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/acestein13/campusintel-mcpWrote 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/acestein13/campusintel-mcp/campusintel)<a href="https://agentmods.dev/mcp/acestein13/campusintel-mcp/campusintel"><img src="https://agentmods.dev/badge/mcp/acestein13/campusintel-mcp/campusintel/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/acestein13/campusintel-mcp/campusintel"><img src="https://agentmods.dev/badge/mcp/acestein13/campusintel-mcp/campusintel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
campusintel 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
{
"campusintel": {
"command": "uv",
"args": [
"--directory",
"/ABSOLUTE/PATH/TO/campusintel-mcp",
"run",
"campusintel-mcp"
],
"env": {
"OPENALEX_API_KEY": "YOUR_OPENALEX_API_KEY",
"COLLEGE_SCORECARD_API_KEY": "YOUR_COLLEGE_SCORECARD_API_KEY"
}
}
}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 · 15 lines scan A cae840a48165
campusintel is an MCP server published in the GitHub repository acestein13/campusintel-mcp (0 stars, last pushed 1mo 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
college-scorecard
College Scorecard MCP — US Department of Education College Scorecard API. Remote server at gateway.pipeworx.io.
openalex-mcp-server
Access the OpenAlex academic research catalog — 270M+ publications. Runs locally from the @cyanheads/openalex-mcp-server npm package. Needs 4 environment variables to run.
zurich-opendata
MCP server "zurich-opendata" as configured in malkreide/zurich-opendata-mcp. Runs zurich_opendata_mcp.server with python.
zurich-opendata-mcp
MCP Server for City of Zurich Open Data — 23 tools for CKAN, geodata, parliament, council resolutions, tourism, and real-time data across 6 APIs. Runs locally from the zurich-opendata-mcp Python package.
chinese-history-mcp
A traceable Chinese-history MCP server: 4 tools over 9 classical texts, every result cited (book→chapter→paragraph). Zero runtime dependencies. Runs locally from the chinese-history-mcp Python package.
pronunciation
Local MCP voice coach with English pronunciation, grammar, fluency, phoneme-level feedback, and practice drills. Runs locally from the mcp-server-pronunciation Python package. Needs 2 environment variables to run.