MCP Observatory
github analyzed 4247df4

Builder106/Halberd

github

A JSON-RPC firewall for MCP agents — inspects every tools/call between an LLM and its MCP servers, blocking argument injection and capability creep before they reach the host.

maintainer
Builder106
license
MIT
first seen
2026-06-04
last seen
2026-06-04
releases · 30d
0
short id
risk30/100 · heuristic grade
B low
  • capability exposureinferred+6
  • recent driftinferred+12
  • tool safetyinferred+12

inferred

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 12m ago · see ecosystem CVEs →

risk trajectory1 movements
  • A · 0 → B · 30
capability exposuregrade factor +6
Inferred surface — each links to servers holding it:
vulnerabilities0 CVEs

no known CVEs for this server.

tool safety1 findings · grade factor +12
  1. highdangerous code

    committed secret: GitHub token

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

analyzed commit 4247df4 · analyzer v17 · 2h ago

danger signals1

other grade factorsevidence elsewhere
embed badgereadme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/github:Builder106/Halberd/badge.svg)](https://mcpobservatory.com/servers/github:Builder106/Halberd/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 Builder106.