MCP App Store
by KeenEthics
EvidenceSignal by XDS icon

EvidenceSignal by XDS MCP Server for ChatGPT

By The Experience Design Studio (XDS)

Overview

A research and reporting tool for medical-device marketing teams. Research public information about a device and assess what HCPs, patients/caregivers, administrators/payers and investors can understand. EvidenceSignal connects audience answers and communication priorities to cited sources, compares compatible competitor reports, and creates briefs to share with a marketing team. Optional observations record AI-platform responses separately from the evidence score. Source access limits are shown. Assessments are observational, not clinical or investment advice, valuations or compliance determinations.

How to connect

  1. ChatGPT: Open the EvidenceSignal by XDS listing in the ChatGPT app directory and choose Connect. ChatGPT listing EvidenceSignal by XDS exposes 6 tools here.

Tools

compare_reports

ChatGPT
Compare two to four saved product reports on shared audience questions. Suppress numerical ranking when indication, engine, audiences, methodology or demo/live mode differ. Communication support is not clinical superiority.

generate_questions

ChatGPT
Generate distinct HCP, Patient/Caregiver, Administrator/Payer and Investor question sets from a saved map. Optional follow-ups depend on retrieved implant/study context and competitors. Investor is supported for business context; Scientific is reserved and not yet supported.

get_question_journey

ChatGPT
Inspect one question's selected source excerpts (contact details redacted and marked), state, scoring contributions, reasoning and diagnosed gaps. Use IDs returned by get_report or assess_audiences. Does not collect new evidence.

get_report

ChatGPT
Retrieve a saved report by its unguessable ID, including scores, selected cited excerpts, source links, access limits and its report URL. Full source documents and internal metadata are omitted. The URL is shareable only with people who can access this server; this tool does not publish it.

get_scan_status

ChatGPT
Read a queued scan's status and completed report ID. Use get_report once complete. A failed scan is not a completed assessment.

start_scan

ChatGPT
Queue fresh public evidence collection and assessment. Returns a job ID; use get_scan_status later. Bedrock runs source-backed AI interpretation. Rules mode is an ungraded retrieval check. OpenAI requires separate configuration. Daily pilot limits apply. Optional visibility adds up to eight paid observed responses from ChatGPT and Gemini, one per audience/platform; no Claude coverage or visibility ranking.

Capabilities

Writes

Example Prompts

Click any prompt to copy it.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/evidencesignal-by-xds"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/evidencesignal-by-xds)