Harvey
Ask legal questions, query Vault projects and search research knowledge sources.

618 MCP servers with 12,363+ tools, ready to connect to Claude, ChatGPT, Cursor and Agentman agents over the Model Context Protocol.
618 connectors
Ask legal questions, query Vault projects and search research knowledge sources.
Check emails, domains and passwords against the HIBP breach corpus.
Read-only access to your own medical records, medications and wearable data in Health Data Avatar.
Read one patient's identified medical record — diagnoses, doses, labs, notes.
One tool, send_turn, hands a message to Enrich Labs' autonomous marketing agent.
Query Amazon keyword research, listing scores, P&L and ad performance.
Ask population-genomics questions across 500,000+ exome-sequenced participants with linked EHR.
Search your sales content library, answer seller questions and query CRM deals.
Query observability data, traces and SLOs.
Deploy sites and manage VPS, domains, DNS and email from an AI agent.
Search contacts, companies, deals and conversations — and create or update them.
Search models, datasets, papers and docs on the Hugging Face Hub, and call Gradio Spaces.
Build animated slides and motion graphics from HTML, then render them to video.
Query IBISWorld industry research — market size, financial ratios, risk scores, procurement data.
Look up, search and validate ICD-10-CM diagnosis and ICD-10-PCS procedure codes.
Query ICE fixed income evaluations, bond trades and reference data.
Query your IcePanel architecture model and decision records from an AI agent.
Search property listings in Spain, Italy and Portugal.
Run a virtual data room: projects, documents, groups, diligence Q&A.
Load a writing-voice profile, then draft, rewrite and score prose.
Run IFTTT actions, query services and create Applets.
Search, browse and read a law firm's document management system.
Query incidents, alerts, on-call schedules and telemetry, and declare or update incidents.
Search Indeed's job marketplace.
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.