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/iowarp/clio-kitWrote 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/iowarp/clio-kit/adios-pandas-mcp)<a href="https://agentmods.dev/mcp/iowarp/clio-kit/adios-pandas-mcp"><img src="https://agentmods.dev/badge/mcp/iowarp/clio-kit/adios-pandas-mcp/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/iowarp/clio-kit/adios-pandas-mcp"><img src="https://agentmods.dev/badge/mcp/iowarp/clio-kit/adios-pandas-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
pandas-mcp 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 10d 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.
This is a copy
77% identical to compression-mcp — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
{
"pandas-mcp": {
"command": "uvx",
"args": [
"clio-kit"
],
"env": {}
}
}What else server.json configures
This page is one entry in a file that holds 24. Installing the file brings all of them; each is measured and scanned on its own page.
- MCP server adios-mcp A not measured
- MCP server arxiv-mcp A not measured
- MCP server chronolog-mcp A not measured
- MCP server compression-mcp A not measured
- MCP server darshan-mcp A not measured
- MCP server geo-mcp A not measured
- MCP server geojson-mcp A not measured
- MCP server hdf5-mcp A not measured
- MCP server jarvis-mcp A not measured
- MCP server lmod-mcp A not measured
- MCP server ndp-mcp A not measured
- MCP server node-hardware-mcp A not measured
- MCP server parallel-sort-mcp A not measured
- MCP server paraview-mcp A not measured
- MCP server parquet-mcp A not measured
- MCP server plot-mcp A not measured
- MCP server sac-mcp A not measured
- MCP server scientific-catalog-mcp A not measured
- MCP server seismic-mcp A not measured
- MCP server slurm-mcp A not measured
- MCP server spack-mcp A not measured
- MCP server terrain-mcp A not measured
- MCP server web-mcp A not measured
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.
- 10d ago First seen · 9 lines scan A 758cca8c2bdc
pandas-mcp is an MCP server published in the GitHub repository iowarp/clio-kit (26 stars, last pushed 2d ago), licensed BSD-3-Clause. 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. It is 77% identical to compression-mcp, differing in 2 lines, and is treated as a copy.
Other mcp servers, from other repositories
ragbuddy
MCP server "ragbuddy" as configured in azmirizkifar20/RAGBuddy. Runs locally from the ragbuddy npm package.
md-vision
Read markdown with inlined images and index headings for agentic RAG workflows. Runs locally from the md-vision npm package.
darwin-rag
Local-first RAG knowledge base with hybrid search (BM25 + embeddings), exposed to AI agents via MCP — fully offline-capable. Runs locally from the darwin-rag Python package. Needs 4 environment variables to run.
mcp-server-azure-ai-search-preview
MCP server "mcp-server-azure-ai-search-preview" as configured in projectAcetylcholine/mcp-server-azure-ai-search-python-preview. Runs locally from the mcp-server-azure-ai-search-preview Python package.
custom-py-mcp-servers-including-rag
MCP server "custom-py-mcp-servers-including-rag" as configured in KaushalprajapatiKP/custom-MCP-servers. Runs locally from the Custom-py-mcp-servers-including-rag Python package.
mcp-vision-server
MCP server for image recognition via Kimi/Moonshot vision API. Works with Claude Code. Runs locally from the mcp-vision-server Python package.