Pod

Available as Markdown and JSON. Pod is also available over MCP.

MCP Servers with a search_tools tool

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

10 servers, ordered by decision readiness and adoption — GitHub stars and npm downloads where available, then reported issue volume. Pod has connected to 10 of them; the rest are publisher-reported and unverified.

1Stay

1Stay lets Claude search and book real hotel rooms from start to finish.

Search hundreds of thousands of hotels worldwide. Compare live rates, room types, and cancellation policies. Then book through a secure checkout page and get a real hotel confirmation number — the same one the front desk sees. Bookings are made in your name, so your loyalty points and status benefits stay intact.

Most travel connectors stop at search or hand you off to another website to finish. 1Stay takes you all the way through to a real reservation, and manages it afterward too.

What you can do: • Search hotels by location, dates, and guest count • Compare live rates, rooms, and cancellation terms • Book through secure checkout and get a real hotel confirmation number • Look up an existing reservation • Cancel a booking, with a clear refund-policy check before anything is final • Resend your confirmation email

Any 1Stay booking fee is itemized in your total before you confirm, and the hotel charges you separately for the stay.

Built by Stayker, whose booking technology has powered hotel reservations for customers for decades.

8 tools reported — Live. Answered with 8 tools.

Adspirer Ads & Performance Marketing Agent

Adspirer is your performance marketing and paid media agent — an AI performance marketer that works like a member of your team. Tell it what you want to achieve, and it understands the goal, builds the right campaigns across the right platforms, and runs them day to day. Create campaigns through conversation, not dashboards. Adspirer turns an objective like "more demos under a $50 cost-per-lead" into well-structured campaigns across Google, Meta, LinkedIn, and TikTok — then keeps working after launch. It paces spend so budgets land where you want them, shifts money toward what's converting, continuously harvests high-intent keywords and prunes the negatives draining budget, catches creative fatigue before it costs you, and flags anything that needs a human call. You set the strategy and approve the moves — new campaigns start paused, so nothing goes live without you. Adspirer manages multiple brands and accounts, and it's always adding new ad platforms.

96 GitHub stars · 18 tools reported — Live, but requires authorization before it will list tools. Publisher lists 18 tools.

Zernio

Zernio connects Claude to your social media workflow. Create and publish posts, manage content across channels, retrieve analytics, and work with your social accounts directly from Claude. Use it to draft and schedule content, review performance, discover top-performing posts, monitor account-level metrics, and streamline day-to-day social media operations—all through natural-language requests

11 GitHub stars · 52 tools reported — Live, but requires authorization before it will list tools. Publisher lists 52 tools.

Amazon Selling Partner

Connect your Amazon Seller Central account to Claude. Ask about sales, inventory, and listing performance and get recommendations grounded in your own data, not generic advice. Review and approve every action, without switching back to Seller Central. Currently in beta.

8 tools reported — Live, but requires authorization before it will list tools. Publisher lists 8 tools.

Cora

Connect Cora and bring your entire customer operation into Claude. Cora's Account Brain holds persistent memory across your CRM, support tickets, product usage, calls, and Slack, so every query is grounded in the whole customer relationship rather than one system's view of it.

Ask which accounts are at risk this quarter and what to do about them. Generate QBR summaries, prep docs, account briefs, and dashboards from live data. Update your CRM, send email and Slack, and assign tasks.

Then automate it. Build and schedule Cora agents that watch for signals and run the work themselves.

6 tools reported — Live, but requires authorization before it will list tools. Publisher lists 6 tools.

Funnel

Funnel brings all your marketing data, semantics, and business context to Claude in one trusted integration covering Google Ads, Facebook Ads (Meta), TikTok Ads, LinkedIn Ads, Google Analytics, Microsoft Advertising (Bing Ads), Shopify, HubSpot and 600+ other platforms. Ask questions like "Compare my spend, CPA, ROAS, and revenue across all my marketing channels in the last 6 months", "How am I pacing towards my budget and revenue target?", or "Which campaigns generated the most HubSpot pipeline?" and get the answers right where you do your work.

8 tools reported — Live, but requires authorization before it will list tools. Publisher lists 8 tools.

Nominal

Nominal is the Agentic Performance Management (APM) platform for finance teams — a layer of AI agents that sit on top of your existing ERP and execute the close, not just track it.

