MCP Observatory
2m ago Tracked 60,036 Last 2m ago 24h 2,463
pypi Python analyzed 1.24.17

n24q02m-mcp-core

v1.24.17
pypi

Unified MCP Streamable HTTP 2025-11-25 transport, OAuth 2.1 AS, lifecycle, install

maintainer
—
licence
Apache-2.0
first seen
2026-08-24
last seen
2026-09-19
releases · 30d
24
short id
risk 47/100 · heuristic grade
C elevated inferred analyzer v33 (current)
  • capability exposure inferred + 35
  • inherited (deps) attested + 15
  • trust mitigators mixed − 3

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 →

capability exposure grade factor +35
Inferred surface — each links to servers holding it:
vulnerabilities 0 CVEs

No known CVEs for this server.

inherited (deps) · grade factor +15

inherited via dependencies 8
HIGH
SSRF & Path Traversal Vulnerability in FastMCP OpenAPI Provider via PrefectHQ/fastmcp · 1 hop CVE-2026-32871
HIGH
Missing Consent Verification in OAuth Proxy Callback Facilitates Confused Deputy Vulnerabilities via PrefectHQ/fastmcp · 1 hop CVE-2026-27124
HIGH
FastMCP Auth Integration Allows for Confused Deputy Account Takeover via PrefectHQ/fastmcp · 1 hop
MEDIUM
Improper Resource Handling in FastMCP OAuth Proxy Enables Token Reuse Across MCP Servers via PrefectHQ/fastmcp · 1 hop CVE-2025-69196
MEDIUM
Command injection via server name in subprocess-backed install commands via PrefectHQ/fastmcp · 1 hop CVE-2025-64340
MEDIUM
Reflected XSS in client's callback page via PrefectHQ/fastmcp · 1 hop CVE-2025-62800
MEDIUM
Windows command injection in FastMCP Cursor installer via server_name via PrefectHQ/fastmcp · 1 hop CVE-2025-62801
LOW
Update to MCP 1.23+ via PrefectHQ/fastmcp · 1 hop
tool safety all quiet

No tool-safety findings — heuristic detectors run on the compute-risk cadence; a finding appears when a tool trips a rule.

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

analyzed v1.24.17 · analyzer v33 · 1h ago

danger signals1

  • over-broad OAuth scope https://mail.google.com/ n24q02m_mcp_core-1.24.17/tests/schema/test_types.py :101 "scopes": ["https://mail.google.com/"],
embed badge readme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/pypi:n24q02m-mcp-core/badge.svg)](https://mcpobservatory.com/servers/pypi:n24q02m-mcp-core/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.