Skip to content

Runpod MCP connector

Connect Runpod to Claude, ChatGPT, Cursor, or any MCP client through Elaichi and start, stop, create, and delete Runpod pods, serverless endpoints, and templates from a chat, with each action running as the person who signed in.

  • How it connects. Connects with an API key. 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 Runpod to Claude, ChatGPT or Cursor

Two steps, about a minute.

1

In Elaichi

Connect Runpod once

  1. Open Connections, choose Add connection, and pick Runpod.

  2. Optionally set Share with to give a team access, then press Connect.

  3. Paste a Runpod API key. One person generates a token in Runpod and pastes it once. Everyone else works through Share with, and never sees it.

The credential is vaulted. Nobody reads it back, not even the AI.

Add connection

Choose a connector.

runpod
Runpod
Apache Airflow
Apify
Boomi
Browserbase
Caspio
2

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.

Runpod MCP connector for Claude

  1. 1

    Open Customize, then Connectors.

  2. 2

    Press Add.

  3. 3

    Name it, paste the MCP server URL, then Continue.

    https://api.elaichi.ai/mcp
  4. 4

    Sign in and approve.

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

Runpod MCP connector for ChatGPT

  1. 1

    Open Plugins, then press the + button.

  2. 2

    Name it and paste the endpoint into Server URL.

    https://api.elaichi.ai/mcp
  3. 3

    Leave Authentication on OAuth, then tick the risk acknowledgement.

  4. 4

    Press Create, then sign in and approve.

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

Runpod MCP connector for Cursor

  1. 1

    Open ~/.cursor/mcp.json.

  2. 2

    Add the endpoint under mcpServers.

    https://api.elaichi.ai/mcp
  3. 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 Runpod to any MCP client

  1. 1

    Add the endpoint as a remote MCP server.

    https://api.elaichi.ai/mcp
  2. 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 Runpod through Elaichi

Every one of these runs inside the access the person already has, and lands in the same audit log.

  • Machine learning

    Stop idle pods before they run up the bill

    Ask which Runpod pods are running right now, see who left them on, and stop the ones nobody is using without opening the Runpod console.

  • Engineering

    Spin up a pod from an approved template

    Create a new Runpod pod from a saved template so the GPU type, container image, and settings match what the team already agreed on.

  • Platform

    Roll out a new endpoint version

    Update a Runpod serverless endpoint to a new template or worker configuration, then confirm it picked up the change.

  • Finance

    Reconcile what is running against the invoice

    List every Runpod pod and endpoint in the account at month end and check the running ones against the charges before approving the bill.

  • Research

    Restart a stuck training pod

    When an experiment hangs, ask for the pod by name, reset or restart it, and get back to the run in a minute.

  • Support

    Look up how Runpod handles something

    Ask a question about Runpod pods, endpoints, or templates and get an answer drawn from Runpod's own docs and API reference instead of searching for it.

Try asking

  • “List running Runpod pods and their GPU types.”
  • “Stop idle pods in the ML research workspace.”
  • “Which Runpod endpoints were created this week?”

See all 58 Runpod tools below

Compare

Elaichi vs Zapier MCP vs Composio for Runpod

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

Elaichi compared with Zapier MCP and Composio for Runpod, by what to check
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 Runpod tools Allow or restrict single Runpod 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 Runpod 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

Runpod tools for your AI agents

58 tools are ready to call through Elaichi's MCP endpoint the moment you connect Runpod, governed by the same roles, restrictions, and audit log as everything else in Elaichi.

See it in Elaichi

What connecting Runpod gets you

6 screens from the product, each doing one job for your Runpod account.

The agent

Ask about pods, read the answer.

Plain language questions return live Runpod pods, endpoints and docs.

  • pods
  • endpoints
  • docs
  • templates

Ask Elaichi to work across your apps.

List running Runpod pods and their GPU types.

Stop idle pods in the ML research workspace.

Which Runpod endpoints were created this week?

Also runs in Claude, ChatGPT or Cursor

MCP clients

Claude, ChatGPT and Cursor reach Runpod.

