MCP Observatory
7m ago Tracked 26,548 Last 7m ago 24h 1,896
github Rust analyzed abaff79 unconfirmed MCP

SECBLOK/belay

github

Belay is an open-source, local-first security layer for AI coding agents (Claude Code, Codex, Cursor, OpenClaw, Hermes Agent and MCP) that blocks dangerous commands, secret leaks, and prompt injection at the tool-call boundary in under 100ms — no LLM in the decision path by default, no cloud, no phone-home.

maintainer
SECBLOK
license
AGPL-3.0
first seen
2026-08-01
last seen
2026-08-01
releases · 30d
3
short id

Drift inferred · capture-to-capture

  1. HIGH code analysis flagged committed secret in SECBLOK/belay
capabilities 0 tools
transport — counts 0 tools · 0 res · 0 prompts permission surface via code analysis

No tools enumerated yet for this server.

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

analyzed commit abaff79 · analyzer v28 · 1h ago

skills & prompt files 21

danger signals1

code evidence vv0.1.14 · github-tarball
evidence-backed findings quoted directly from the published source artifact — not inferred

code files: 413

network 1

  • net SECBLOK-belay-abaff79/web/src/lib/api.ts :39 const j = (p: string) => fetch(BASE + p).then((r) => r.json());

declared dependencies 23

  • @tauri-apps/api@^2
  • @tauri-apps/cli@^2
  • belayd@*
  • belay-channels@*
  • belay-server@*
  • belay-auth@*
  • scanner@*
  • belay-manage@*
  • clap@4
  • tokio@1
  • anyhow@1
  • serde_json@*
  • reqwest@0.12
  • belay-transport@*
  • hostname@0.4
  • httpmock@0.7
  • tempfile@3
  • serde@1
  • serde_yaml@0.9
  • regex@1
  • fancy-regex@0.13
  • sha2@0.10
  • unicode-normalization@0.1

perm:untrusted 1

  • untrusted SECBLOK-belay-abaff79/web/src/lib/api.ts :39 const j = (p: string) => fetch(BASE + p).then((r) => r.json());