Port (US) MCP connector
Connect Port (US) to Elaichi and Claude, ChatGPT, Cursor, or the Elaichi Agent can list your services, run self-service actions, track runs, and check scorecards, each person inside their own Port access, every call logged.
-
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.
51 tools
How to connect
How to connect Port (US) to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Port (US) once
-
Open Connections, choose Add connection, and pick Port (US).
-
Optionally set Share with to give a team access, then press Connect.
-
Approve it in Port (US). Port (US)'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.
Port (US) 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.
Port (US) 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.
Port (US) 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 Port (US) 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 Port (US) through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Platform engineering
Run a self-service action from a chat
Ask which self-service actions are available in Port (US), run the one that provisions an environment, and follow the run until it finishes without opening the portal.
-
Engineering
Find the services your team owns
List the entities under the service blueprint, narrow them to your team, and get a plain summary of what is in Port (US) and who owns it.
-
SRE
Check a workflow run after a deploy
Pull up the latest workflow run for a service, see which step stopped it, and trigger it again once the fix is in.
-
Security
Search the audit log for a change
Ask who changed the permissions on an action in Port (US) and when, and get the audit log entries back in a sentence instead of a query.
-
Engineering management
See which scorecards are slipping
List the scorecards in Port (US) and the services failing them before the review, so the conversation starts with the facts.
-
Developer experience
Keep actions and workflows up to date
Draft a new action or workflow, update who is allowed to run it, and retire stale ones, with a person reviewing each change before it lands in Port (US).
Try asking
- “List the self-service actions I can run in Port today.”
- “Which services are failing the production readiness scorecard?”
- “Show the last workflow run for the checkout service deploy.”
Compare
Elaichi vs Zapier MCP vs Composio for Port (US)
All three can connect Port (US) 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 Port (US) tools | Allow or restrict single Port (US) 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 Port (US) 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
Port (US) tools for your AI agents
51 tools are ready to call through Elaichi's MCP endpoint the moment you connect Port (US), governed by the same roles, restrictions, and audit log as everything else in Elaichi. Port (US) builds and runs these tools.
No tools match your search.
See it in Elaichi
What connecting Port (US) gets you
6 screens from the product, each doing one job for your Port (US) account.
The agent
Ask Port (US) questions in plain language.
Get answers from live actions, entities, and scorecards without opening the portal.
- actions
- workflows
- entities
- scorecards
Ask Elaichi to work across your apps.
List the self-service actions I can run in Port today.
Which services are failing the production readiness scorecard?
Show the last workflow run for the checkout service deploy.
Also runs in Claude, ChatGPT or Cursor
MCP clients
One endpoint reaches Claude, ChatGPT, and Cursor.
Reach Port (US) from any MCP client, no SDK and no shared API key.
ElaichiMCP clientsClaude
ChatGPT
Cursor
Copy the endpoint
Tool catalog
51 Port (US) tools, no custom code.
Actions, workflows, blueprints, entities, scorecards, and audit logs, covered without writing a line.
- Get action permissions
- Get workflow run
- List actions
- List self service triggers
ElaichiToolsToolboxes
Every team gets its own Port (US) toolbox.
Platform engineering runs actions, security reads audit logs, each from a toolbox scoped to them.
- Platform engineering
- Engineering
- SRE
- Security
ElaichiToolboxesShared connections
Teammates work through Port (US) without credentials.
One person connects Port (US), shares it with teams, and nobody else handles a credential.
- Platform
- Backend
- SRE
- Security
ElaichiConnectionsAudit log
Every Port (US) call names who did it.
When, who, what happened, and which action or entity, in one append-only log.
- 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 starts real Port (US) work.
Action runs get fetched, grouped, drafted, approved by a person, then posted back.
Port (US) digest
Run 418 · started 2 minutes ago · on behalf of Emily Carter
-
✓
Schedule
Every weekday at 8:00 AM
0.2s -
✓
Fetch actions
Port (US)
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
Port (US)
Queued
Collections and dashboards
Port (US) health numbers, computed without a model.
Four metrics, 14 days of entities created, and a breakdown by team, refreshed on schedule.
Port (US) health
Refreshed 4 minutes ago · every 15 minutes · from the actions collection
Actions
1,284 ↓ 12%
Workflows
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Actions created
Last 14 days
By team
Share of activity
Platform 34%
Backend 27%
SRE 21%
Security 18%
FAQ
Frequently asked questions
How do I connect Port in US to Claude?
Connect Port (US) in Elaichi first: pick Port (US) from the catalog, sign in to Port in US with your normal Port account, and approve the access. There is no OAuth application to register and no client ID or secret to generate. Then in Claude open Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Sign in as yourself and Port (US) is ready in the conversation.
Does Port in US work with ChatGPT and Cursor as well as Claude?
Yes. Port (US) is connected once in Elaichi, and the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client, and the Elaichi Agent. Each person signs in as themselves in each client, and the Port in US connection follows them.
What can an AI agent actually do with my Port in US data?
It can list the services, environments, and other entities in Port (US), show which ones fail a scorecard, list self-service actions and run one, trigger a workflow and track the run, search the audit log, and read pages and sidebars. If you allow it, it can also create or update actions and workflows and change action permissions. Short concrete asks, such as run the restart action for checkout, work better in Port in US than long paragraphs.
Does connecting Port in US give the AI everything in my portal?
No. Every call to Port (US) runs as the person who signed in, so the AI sees only the blueprints, entities, and actions that person already has in Port in US. Elaichi can narrow that further with restrictions per action, and it can never widen access beyond what Port itself allows that person.
Can I stop an agent from deleting or changing things in Port in US?
Yes. Restrictions in Elaichi work per action, so you can allow reading entities and running self-service actions in Port (US) while blocking deleting actions, deleting workflows, or changing action permissions. A restricted capability is never advertised to Claude, ChatGPT, or Cursor at all, so no prompt can reach it in Port in US.
What happens to a Port in US connection when someone leaves?
Offboarding the person in Elaichi ends their access to Port (US) at once, in every client they used. A shared Port in US connection keeps working for everyone else on the team. If you want it gone entirely, disconnecting Port (US) once in Elaichi removes it from Claude, ChatGPT, Cursor, and every other client.
Does the Port (US) MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. Port (US) 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 Port (US)?
Yes. Both let Claude, ChatGPT or Cursor use Port (US). 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 Port (US) call.
How is Elaichi different from Composio for Port (US)?
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 Port (US): one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.
Put Port (US) 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.