MCP Observatory
1m ago Tracked 58,273 Last 1m ago 24h 2,653
github TypeScript analyzed b654261

modelcontextprotocol/typescript-sdk

github

The official TypeScript SDK for Model Context Protocol servers and clients

maintainer
modelcontextprotocol
licence
NOASSERTION
first seen
2026-08-04
last seen
2026-09-12
releases · 30d
0
short id
risk 89/100 · heuristic grade
E critical inferred analyzer v33 (current)
  • vulnerabilities attested + 50
  • capability exposure inferred + 35
  • tool safety inferred + 12
  • trust mitigators mixed − 8

attested inferred mixed

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.

grade last moved 1w ago · see ecosystem CVEs →

risk trajectory 1 movements
  • C · 39 → E · 89
capability exposure grade factor +35
Inferred surface — each links to servers holding it:
vulnerabilities 3 CVEs · grade factor +50
HIGH
DNS Rebinding Protection Disabled by Default in Model Context Protocol TypeScript SDK for Servers R… EPSS 1% CVE-2025-66414 affects ["< 1.24.0"]
HIGH
Regular Expression Denial of Service (ReDoS) in UriTemplate EPSS 0% CVE-2026-0621 affects ["<1.25.2"]
HIGH
Sharing server/transport instances can leak cross-client response data EPSS 0% CVE-2026-25536 affects [">= 1.10.0, <= 1.25.3"]
tool safety 1 findings · grade factor +12
  1. high dangerous code

    credential logged in 1 file(s)

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

analyzed commit b654261 · analyzer v33 · 5h ago

skills & prompt files 3

danger signals1

embed badge readme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/github:modelcontextprotocol/typescript-sdk/badge.svg)](https://mcpobservatory.com/servers/github:modelcontextprotocol/typescript-sdk/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 modelcontextprotocol.