Connect Runpod to AI agents

Connect Runpod to Claude, Codex, Cursor, or other AI agents for your entire team. Metorial security, governance, observability, and gives your team a unified Magic MCP url to connect.

Deploy RunpodBook a demo

Supported Tools

Tools20Triggers1

manage_network_volume

Manage Network Volume

Update or delete a network volume. You can change the volume name and size, or permanently delete it.

manage_pod

Manage Pod

Perform lifecycle actions on a Pod: start, stop, restart, reset, or terminate. Use this to control the state of a running or stopped Pod.

list_templates

List Templates

List templates in your RunPod account. Templates define reusable Pod and endpoint configurations including container images, environment variables, and resource requirements. Optionally include public and RunPod-provided templates.

run_job

Run Serverless Job

Submit a job to a Serverless endpoint. Choose between **synchronous** execution (waits for result, best for quick tasks under 30s) or **asynchronous** execution (returns immediately with a job ID for polling). Optionally specify a webhook URL to receive results when complete.

manage_job

Manage Job

Perform actions on a Serverless job: cancel a running/queued job, retry a failed/timed-out job, or purge all pending jobs from the queue.

manage_template

Manage Template

Update or delete a template. When updating, any changes will trigger a rolling release for associated endpoints. Templates in use by Pods or endpoints cannot be deleted.

get_job_status

Get Job Status

Check the status and results of a Serverless job. Use this to poll for completion after submitting an asynchronous job. Returns the job's current status and output if completed.

delete_endpoint

Delete Endpoint

Permanently delete a Serverless endpoint. This terminates all associated workers and removes the endpoint configuration.

list_network_volumes

List Network Volumes

List all persistent network storage volumes in your RunPod account. Network volumes can be attached to Pods and Serverless endpoints, and they persist across restarts.

get_endpoint

Get Endpoint

Retrieve detailed information about a specific Serverless endpoint including its configuration, autoscaling settings, template, and health status. Also fetches endpoint health for operational insights.

list_endpoints

List Endpoints

List all Serverless endpoints in your RunPod account. Returns endpoint configuration details including autoscaling settings, GPU types, and worker counts.

update_endpoint

Update Endpoint

Update a Serverless endpoint's configuration including autoscaling parameters, GPU type, worker limits, and timeouts.

get_billing

Get Billing

Retrieve billing history for Pods, Serverless endpoints, or Network Volumes. Filter by date range, resource ID, and grouping to analyze costs. Amounts are in USD.

create_endpoint

Create Endpoint

Create a new Serverless endpoint for AI inference on RunPod. Configure autoscaling, GPU type, worker counts, and timeouts. Requires an existing template ID.

create_template

Create Template

Create a reusable template for Pods or Serverless endpoints. Templates define the container image, environment variables, ports, disk sizes, and other configuration that can be shared across deployments.

update_pod

Update Pod

Update a Pod's configuration including its name, container image, disk sizes, environment variables, ports, and other settings. Note: updating triggers a Pod reset, and GPU type cannot be changed.

create_network_volume

Create Network Volume

Create a persistent network storage volume that can be attached to Pods and Serverless endpoints. Volumes are region-specific and persist across Pod restarts.

get_pod

Get Pod

Retrieve detailed information about a specific Pod by its ID, including its configuration, status, GPU details, networking, and attached volumes.

list_pods

List Pods

List all GPU/CPU Pods in your RunPod account. Filter by compute type, status, GPU type, name, or attached network volume to find specific Pods. Returns Pod details including configuration, pricing, and status.

create_pod

Create Pod

Create a new GPU or CPU Pod on RunPod. Specify the container image, GPU type, disk sizes, ports, and environment variables. Supports both on-demand and spot (interruptible) instances.