One org MCP endpoint over OAuth, no SDK and no shared API key.

ElaichiMCP clients
Claude ChatGPT Cursor

Copy the endpoint

https://api.elaichi.ai/mcp
Client Connected by Status Last used
Claude
E

Emily Carter

• Connected 4 minutes ago
Cursor
M

Megan Brooks

• Connected 2 hours ago
ChatGPT
R

Ryan Hayes

• Connected Yesterday

Tool catalog

58 Runpod tools arrive ready to call.

Pods, endpoints, docs and OpenAPI methods listed, with no custom code written.

  • List all Runpod openapi jsons
  • List all Runpod docs
  • List all Runpod pods
  • Create a Runpod pod
ElaichiTools
Tool Action Description
List all Runpod openapi jsons List Get the OpenAPI 3.0 specification for the runpod API. Returns the complete API specification as an opaque JSON document; the source provides no enumerable field-level schema (example payload is an empty object), and the response structure follows the OpenAPI 3.0 standard.
List all Runpod docs List Get the interactive RunPod API documentation page. Returns an HTML page rendering the OpenAPI schema UI — this endpoint serves a text/html response rather than structured JSON data, so no enumerable fields are available.
List all Runpod pods List List runpod Pods with optional filters. Returns: env, gpu, id, image, interruptible, locked, machine, name, ports. Supports filtering by computeType, desiredStatus, gpuTypeId, dataCenterId, imageName, and more.
Create a Runpod pod Create Create a new runpod Pod and optionally deploy it. Returns: env, gpu, id, image, interruptible, locked, machine, machineId, name, ports, templateId, imageName.
Get single Runpod pod by ID Get Get a single runpod Pod by id. Returns: env, gpu, id, image, interruptible, locked, machine, name, ports. Required: id.

Toolboxes

Every team gets its own Runpod toolbox.

Toolboxes are scoped per team, so ML research and platform see different tools.

  • ML research
  • Platform
  • Inference
  • Data engineering
ElaichiToolboxes
Name Source template Tools Created

ML research toolbox

Runpod · training pods and GPU types

Runpod starter 18 Mar 4, 2026

Platform toolbox

Runpod · endpoints and pod restarts

— 9 Mar 2, 2026

Inference toolbox

Runpod · serverless endpoints and scaling

— 24 Feb 27, 2026

Data engineering toolbox

Runpod · batch pods and volumes

Runpod starter 6 Feb 19, 2026

Finance toolbox

Runpod · pod usage and spend

— 31 Jan 30, 2026

Support toolbox

Runpod · pod status and docs

— 12 Jan 22, 2026

Shared connections

Teammates run pods without seeing keys.

The connections table shows who connected each Runpod account and its sharing.

  • ML research
  • Platform EU
  • Inference prod
  • Data engineering
ElaichiConnections
Connection Scope Status Access
RU

Runpod (ML research)

Connected by Emily Carter

Personal • Active 1 team · 6 members
RU

Runpod (Platform EU)

Connected by Jake Morgan

Organization • Active 3 teams · 24 members
RU

Runpod (Inference prod)

Connected by Megan Brooks

Organization • Active 2 teams · 11 members
RU

Runpod (Data engineering)

Connected by Tyler Reed

Personal • Needs re-auth 1 team · 3 members
RU

Runpod (Staging)

Connected by Ryan Hayes

Personal • Active Not shared
RU

Runpod (Finance)

Connected by Ashley Parker

Personal • Active 2 teams · 9 members

Audit log

Every pod start has a name on it.

When, who, what happened, type and resource for each Runpod call.