Nominal's agents run reconciliation, transaction matching, journal entry automation, intercompany elimination, and full-population flux analysis directly against a transaction-level mirror of your GL. Work is read-only by default; write-back to your ERP requires human approval, with every action logged for a complete, auditor-ready trail (SOC 1 Type 2 + SOC 2).

With the Nominal connector, Claude can query close status, reconciliation and matching results, intercompany activity, and variance findings across your entities and currencies — scoped to your own tenant and permissions.

Works with 70+ ERPs (SAP, NetSuite, Sage Intacct, Oracle, Workday, Microsoft Dynamics, QuickBooks, Xero, and more) with no migration required. Built for controllers and finance leaders running multi-entity, multi-currency close.

8 tools reported — Live, but requires authorization before it will list tools. Publisher lists 8 tools.

Recruit CRM

Work with your Recruit CRM data directly from Claude. Search, analyze, create, and update candidates, jobs, companies, contacts, tasks, meetings, notes, call logs, hotlists, hiring stages, pitch activity, and custom fields. Prepare client briefs, analyze job pipelines, assign candidates to jobs, update hiring stages, log recruiting activity, create follow-up tasks, and review account details before meetings. Use it for quick CRM updates or deeper recruiting workflow management, with answers and actions based on the records in your Recruit CRM account.

112 tools reported — Live, but requires authorization before it will list tools. Publisher lists 112 tools.

SnapVisor

SnapVisor is a visual regression testing platform. Your CI uploads screenshots as builds, SnapVisor pixel-diffs them against an approved baseline, and your team reviews and approves the changes it finds. This connector lets Claude work that review loop: list projects and builds, pull the diffs detected in a build, approve or reject a build, dismiss a review, ignore or un-ignore a flaky change, read tests and their changes, and run the conversation on builds, tests and media. It also covers administration: projects, automation rules, members and invites, deployments, analytics and the media library.

The connector exposes that REST API through two tools: search_tools returns typed TypeScript declarations for the operations that match your request (90 operations today), and execute_typescript runs a short program that calls them. Every call goes through the same handler, OAuth scope check and plan gate as the REST API. The operation catalog is generated from SnapVisor's own OpenAPI document, so it cannot drift from the product.

SnapVisor does not generate images: no browser engine in the backend, no media-generation dependency anywhere. It compares the screenshots your own CI produced using deterministic pixel math and returns them as signed links that expire after an hour. Builds and screenshots are uploaded by your CI through project-token endpoints kept off this surface, so Claude can read and review your screenshots but cannot capture, alter or fabricate one.

Connections use OAuth 2.1 with PKCE and dynamic client registration, through a consent screen where you choose which accounts the connection covers and can narrow the scopes. Authorized applications are listed under Settings with a revoke button. MCP access requires a paid SnapVisor plan; a free account is refused. Approving a build, removing a member or deleting media are real, visible actions for your team: ask Claude to show you first and confirm before it acts. Docs: snapvisor.io/docs/agents/mcp-server.

2 tools reported — Live, but requires authorization before it will list tools. Publisher lists 2 tools.

app.cotera.co

Cotera is where teams build AI agents on top of their own data and tools. This connector puts that workspace inside Claude: browse the agents you already have, build new ones, run them, and bring the output back into the conversation.

Build agents. Describe what an agent should do in plain markdown and Claude creates it in your workspace, with headings, lists, and code blocks intact. Prompts can reference your connected tools, your documents, and your other agents, so a new agent delegates work the same way one built in the Cotera editor does.

Find what to reference. Search the tools your workspace has connected — including whether each one is currently connected and ready to run — and search your documents, so an agent is wired to the real thing rather than to a guess.

Run them, one input or many. Run an agent against a single input, or start up to 50 runs in parallel over a list: a batch of leads, tickets, transcripts, or rows. Runs execute in the background, and you collect the outputs as they finish.

Read what you have. List every agent in the workspace, newest first, including ones your teammates built in the Cotera app, and read any agent's full prompt.

Everything happens in the workspace you authenticate with. Agents created here are ordinary Cotera agents — your team can open, edit, schedule, and share them in the app afterwards. Nothing is destructive: creating an agent never modifies an existing one, and running an agent never changes it.

Two things I deliberately kept in, since they're the details that make the listing trustworthy: the 50-run batch ceiling (the real MAX_BATCH_SIZE) and the read-only/non-destructive framing, which matches the tool annotations you ship.

8 tools reported — Live, but requires authorization before it will list tools. Publisher lists 8 tools.

For agents

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