Lucid
Search Lucidchart and Lucidspark docs, generate diagrams from a prompt, and share them by link.

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 Lucidchart and Lucidspark docs, generate diagrams from a prompt, and share them by link.
Send documents for e-signature, track them, and generate agreements from templates.
Search B2B contacts and companies, reveal verified emails and phone numbers, and pull buying signals.
Read, search and act on scanned postal mail in a LegalZoom Virtual Mail box.
Generate and edit Magic Patterns UI designs.
Run Make scenarios and manage your Make account from an AI assistant.
Check a link, phone number or email against Malwarebytes threat intelligence before you click, call or reply.
Check suspicious emails, texts and links for scams inside an AI chat, backed by McAfee's Scam Detector.
Search Medidata product documentation and rank clinical trial sites from an AI agent.
Run MeisterTask projects, tasks and Notes from an AI agent.
Query Korean music charts, your Melon listening history and DJ Mallang recommendations.
Search, create and organise a Mem knowledge base.
Search a private-capital firm's deals, companies, people and documents, and run its workflows.
Query interview transcripts, AI notes and recruiting data.
Anthropic’s connector for SharePoint, OneDrive, Outlook and Teams.
Search US federal and state case law, with answers grounded in verbatim opinion text and pin-cite deeplinks.
Ask an AI agent about your Pocket Capture leads, capture points and funnel.
Design, publish and analyse Ninout forms from an AI agent.
Query and edit NocoDB records from an AI agent.
Query a Nooks sales-engagement workspace — prospects, sequences, calls, transcripts.
Check suspicious messages, links and emails for scams in an AI chat, via Norton Genie.
Search, read, create and update Notion pages and databases.
Search O'Reilly books, videos, courses and events from an AI agent.
Pull keyword, SERP, backlink, site-audit and AI-citation data, plus Search Console and GA, into an AI agent.
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.