
Prognyx MCP server
Which MCP servers are Prognyx's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-20
- Registry namecom.prognyx/oncology-intelligenceverified in the MCP registry
The registry name sits under prognyx.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-20
- Tools3
- Server calls itselfprognyx
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-20 the server answered initialize and tools/list without a sign-in. First answer in 2165 ms.
- Whether its tools do the product's job has not been judged yet.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP score96 of 100answers 90 · definitions 100 · context 100 · connects 100
- Answered100% of days8 of 8 daily checks
- Median first answer1983 ms
- Space in an agent's context≈ 494 tokensthe definitions of all its tools (3), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 3 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- not sure · Track competitor trial readouts before they affect a filing
- not sure · Review regulatory actions that shift a competitive position
- not sure · Decide the next move for one oncology asset
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
compare_trialsUp to three interventional ClinicalTrials.gov studies matching an asset or target AND an oncology indication, side by side: sponsor, phase, status, declared arms, primary outcomes, last update, registry URL. Active studies first, then…
search_registryLive landscape for a target, asset, company, indication or NCT number: total and active study counts, leading sponsors, phase mix, the most recently updated studies with URLs, and related Prognyx briefings. Counts for phases and sponsors…
search_briefingsPrognyx oncology competitive-intelligence briefings (each claim linked to a primary source) matching a drug, company, target or indication, newest first, with URL, date and summary.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"oncology-intelligence": {
"type": "http",
"url": "https://www.prognyx.com/api/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http prognyx https://www.prognyx.com/api/mcpclaude.ai, ChatGPT and other clients: add https://www.prognyx.com/api/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.