MCP Observatory
npm analyzed 2.9.5

@cyanheads/pubmed-mcp-server

v2.9.5
npm

Search PubMed/Europe PMC, fetch articles and full text (PMC/EPMC/Unpaywall), citations, MeSH terms via MCP. STDIO or Streamable HTTP.

maintainer
cyanheads
license
Apache-2.0
first seen
2026-05-22
last seen
2026-06-16
releases · 30d
36
short id
risk20/100 · heuristic grade
B low
  • capability exposureinferred+10
  • inherited (deps)attested+14
  • tool safetyinferred+4
  • trust mitigatorsmixed−8

attestedinferredmixed

The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.

graded 14m ago · see ecosystem CVEs →

risk trajectory3 movements
  • B · 15 → B · 20
  • B · 20 → B · 15
  • B · 26 → B · 20
capability exposuregrade factor +10
Inferred surface — each links to servers holding it:
vulnerabilities0 CVEs

no known CVEs for this server.

inherited (deps) · grade factor +14

inherited via dependencies3
HIGH
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse via @cyanheads/mcp-ts-core · 2 hops CVE-2026-25536 fixed in 1.26.0
HIGH
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability via @cyanheads/mcp-ts-core · 2 hops CVE-2026-0621 fixed in 1.25.2
HIGH
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default via @cyanheads/mcp-ts-core · 2 hops CVE-2025-66414 fixed in 1.24.0
tool safety2 findings · grade factor +4
  1. lowexfiltration combopubmed_search_articles

    single tool reads + sends: net, db

  2. lowexfiltration combopubmed_spell_check

    single tool reads + sends: net, db

skills & danger signalsnpm-tarball
prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed v2.9.5 · analyzer v17 · 55m ago

skills & prompt files 2

embed badgereadme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/smithery:cyanheads/pubmed-mcp-server/badge.svg)](https://mcpobservatory.com/servers/smithery:cyanheads/pubmed-mcp-server/security)

Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of cyanheads.