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/gmitch215/MyMCPWrote 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/gmitch215/mymcp/tabroom)<a href="https://agentmods.dev/mcp/gmitch215/mymcp/tabroom"><img src="https://agentmods.dev/badge/mcp/gmitch215/mymcp/tabroom/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/gmitch215/mymcp/tabroom"><img src="https://agentmods.dev/badge/mcp/gmitch215/mymcp/tabroom.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
tabroom 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
{
"tabroom": {
"type": "http",
"url": "https://mymcp.gmitch215.xyz/tabroom/mcp",
"headers": {
"X-Mcp-Upstream-Authorization": "${TABROOM_TOKEN}"
}
}
}What else .mcp.json configures
This page is one entry in a file that holds 4. 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.
- yesterday First seen · 9 lines scan A 597c332e6502
tabroom is an MCP server published in the GitHub repository gmitch215/MyMCP (7 stars, last pushed today), licensed MPL-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 2026-09-10.
Other mcp servers, from other repositories
kaneo
Official MCP server for Kaneo: manage tasks, projects, and labels from Claude and other MCP clients. Runs locally from the @kaneo/mcp npm package. Needs 2 environment variables to run.
artifact-use
MCP server "artifact-use", hosted remotely at artifacts.iofold.com, as configured in iofold/artifact-use.
gw1-mcp
MCP server "gw1-mcp", hosted remotely at gw1-mcp.graphmaxer.workers.dev, as configured in Graphmaxer/gw1-mcp.
mcp-typescript-starter
MCP server "mcp-typescript-starter" as configured in lukegskw/mcp-typescript-starter. Runs locally from the mcp-typescript-starter npm package.
ctx
Turn a GitHub repo or docs site into agent-ready context: pack it or search it, over MCP. Remote server at ctx.vanshul.com.
mcp
Read any web page as clean Markdown for AI agents: fetch, search, metadata, links. SSRF-safe. Remote server at mcp.vanshul.com.