Seismic
Search your sales-enablement library and mint trackable LiveSend links.

618 MCP servers with 12,363+ tools, ready to connect to Claude, ChatGPT, Cursor and Agentman agents over the Model Context Protocol.
234 of 618 connectors in ProductivityShow all
Search your sales-enablement library and mint trackable LiveSend links.
Query live HR data — headcount, org charts, time off, reviews, surveys.
Buy shipping labels, compare rates and track packages.
Manage a Shopify store.
Track contracts, query an AI-analysed repository, send signature requests.
Send documents for e-signature, mint signing links and track invites.
Query website traffic, audience, referral and app-store data.
Search a Slack workspace and send messages, reactions and canvases.
Generate a full presentation deck from a prompt and re-theme it without leaving the chat.
Search your Slite workspace and draft, edit and organize docs from an AI agent.
Machine translate text, manage translation jobs and triage quality issues.
Search US hourly job listings with no account.
Search Spinach recordings, summaries and action items.
Search Spotify, build playlists and manage your library via an AI agent.
Run the Storyblok Management API from an AI agent.
Search StubHub's live event catalog and browse resale ticket listings from an AI agent.
Create docs, build tables, run formulas and search your workspace from an AI assistant.
Search your inbox, draft in your voice, manage your calendar and send email from an AI assistant.
Build surveys, publish public response links and read respondent data from your AI assistant.
Read Sybill call transcripts, recordings, deals and CRM accounts, and ask its sales reasoning a question.
Search meetings and read Google Meet, Zoom and Teams transcripts.
Build Tally forms from a sentence and read the responses back without exporting a CSV.
Check Taskrabbit availability and pricing, and list local services.
Query jobs, candidates and pipelines, move applications between stages, manage todos.
Product names and logos belong to their owners. Each connector is built by its own developer, and Agentman is not affiliated with them. The ones Agentman builds and runs are marked “Built and run by Agentman”.
A server that exposes a tool’s capabilities over the Model Context Protocol, so an AI agent can call them directly. It is the standard way to let an assistant act in a system rather than just describe it.
Each server page carries its connection URL, which works in any MCP-compatible client. In Agentman Studio connecting is one click and there is no config file to edit.
Most are not. Each is built by its own developer, and each page names them and links to their documentation. The few Agentman builds and runs are marked “Built and run by Agentman”. Every page lists what the server exposes and cites the sources its factual claims come from.
Each page lists the tools the server exposes. Where we could read the server directly, every tool carries the safety label its vendor gave it: read-only, acts, or destructive. Each page also has a Limits section; read both before connecting anything to a production system.
Connect any of these once and your agents call their tools on their own: on a schedule, in a workflow, with nobody at the keyboard.