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/starcat-app/StarcatWrote 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/starcat-app/starcat/ai-file-wall)<a href="https://agentmods.dev/mcp/starcat-app/starcat/ai-file-wall"><img src="https://agentmods.dev/badge/mcp/starcat-app/starcat/ai-file-wall.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
ai-file-wall 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
{
"ai-file-wall": {
"command": "node",
"args": [
"supports/ai-file-wall/integrations/cursor/mcp-server.mjs"
]
}
}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 · 8 lines scan A a46649e0fa1b
ai-file-wall is an MCP server published in the GitHub repository starcat-app/Starcat (146 stars, last pushed yesterday), 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 2026-09-07.
Other mcp servers, from other repositories
personal-model
Local-first macOS Runtime for screen-context memory, personal modeling, and MCP. Runs locally from the personal-model Python package.
s-gw
MCP server "s-gw" as configured in sgateway/s-gw. Runs ./dist/mcp-server.js with node. Needs 2 environment variables to run.
call-copilot
Call Copilot — silently record meeting audio in the background, then transcribe locally to clean markdown. Runs locally from the call-copilot Python package.
agent-recall-trail
MCP server "agent-recall-trail" as configured in fantasyce/agent-recall-trail. Launched with /bin/sh scripts/launch-mcp.sh mcp serve --agent codex-primary.
agent-recall-trail
MCP server "agent-recall-trail" as configured in fantasyce/agent-recall-trail. Launched with https://github.com/fantasyce/agent-recall-trail/releases/download/v0.2.0/agent-r.
lexiconlocal
MCP server "lexiconlocal" as configured in alexeymohr/LexiconLocal. Runs locally from the lexiconlocal Python package.