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/thangchung/agent-engineering-experimentWrote 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/thangchung/agent-engineering-experiment/vscode-markitdown)<a href="https://agentmods.dev/mcp/thangchung/agent-engineering-experiment/vscode-markitdown"><img src="https://agentmods.dev/badge/mcp/thangchung/agent-engineering-experiment/vscode-markitdown/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/thangchung/agent-engineering-experiment/vscode-markitdown"><img src="https://agentmods.dev/badge/mcp/thangchung/agent-engineering-experiment/vscode-markitdown.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
Grade A, and why
markitdown 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 6d 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
{
"markitdown": {
"command": "uvx",
"args": [
"markitdown-mcp"
],
"type": "stdio"
}
}What else mcp.json configures
This page is one entry in a file that holds 8. 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.
- 6d ago First seen · 9 lines scan A a36f828fb432
markitdown is an MCP server published in the GitHub repository thangchung/agent-engineering-experiment (25 stars, last pushed 7d 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 2026-09-16.
Other mcp servers, from other repositories
adeu
MCP server "adeu" as configured in dealfluence/adeu. Runs locally from the adeu-server Python package.
excel-csv-mcp-server
🚀 The Ultimate Data Science MCP Server - Advanced statistical analysis, ML preprocessing, and data visualization for Excel & CSV files. Runs locally from the excel-csv-mcp-server npm package.
mcp-itglue
IT Glue MCP server for MSPs — documents, flexible assets, semantic vector search, RBAC, and BYOK. Runs locally from the mcp-itglue npm package. Needs 9 environment variables to run.
mcp-google-docs
MCP server for the Google Docs API: read and edit documents, styles, tables, images, comments. Runs locally from the @a1-x-tech/mcp-google-docs npm package. Needs 8 environment variables to run.
google_sheets
MCP server "googlesheets", hosted remotely at gateway.pipeworx.io, as configured in pipeworx-io/mcp-googlesheets.
mistral-ocr-mcp
MCP server for extracting text and images from documents using Mistral OCR API. Runs locally from the mistral-ocr-mcp Python package.