github JavaScript analyzed 2bf6d23 deep scan · partial (324/4,223 files)

ooples/token-optimizer-mcp

v6.0.2
github

Measure token savings per AI coding agent, optimize context, and share a live local knowledge graph across 16 CLI clients.

maintainer
ooples
licence
MIT
first seen
2026-06-01
last seen
2026-09-17
releases · 30d
9
short id
risk 56/100 · heuristic grade
C elevated inferred analyzer v33 (current)
  • vulnerabilities attested + 25
  • capability exposure inferred + 35
  • tool safety inferred + 12
  • supply-chain attested + 6
  • trust mitigators mixed − 22

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 13 movements
  • D · 64 C · 56
  • C · 52 D · 64
  • C · 54 C · 52
  • B · 29 C · 54
  • B · 32 B · 29
  • C · 44 B · 32
  • C · 52 C · 44
  • C · 59 C · 52
  • C · 54 C · 59
  • C · 57 C · 54
  • D · 67 C · 57
  • D · 75 D · 67
  • D · 67 D · 75
capability exposure grade factor +35
Inferred surface — each links to servers holding it:
vulnerabilities 2 CVEs · grade factor +25
HIGH
OS command injection in smart_user via username in get-user-info CVE-2026-55157 affects ["5.0.1"]
MEDIUM
Unauthenticated Path Traversal in Dashboard Session Log API Endpoints CVE-2026-55156 affects ["5.0.1"]
tool safety 3 findings · grade factor +12
  1. high dangerous code

    committed secret: Anthropic key · obfuscated payload: dynamic require()/import()

  2. low dangerous code

    env-secret-flows-to-network-js: A process environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a ke

  3. low dangerous code

    env-secret-flows-to-network-js: A process environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a ke

skills & danger signals github-tarball
other grade factors evidence elsewhere
embed badge readme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/github:ooples/token-optimizer-mcp/badge.svg)](https://mcpobservatory.com/servers/github:ooples/token-optimizer-mcp/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 ooples.