Consensus
Search 220M+ peer-reviewed papers from your AI assistant.

618 MCP servers with 12,363+ tools, ready to connect to Claude, ChatGPT, Cursor and Agentman agents over the Model Context Protocol.
618 connectors
Search 220M+ peer-reviewed papers from your AI assistant.
Ask in plain English how visitors behave on your site: funnels, journeys, page metrics, errors.
Up-to-date library docs for coding agents.
Look up French companies, SIREN/SIRET numbers, directors and establishments from INPI's Registre National des…
Deploy, scale and delete cloud workloads on AWS, GCP and Azure.
Ask natural-language questions about global chemistry, manufacturing and controls requirements.
Generate classroom-ready K-12 math diagrams.
Search Awaze's cottages.com UK holiday-rental inventory from an AI agent.
Query data Coupler.io imported from 400+ marketing, sales and finance platforms.
Search your organisation's Coursera catalogue and run an AI Role Play scenario in chat.
Search US case law, PACER dockets, judges and oral arguments, and verify a brief's citations against a real database.
Civil legal information for people going to court without a lawyer.
Read, write, reorganize and delete documents in a Craft space.
Ask which partners share an account, who can make a warm introduction, what moved this week.
Research private companies, funding rounds, investors and people.
Search and enrich B2B company and people data.
Read live crypto exchange market data: prices, order books, trades, candlesticks, instrument specs.
Query Cube semantic models, build dashboards and edit data models from an AI agent.
Run credit origination, company reports and portfolio risk review.
Run KYB, sanctions and PEP screening, UBO mapping and supplier risk.
Pull SEC-sourced fundamentals, filing text and stock prices, with a source link on every number.
Search DataCamp’s course catalogue, then authenticate for team admin and learning reports.
Search your data catalogue, trace column-level lineage, draft SQL and edit governance metadata.
Query consolidated actuals, budgets, forecasts and KPIs.
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.