufact records, not a dashboard export.
- servers
- deployments
- organizations
- invitations
Ask Elaichi to work across your apps.
Show build logs for the latest billing server deployment
Which tools on the docs server got the most requests this week?
Redeploy the staging server and tell me when it is healthy
Also runs in Claude, ChatGPT or Cursor
MCP clients
One endpoint puts Manufact in every client.
Claude, ChatGPT and Cursor reach Manufact through one governed endpoint, no SDK, no shared API key.
ElaichiMCP clientsClaude
ChatGPT
Cursor
Copy the endpoint
Tool catalog
22 Manufact tools, ready without writing code.
Servers, deployments, logs, invitations and analytics covered the moment Manufact is connected.
- List organizations
- Get organization stats
- Invite org member
- List org invitations
ElaichiToolsToolboxes
Every team gets its own Manufact toolbox.
Platform deploys, Support reads logs, Product sees analytics, each from a toolbox scoped to them.
- Platform
- Engineering
- Support
- Product
ElaichiToolboxesShared connections
Share a Manufact connection, never a credential.
One person connects Manufact, teammates deploy and read logs through it without seeing a secret.
- Platform
- Production
- Staging
- Support
ElaichiConnectionsAudit log
Every Manufact deploy is on the record.
Who redeployed, who stopped a deployment and when, in an append-only log you can search.
- When
- Who
- What happened
- Type
ElaichiAudit logLaunching 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 runs the Manufact digest for you.
Error logs are fetched, grouped and drafted into a digest a person approves before it posts.
Manufact digest
Run 418 · started 2 minutes ago · on behalf of Emily Carter
-
✓
Schedule
Every weekday at 8:00 AM
0.2s -
✓
Fetch servers
Manufact
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
Manufact
Queued
Collections and dashboards
Manufact server health, computed, not asked for.
Requests, errors and deployments over 14 days, refreshed on a schedule with no model involved.
Manufact health
Refreshed 4 minutes ago · every 15 minutes · from the servers collection
Servers
1,284 ↓ 12%
Deployments
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Servers created
Last 14 days
By team
Share of activity
Platform 34%
Production 27%
Staging 21%
Support 18%
FAQ
Frequently asked questions
How do I connect Manufact to Claude?
Connect Manufact in Elaichi first: you are sent to Manufact's own sign-in page, approve access, and come back. There is no OAuth application to register and no client ID or secret to generate. Then in 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 and Manufact is available in your chats.
Does Manufact work with ChatGPT and Cursor as well as Claude?
Yes. Once Manufact 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 Manufact once and every client picks it up.
What can an AI agent actually do with my Manufact data?
With Manufact connected, an agent can list your organizations and servers, start a deploy or redeploy, stop a deployment, and read build logs and runtime logs. It can also pull server analytics such as health, requests by country, and which clients and tools are getting traffic, and it can invite or cancel organization members. Short, specific asks like "show the error logs for the docs server" work better than long sentences.
Does connecting Manufact give the AI access to every organization and server?
No. Access follows the person who signed in to Manufact, so the agent sees only the organizations, servers and deployments that person can already see. Elaichi can narrow that further, for example read-only analytics for one team, but it can never widen access beyond what Manufact grants.
Can I stop an agent from stopping deployments or changing servers in Manufact?
Yes. Restrictions in Elaichi work per action, so you can allow reading Manufact logs and analytics while blocking deploy, redeploy, stop deployment or server updates. A restricted action is never advertised to the AI client at all, so no prompt can reach it.
What happens to a Manufact connection when someone leaves?
Offboarding that person in Elaichi ends their Manufact access at once, in every client they used. A shared Manufact connection keeps working for everyone else on the team. If you need to remove Manufact entirely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor and every other client.
Does the Manufact MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. Manufact 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 Manufact?
Yes. Both let Claude, ChatGPT or Cursor use Manufact. 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 Manufact call.
How is Elaichi different from Composio for Manufact?
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 Manufact: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.
Put Manufact 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.