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/Trushtonfactory/anthropic-admin-mcpInstalling this writes the configuration, not the program: `anthropic-admin-mcp` has to be on your PATH already, or the server will not start.
Wrote 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/trushtonfactory/anthropic-admin-mcp/anthropic-admin-readonly)<a href="https://agentmods.dev/mcp/trushtonfactory/anthropic-admin-mcp/anthropic-admin-readonly"><img src="https://agentmods.dev/badge/mcp/trushtonfactory/anthropic-admin-mcp/anthropic-admin-readonly/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/trushtonfactory/anthropic-admin-mcp/anthropic-admin-readonly"><img src="https://agentmods.dev/badge/mcp/trushtonfactory/anthropic-admin-mcp/anthropic-admin-readonly.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
anthropic-admin-readonly 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
{
"anthropic-admin-readonly": {
"command": "anthropic-admin-mcp",
"args": [
"--read-only"
],
"env": {
"ANTHROPIC_ADMIN_KEY": "sk-ant-admin-REPLACE_ME"
}
}
}What else claude_desktop_config.json configures
This page is one entry in a file that holds 3. 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 · 11 lines scan A 4870c21c1ecd
anthropic-admin-readonly is an MCP server published in the GitHub repository Trushtonfactory/anthropic-admin-mcp (0 stars, last pushed 5mo 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 2026-08-31.
Other mcp servers, from other repositories
ip-mcp
MCP server "ip-mcp" as configured in kitepon/IP-MCP. Runs locally from the ip-mcp Python package.
wingman
MCP server "wingman" as configured in adeoluwaadesina/wingman-mcp. Runs wingman with python.
ukr-vitalinguist-mcp
MCP server for Ukrainian language checking and authentic-rendering lookup. Wraps the public ukr.vitalinguist.com API as Model Context Protocol tools — install in Claude Desktop / Cursor / Cline / Windsurf / Continue and your AI can check grammar, detect surzhyk, and find natural Ukrainian phrasings on demand. Runs…
mcp
Search and post remote jobs, browse companies, check salaries, and find talent on Himalayas.app. Remote server at mcp.himalayas.app.
google-search-console-mcp
MCP server for Google Search Console: query performance data, inspect URLs, check indexing, and generate HTML SEO audit reports from Claude, Cursor, Zed, and any Model Context Protocol client. Runs locally from the mcp-google-search-console Python package. Needs 6 environment variables to run.
lorg-mcp-server
Shared, peer-validated knowledge archive for AI agents — search, contribute, and validate via MCP. Runs locally from the lorg-mcp-server npm package. Needs 1 environment variable to run.