  • When
  • Who
  • What happened
  • Type
ElaichiAudit log
When Who What happened Type

2 minutes ago

Mar 6, 2026, 3:10 PM

E

Emily Carter

emily.carter@northwind.io

Restriction Created Access

8 minutes ago

Mar 6, 2026, 3:04 PM

J

Jake Morgan

jake.morgan@northwind.io

Restriction Updated Access

14 minutes ago

Mar 6, 2026, 2:58 PM

M

Megan Brooks

megan.brooks@northwind.io

Role Assigned Access

20 minutes ago

Mar 6, 2026, 2:52 PM

T

Tyler Reed

tyler.reed@northwind.io

Runpod Users Updated MCP

26 minutes ago

Mar 6, 2026, 2:46 PM

R

Ryan Hayes

ryan.hayes@northwind.io

Runpod Pods Created MCP

32 minutes ago

Mar 6, 2026, 2:40 PM

A

Ashley Parker

ashley.parker@northwind.io

Runpod Pods List Toolbox

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 fires, a digest posts back.

Six steps fetch Runpod pods, group them, draft, wait for approval, post.

Runpod digest

Run 418 · started 2 minutes ago · on behalf of Emily Carter

  1. ✓

    Schedule

    Every weekday at 8:00 AM

    0.2s
  2. ✓

    Fetch pods

    Runpod

    1.4s
  3. ✓

    Group by owner

    Transform

    0.1s
  4. ✓

    Draft the digest

    Agent step

    Ran with 4 tools, returned a structured summary

    6.2s
  5. Approve the digest

    Needs approval

    Assigned to Michael Brennan

    Approve
  6. Post the digest

    Runpod

    Queued

Collections and dashboards

Runpod health counted, not asked for.

Four metrics, 14 days of pods created, split by team, refreshed on schedule.

Runpod health

Refreshed 4 minutes ago · every 15 minutes · from the pods collection

Live

Pods

1,284 ↓ 12%

Endpoints

96 ↓ 8%

Needs attention

3 ↑ 2

Updated this week

412 ↑ 9%

Pods created

Last 14 days

By team

Share of activity

ML research 34%

Platform EU 27%

Inference prod 21%

Data engineering 18%

FAQ

Frequently asked questions

How do I connect Runpod to Claude?

In Elaichi, choose Runpod from the connector list and paste in a Runpod API key, which you copy from your Runpod account settings. 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 the endpoint https://api.elaichi.ai/mcp. Sign in as yourself and Runpod is available in the chat.

Does Runpod work with ChatGPT and Cursor as well as Claude?

Yes. Once Runpod 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 Runpod once and every client picks it up.

What can an AI agent actually do with my Runpod account?

With Runpod connected, an agent can list your pods, endpoints, and templates, create new ones, start, stop, reset, or restart a pod, update an endpoint or template, and delete what is no longer needed. It can also answer questions from Runpod's docs and API reference. Because Runpod exposes a lot of actions, short concrete asks like "stop the pod called training-3" work better than long paragraphs.

Does connecting Runpod give the AI access to my whole Runpod account?

The agent can only do what the Runpod API key it was given can do, and every call runs as the person who signed in to Elaichi. Elaichi can narrow that further, for example to viewing and stopping pods but never creating or deleting them. Elaichi never widens access beyond what the Runpod key already allows.

Can my team share one Runpod connection?

Yes. One person connects Runpod in Elaichi and shares the connection with a team, and nobody else ever sees or handles the Runpod API key. Each teammate still signs in as themselves, so the audit log names the person who started, stopped, or deleted a Runpod pod, not the account.

Can I stop an agent from deleting or changing things in Runpod?

Yes. Restrictions in Elaichi apply per action, so you can allow listing and starting Runpod pods while blocking deleting pods, endpoints, or templates. A blocked action is never shown to Claude, ChatGPT, or Cursor at all, so no prompt, however worded, can reach it.

What happens to a Runpod connection when someone leaves?

Offboarding a person in Elaichi ends their access to Runpod immediately across every client they used. A Runpod connection shared with the team keeps working for everyone else. If you want it gone entirely, disconnecting Runpod once in Elaichi removes it from Claude, ChatGPT, Cursor, and every other client at the same time.

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

Yes. Runpod 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 Runpod?

Yes. Both let Claude, ChatGPT or Cursor use Runpod. 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 Runpod call.

How is Elaichi different from Composio for Runpod?

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 Runpod: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.

Put Runpod in front of your team

14 days on Gold, no credit card. Connect it once and pick what each team can call.

Works with
Claude ChatGPT Cursor 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.