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/marmar9615-cloud/agentbridge-protocol/codex-plugin-agentbridgegit clone --depth 1 https://github.com/marmar9615-cloud/agentbridge-protocolGrade A, and why
agentbridge 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
{
"agentbridge": {
"command": "npx",
"args": [
"-y",
"@marmarlabs/agentbridge-mcp-server"
]
}
}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 · 9 lines scan A b58ec05bd82f
agentbridge is an MCP server published in the GitHub repository marmar9615-cloud/agentbridge-protocol (1 stars, last pushed 1mo 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
mcp
Authorize consequential AI agent actions before execution. Runs locally from the @decionis/mcp npm package. Needs 1 environment variable to run.
agentgate
Human-in-the-loop approval gateway for AI agents over MCP: request, decide, approve. Runs locally from the @agentkitai/agentgate-mcp npm package.
thumbgate
Pre-action gates that block AI agents from repeating known mistakes. Runs locally from the thumbgate npm package.
agentlens
Tamper-evident, SHA-256 hash-chained audit trail and observability for AI agents. Runs locally from the @agentkitai/agentlens-mcp npm package.
agentguard47
Read-only MCP server for coding-agent traces, alerts, costs, usage, and budget health. Runs locally from the @agentguard47/mcp-server npm package. Needs 2 environment variables to run.
regula
MCP server "regula" as configured in kuzivaai/getregula. Runs locally from the regula-ai Python package.