Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add mcp/heossihq/bee-public/python-bee-publicgit clone --depth 1 https://github.com/heossihq/bee-publicGrade A, and why
bee-public scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"bee-public": {
"command": "uvx",
"args": [
"bee-sdk"
],
"env": {
"BEE_API_KEY": "",
"BEE_MODEL": "",
"BEE_API_URL": ""
}
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 13 lines scan A 0e7ee22bf794
bee-public is an MCP server published in the GitHub repository heossihq/bee-public (1 stars, last pushed 5d ago), licensed Apache-2.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
openosint
AI-powered OSINT agent, MCP server, and CLI. Interactive REPL + 19 tools. Anthropic Claude or local Ollama. For authorized security research use only. Runs locally from the openosint Python package. Needs 5 environment variables to run.
mcp
MCP server "mcp" as configured in vulncheck-oss/mcp. Runs in Docker (ghcr.io/vulncheck-oss/mcp:0.2.1).
halo
MCP server "halo" as configured in XenoCoreGiger31/GEMMA-by-GOOGLE. Launched with XenoCoreGiger31/GEMMA-by-GOOGLE mcp_server.py. Needs 4 environment variables to run.
malware-sandbox-mcp
MCP server "malware-sandbox-mcp" as configured in inadvisable-hibiscusfarragei279/Malware-Sandbox-mcp. Runs locally from the malware-sandbox-mcp Python package.
zugashield
AI Agent Security System - 7-layer defense against prompt injection, data exfiltration, and AI-specific attacks. Runs locally from the zugashield Python package.
white-hat-agent
MCP server "white-hat-agent" as configured in kappa9999/white-hat-agent. Runs locally from the white-hat-agent Python package.