About research-intel
Research GTM triggers: new NIH grants by PI/institution and new clinical trials by sponsor/phase
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://research.dropwatchhq.com/mcpclaude mcp add --transport http com-dropwatchhq-research-intel https://research.dropwatchhq.com/mcp{"mcpServers":{"com-dropwatchhq-research-intel":{"type":"http","url":"https://research.dropwatchhq.com/mcp"}}}Open in Cursor{"servers":{"com-dropwatchhq-research-intel":{"type":"http","url":"https://research.dropwatchhq.com/mcp"}}}Open in VS Code{"mcpServers":{"com-dropwatchhq-research-intel":{"type":"http","url":"https://research.dropwatchhq.com/mcp"}}}{"mcpServers":{"com-dropwatchhq-research-intel":{"serverUrl":"https://research.dropwatchhq.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
5| Parameter | Type | Required | Description |
|---|---|---|---|
| ic | string | No | NIH Institute/Center abbreviation, e.g. 'NCI'. |
| pi | string | No | Principal investigator name substring. |
| kind | string | No | 'grant' or 'trial' to restrict. |
| limit | number | No | Max per kind (default 50). |
| phase | string | No | Trial phase substring, e.g. 'PHASE2'. |
| state | string | No | 2-letter US state of the org/site. |
| topic | string | No | Canonical topic slug, e.g. 'oncology', 'neuroscience'. |
| keyword | string | No | |
| sponsor | string | No | Trial sponsor name substring. |
| maxAmount | number | No | |
| minAmount | number | No | |
| institution | string | No | Institution name substring. |
| sponsorClass | string | No | INDUSTRY | NIH | OTHER_GOV | OTHER | INDIV. |
Details
The maintainer has not added details yet. Check the README in the repository.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.