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.
git clone --depth 1 https://github.com/Auties00/CobaltWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/auties00/cobalt/debugger)<a href="https://agentmods.dev/mcp/auties00/cobalt/debugger"><img src="https://agentmods.dev/badge/mcp/auties00/cobalt/debugger/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/auties00/cobalt/debugger"><img src="https://agentmods.dev/badge/mcp/auties00/cobalt/debugger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
debugger 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 1mo ago.
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
{
"debugger": {
"type": "http",
"url": "http://127.0.0.1:29190/debugger-mcp/streamable-http"
}
}What else .mcp.json configures
This page is one entry in a file that holds 2. Installing the file brings all of them; each is measured and scanned on its own page.
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.
- 1mo ago First seen · 6 lines scan A 79314e7b34ff
debugger is an MCP server published in the GitHub repository Auties00/Cobalt (927 stars, last pushed 3mo ago), licensed MIT. 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 2026-08-30.
Other mcp servers, from other repositories
dbgprobe-mcp-server
Debug probe Model Context Protocol server for AI agents and developer tooling. Runs locally from the dbgprobe-mcp-server Python package. Needs 9 environment variables to run.
repo-lens-mcp
MCP server for multi-repository AST-based symbol search and API route discovery. Runs locally from the repo-lens-mcp npm package.
broken-link-checker-mcp
MCP server "broken-link-checker-mcp" as configured in davinoishi/BLC-ground. Runs locally from the broken-link-checker-mcp Python package.
rea
Reverse engineer anything from your terminal or agent with one CLI and MCP server. Runs locally from the rea-agents npm package.
bls-mcp
MCP server "bls-mcp", hosted remotely at 127.0.0.1, as configured in openai/openai-cookbook.
mcp-search
MCP server "mcp-search" as configured in thedotmack/claude-mem. Runs const f=require('fs'),p=require('path'),o=require('os');const h=o.homedir();const C=process.env.CLAUDE_CONFIG_DIR||p.join(h,'.claude');const E=process.env.CLAUDE_PLUGIN_ROOT||process.env.PLUGIN_ROOT||'';const d=process.cwd();const S=n=>{const…