More integrations teams use with Runpod

GitHub

Manage repositories, issues, and pull requests. Create and configure branches, star repositories, review code, and merge changes. Automate CI/CD workflows with GitHub Actions, manage workflow runs, secrets, and artifacts. Track issues with labels, milestones, and assignees. Search across code, repositories, issues, and users. Manage organizations, teams, and memberships. Create and manage projects, gists, packages, deployments, and environments. Access security alerts including code scanning, secret scanning, and Dependabot alerts. Read and write file contents in repositories. Manage webhooks, notifications, and codespaces.

Sharepoint

Manage SharePoint sites, document libraries, lists, and files. Create, read, update, and delete lists and list items with custom columns. Upload, download, move, copy, and version files in document libraries. Search across sites, files, folders, lists, and list items using Microsoft Search. Manage permissions at site, list, and item levels with granular access control. Define and manage content types and site columns. Subscribe to webhooks for list and library change notifications. Retrieve site properties and search for sites across Microsoft 365.

Salesforce

Manage CRM data including Accounts, Contacts, Leads, Opportunities, Cases, and custom objects. Create, read, update, and delete records. Query data using SOQL and search across objects using SOSL. Perform bulk data operations for large-scale imports, exports, and migrations. Execute composite requests to batch multiple operations in a single API call. Access analytics, reports, and dashboards. Manage files and attachments associated with records. Interact with Chatter feeds, posts, and groups for social collaboration. Subscribe to real-time change events via Change Data Capture and Platform Events. Manage org metadata including custom objects, fields, layouts, and workflows. Query data using GraphQL for precise data retrieval across related objects.

Airtable

Create, read, update, and delete records in Airtable bases and tables. Manage base schemas including creating tables and fields. Filter records using formulas, sort by fields, and scope queries to specific views. Upsert records to find, create, or update in a single call. Upload attachments to records, read and write record comments, list accessible bases, and receive real-time base change events through webhooks.

Bitbucket

Manage Git repositories, pull requests, and CI/CD pipelines on Bitbucket Cloud. Create, fork, and configure repositories within workspaces and projects. Create, review, approve, merge, and decline pull requests with inline code comments. Browse source code, list commits, and manage branches and tags. Track issues with the built-in issue tracker. Trigger, monitor, and manage Bitbucket Pipelines. List workspace members, configure repository default reviewers and branch restrictions, create and manage repository webhooks, and search code across repositories.

Heroku

Deploy, manage, and scale applications on Heroku's cloud platform. Create and configure apps, scale dynos, provision add-ons (databases, caching, etc.), manage configuration variables, build and release code, add custom domains and SSL certificates, manage collaborators and team permissions, configure pipelines for continuous delivery, set up log drains, and sync data with Salesforce via Heroku Connect. Subscribe to webhooks for real-time notifications on app changes, builds, releases, dyno lifecycle events, and more.

Technical notes for Runpod

Manage GPU/CPU cloud infrastructure for AI/ML workloads. Create, start, stop, and terminate GPU Pods for training and development. Deploy and manage serverless endpoints for AI inference with synchronous, asynchronous, and streaming execution modes. Submit jobs, check job status, cancel jobs, and purge queues. Create and manage persistent network volumes for storage. Save and reuse deployment configurations as templates. Connect private container registries. Monitor endpoint health, worker availability, and job statistics. Access billing history and usage data. Call pre-deployed public AI model endpoints for image, video, audio, and text generation.

Connect Runpod to production AI agents

See how Metorial gives Runpod access the governance, tracing, and security controls teams need.

Book a demoDeploy Runpod

Frequently asked questions

Common questions about connecting Runpod to AI agents with Metorial.

  1. Can Metorial connect Runpod to AI agents?
    Yes. Metorial connects AI agents to Runpod through a governed integration layer, so teams can use the provider while keeping access controlled and observable.
  2. Metorial is MCP compatible and lets teams expose approved provider tools to MCP-capable agents and clients through a controlled access layer.
  3. Metorial applies policies across users, groups, providers, agents, and individual tools, then records the context around every agent interaction.
  4. Yes. Metorial records provider activity so teams can inspect tool calls, troubleshoot integrations, and give security teams the visibility they need.