MCP Observatory
github analyzed 4ed0a48

universal-tool-calling-protocol/python-utcp

github

Official python implementation of UTCP. UTCP is an open standard that lets AI agents call any API directly, without extra middleware.

maintainer
universal-tool-calling-protocol
license
MPL-2.0
first seen
2026-05-22
last seen
2026-06-04
releases · 30d
0
short id
risk 53/100 · heuristic grade
C elevated
  • vulnerabilitiesattested+43
  • capability exposureinferred+10

attestedinferred

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 7m ago · see ecosystem CVEs →

risk trajectory 1 movements
  • D · 65 → C · 53
capability exposure grade factor +10
Inferred surface — each links to servers holding it:
vulnerabilities 3 CVEs · grade factor +43
HIGH
Full Process Environment Exposed to CLI Subprocess - Secrets Leakage via Command Injection EPSS 0% CVE-2026-45370 affects ["<= 1.1.1"]
HIGH
Command Injection via Unsanitized Argument Substitution in CLI Communication Protocol EPSS 0% CVE-2026-45369 affects ["<= 1.1.1"]
MEDIUM
SSRF via attacker-controlled OpenAPI servers[0].url in HTTP communication protocol EPSS 0% CVE-2026-44661 affects ["<= 1.1.2"]
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 github-tarball
prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed commit 4ed0a48 · analyzer v18 · 9h ago

skills & prompt files 1

embed badge readme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/github:universal-tool-calling-protocol/python-utcp/badge.svg)](https://mcpobservatory.com/servers/github:universal-tool-calling-protocol/python-utcp/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 universal-tool-calling-protocol.