Kepler
Run citation-backed research on public company financials and export the Excel models as CSV.

618 MCP servers with 12,363+ tools, ready to connect to Claude, ChatGPT, Cursor and Agentman agents over the Model Context Protocol.
618 connectors
Run citation-backed research on public company financials and export the Excel models as CSV.
Query regulated medical-device lifecycle data — requirements, tests, risks, traceability.
Query and change a Kick bookkeeping ledger: categorize transactions, post journal entries, edit accounts, run reports.
Search 209K+ US foundations, 9.6M+ IRS 990 grant records and open grant programs.
Search flights on Kiwi.com from an AI assistant.
Report on campaigns and flows, query profiles and events, and create campaigns and templates.
Search your company's competitive intelligence, battlecards and win-loss evidence — and edit cards in the conversation.
Query Kpler maritime and commodities data — trade flows, AIS, refinery, LNG, freight, compliance risk.
Search Krisp transcripts, notes and action items.
Turn documents in a Kuliko study library into flashcards, quizzes, notes and summaries.
Search flights, hotels and flight-plus-hotel packages.
Browse bioinformatics data, launch Nextflow and Python workflows, monitor executions.
Draft, validate and submit performance reviews from your AI assistant.
Browse official legislation, regulations, case law and guidance across 100+ jurisdictions.
Search a public catalog of practitioner-written legal Agent Skills.
Search matters, contracts and knowledge in a LawVu tenancy, and create or delete records.
Look up US K-12 standards, break them into learning components, trace prerequisites.
Ask Japan's legal corpus — statutes, case law, guidelines, books — with citations.
Search primary legal sources across 237 jurisdictions.
Check attorney-plan access and send a matter to a real lawyer.
Read and send WhatsApp Business messages.
Query your company's bills, cards, expenses and ledger data.
Read and write an agent-native CRM.
Translate text and files from your AI assistant using LILT's enterprise platform.
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.