Pod

Yes, this is on purpose. Pod is built for agents, so the default page is plain HTML.
Human? View the normal website.
Agent? You probably prefer /mcp/tool/get-run.md or /mcp/tool/get-run.json, or Pod over MCP.

MCP Servers with a get_run tool

Every MCP server Pod knows of that exposes a get_run tool.

8 servers, ordered by decision readiness and adoption — GitHub stars and npm downloads where available, then reported issue volume. Pod has connected to 7 of them; the rest are publisher-reported and unverified.

AccessLint

AccessLint monitors and scans websites for accessibility problems.

Most accessibility problems live behind an interaction. AccessLint saves user journeys that cross multiple pages and interactions, that a real browser replays and checks on a schedule. AccessLint can also scan a public page ad hoc against WCAG. In either case, it returns rich findings that you can dig into with Claude and file issues or spin up remediations.

What you can do:

Requires a free AccessLint account. Single page scans work out of the box; you must verify ownership of a domain to run flows against it.

15 tools reported — Live, but requires authorization before it will list tools. Publisher lists 15 tools.

Ballet

Ballet is an agent and workflow automation platform for building AI-powered processes that can reason, take action, and run automatically.

Create specialized AI agents, chain them together into multi-step playbooks, and connect them to the tools and systems your team already uses through MCP servers. Playbooks can coordinate multiple agents and actions to complete end-to-end workflows instead of handling just a single prompt or task.

Ballet workflows can be launched manually or automatically from triggers including schedules, webhooks, Slack commands, form submissions, and other events. This makes it possible to turn repeatable operational processes into persistent AI-powered automations.

Use Ballet to:

Example workflows include researching and enriching leads, generating recurring reports, processing inbound requests, coordinating customer or operational workflows, transforming information between systems, and automating internal processes that previously required several tools and manual steps.

With the Ballet connector, Claude can interact with your Ballet environment to help users work with their agents, playbooks, and automated workflows.

31 tools reported — Live, but requires authorization before it will list tools. Publisher lists 31 tools.

Cargo

Cargo is GTM infrastructure for AI assistants. Connect this MCP server and Claude can operate your Cargo workspace: discover and run connector actions across 130+ integrations, execute tools and agents, query your CRM and revenue data models, and read the playbooks and context your team already wrote.

Sign in with OAuth — no API key to paste. Your session binds to one workspace, so Claude sees your integrations, your models, and your credits.

What you can do from chat: • Search the action catalog and see credit cost before anything runs • Enrich people and companies, look up CRM records, and call native platform ops • Run a single action or a batch across many records (with cost sampling before large runs) • Query workspace models with SQL-style selects, joins, and aggregates • Read workspace context — ICP definitions, playbooks, rubrics — before guessing how your team works

Ask in plain English. Claude finds the right action, confirms cost when it matters, and brings results back into the conversation.

Best for RevOps, sales ops, and GTM engineers who already live in Claude and want the research-to-action loop without leaving the chat. Building multi-step workflows, warehouse-wide SQL, or workspace-as-code deploys stays in the Cargo CLI — this connector is the runtime for in-conversation work.

Learn more: https://www.getcargo.ai/mcp

17 tools reported — Live, but requires authorization before it will list tools. Publisher lists 17 tools.

CircleCI

The CircleCI MCP Server is a remote server hosted by CircleCI that connects Claude directly to your CI/CD pipelines, giving you a conversational interface to the same pipeline, workflow, job, and artifact data you'd normally reach through the CircleCI CLI or dashboard.

With this connector, you can ask Claude to check the latest pipeline status for a project or roll back a deployment - all without leaving your conversation. When something breaks, Claude can pull the failure logs for a specific build and help you understand what went wrong, or dig into test results for a job to pinpoint which tests failed and why.

Beyond troubleshooting individual runs, the server supports broader pipeline health and efficiency work. Claude can identify underused resource classes to help you right-size compute and control costs, and list artifacts produced by your builds so you can retrieve build outputs without hunting through the UI.

It also helps with day-to-day project management: checking component versions across your fleet, and pulling usage data for cost and consumption analysis. For configuration work, it can act as a config helper - assisting with validating and troubleshooting your .circleci/config.yml setup.

In short, this MCP Server turns Claude into a working partner for CI/CD: monitoring pipeline health, debugging build and test failures, managing releases and rollbacks, and keeping an eye on cost and reliability - all through natural conversation rather than manual dashboard digging or CLI commands.

24 tools reported — Live, but requires authorization before it will list tools. Publisher lists 24 tools.

Coval

Connect Claude to your Coval workspace to inspect agents, test sets, test cases, personas, metrics, and evaluation runs. Build or update evaluation fixtures, launch safe chat and SMS evaluation runs, and ask Sofia for grounded, read-only analysis and recommendations. The Claude connector does not start voice, outbound voice, or WebSocket voice runs.

19 tools reported — Live, but requires authorization before it will list tools. Publisher lists 19 tools.

QA.tech

QA.tech uses agents to automatically verify changes to your product. They learn your product and verify changes, tests PRs dynamically and write reviews. Connect this MCP to interact with the QA.tech agents directly from Claude.

43 tools reported — Live, but requires authorization before it will list tools. Publisher lists 43 tools.

Manifestly

Manifestly brings structured workflow execution directly into Claude. Create and launch workflow runs, assign steps to team members, track completion status, and keep recurring processes on schedule without leaving your conversation. Search across your workflows and active runs to surface what’s in progress, what’s overdue, and who owns what. Get full read, write, and author access, with tools for managing checklists, approvals, step data, and audit trails across every department in your organization.

66 tools reported — Did not respond when Pod last checked.

TinyFish

Connect TinyFish to Claude to search, read, and operate the live web at scale. Three core tools cover the workflow: a search API to find relevant pages and sources across the web, a fetch API to read and extract content from URLs in a clean, token-efficient form, and a web agent to navigate complex, dynamic sites: logging in, filling and submitting forms, clicking through multi-step workflows, and extracting structured data that requires real page interaction. Powered by TinyFish's cloud browser infrastructure and proprietary web navigation model, it reaches sites that static fetching can't. Useful for researching across many sources, pulling live data from web apps, completing multi-step web workflows, monitoring or scraping pages behind navigation, and running the same web operation across many sites or URLs.

16 tools reported — Publisher-reported; not verified by Pod.

For agents

This page has a Markdown and a JSON twin. Pod is also queryable over MCP at https://api.askpod.ai/mcp/read.