Jay Alexander Moore
Jay Alexander Moore • computational biology, cancer genomics, and neurodegeneration.
https://jaydata.bio/Opens ChatGPT on the web or desktop and asks it to use the WebMCP tools available here.
Connect straight to this server’s public endpoint.
https://mcp.jaydata.bio/mcpWe add this server to your workspace, then open Studio — saved access, one connection to many servers, with a history of what ran.
Last probed Sep 14, 2026 · mcp.jaydata.bio
4tools discovered
Cohort Summary
How many samples are in the cohort, and how do they split by tumour type? The orientation question, and the only tool that returns anything without an argument. It returns counts and nothing identifying, so it tells you the shape of the cohort without naming anyone in it. Every count is published as it is, because the fixture is invented and there is nobody in it to disclose.
Assay Results
What was recorded for one named sample? One sample at a time, on purpose, and the caller must already know the identifier. A tool that took a list, or took no argument at all, would be an export tool, and an export tool is a different risk class from a lookup. There is deliberately no tool on this server that returns the list of identifiers, so the individual-level route cannot be used to walk the cohort.
Biomarker Prevalence
What fraction of the cohort sits at or above a cut-off on one measurement? This is the question the surface exists for, because the routine ask is not "give me the table" but "is the biomarker-positive subgroup large enough to be worth an analysis". It answers with a numerator, a denominator and a proportion, and with nothing else. One thing constrains it. The marker is a closed vocabulary of four column names, so there is no free-text filter and no column that is not a parameter can be reache
Assay Qc
Is the assay data good enough to trust an answer from the other tools? The caveat that has to travel with the number. A TMB-high fraction computed over samples with low tumour purity or thin coverage is a statement about the assay and not about the disease, so this returns median purity and median depth alongside the count of samples falling below each floor. The floors are quoted in the result, because a QC count is unreadable without them. Counts only, and both floors are fixed in the server
Get your MCP into directories
A working endpoint is step one. Directory coverage is the coordinated launch across ChatGPT, Claude, Cursor, the MCP Registry, and community indexes.
Directory coverage for brandsJay Alexander Moore • computational biology, cancer genomics, and neurodegeneration.
Use the MCP endpoint listed on this page in your MCP client configuration. One-click install pills support Claude, Cursor, VS Code, and other hosts. Copy the remote MCP URL if your client needs a manual entry.
MCPBundles probed 4 tools on the live server. The tool list on this page reflects what was discovered at the last refresh — connect your client to see the full set available to your session.
No provider sign-in was required during MCPBundles' probe. Your client may still need MCPBundles credentials depending on how you connect.
Operate Takeda Demo Readonly? Verify ownership to take over this directory entry.
This server appears in the MCPBundles directory. Verify you operate it to take over the listing — name, description, logo, contact email, and skill content. We email a 6-digit code to a maintainer address your server publishes in /.well-known/security.txt or /.well-known/mcpbundles.json. Free, takes about a minute.