MCP Observatory
github re-analysis due

KazeFreeze/actual-budget-mcp

github

MCP server for Actual Budget — direct @actual-app/api SDK, 52 tools, Streamable HTTP/SSE/stdio transports

maintainer
KazeFreeze
license
MIT
first seen
2026-06-07
last seen
2026-06-15
releases · 30d
3
short id
risk 25/100 · heuristic grade
B low
  • capability exposureinferred+16
  • tool safetyinferred+12
  • trust mitigatorsmixed−3

inferredmixed

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 11m ago · see ecosystem CVEs →

risk trajectory 1 movements
  • C · 44 → B · 25
capability exposure grade factor +16
Inferred surface — each links to servers holding it:
vulnerabilities 0 CVEs

No known CVEs for this server.

tool safety 1 findings · grade factor +12
  1. hightool shadowingquery

    tool "query" shadows a verified server's tool

    shadows burtthecoder/mcp-shodan

embed badge readme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/github:KazeFreeze/actual-budget-mcp/badge.svg)](https://mcpobservatory.com/servers/github:KazeFreeze/actual-budget-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 KazeFreeze.