Developers · MCP
Feasibility as an MCP server — use it from Claude, Cursor, or your own agent.
MCP is an open standard that lets AI assistants call external tools. Connect ours and ask for a cited feasibility verdict in plain language — citations and audit hash included.
Six deterministic scorers, exposed as tools.
Tools we expose
Six deterministic tools, every result cited.
The same scorers that power the product, callable directly by your agent.
run_feasibilitycitedRun a full cited feasibility verdict
get_ptrscitedProbability of technical & regulatory success
get_site_densitycitedEligible site & investigator density
estimate_budgetcitedPer-patient & study budget envelope
get_citationscitedCitations behind any number
get_audit_trailcitedTamper-evident audit chain
Every tool result carries the same citations and audit hash as the API.
Connect
Add the server to your client.
Drop the config into your MCP client, set your API key, and the tools appear.
Claude Desktop / Cursor
{
"mcpServers": {
"feasibility": {
"url": "https://mcp.feasibility.example.com/sse",
"headers": {
"Authorization": "Bearer ${FEASIBILITY_API_KEY}"
}
}
}
}Your own agent (TypeScript SDK)
import { Client } from '@modelcontextprotocol/sdk/client/index.js';
import { SSEClientTransport } from '@modelcontextprotocol/sdk/client/sse.js';
const client = new Client({ name: 'my-agent', version: '1.0.0' });
await client.connect(
new SSEClientTransport(new URL('https://mcp.feasibility.example.com/sse'), {
requestInit: {
headers: { Authorization: `Bearer ${process.env.FEASIBILITY_API_KEY}` },
},
}),
);
const { content } = await client.callTool({
name: 'run_feasibility',
arguments: { protocol: 'A Phase 2 RCT in early Alzheimer\'s disease …' },
});See a verdict you can actually check.
Send us a protocol. We'll return a fully cited feasibility verdict you can trace, line by line, back to public data — yours to white-label, defend in a bid, or hand to a regulator.