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.
npx agentmods add mcp/fish121380/auto-mouse/little-mouse-pointer-mouse-pointer-ui-contextgit clone --depth 1 https://github.com/Fish121380/auto-mouseWrote 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/fish121380/auto-mouse/little-mouse-pointer-mouse-pointer-ui-context)<a href="https://agentmods.dev/mcp/fish121380/auto-mouse/little-mouse-pointer-mouse-pointer-ui-context"><img src="https://agentmods.dev/badge/mcp/fish121380/auto-mouse/little-mouse-pointer-mouse-pointer-ui-context.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
mouse-pointer-ui-context 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 4d 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
{
"mouse-pointer-ui-context": {
"command": "./app/MousePointer.Windows.exe",
"args": [
"--mcp-stdio",
"--endpoint",
"http://127.0.0.1:49153/"
],
"cwd": ".",
"env": {
"MOUSE_POINTER_HTTP_PORT": "49153"
}
}
}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.
- 4d ago First seen · 14 lines scan A e689fdbd9a58
mouse-pointer-ui-context is an MCP server published in the GitHub repository Fish121380/auto-mouse (3 stars, last pushed 14d 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
dsh-continuity
Asset consistency and output verification for agent-generated game media: image, voice, music and SFX from local Vulkan backends with zero VRAM when idle, or from any OpenAI-shaped image/ASR API instead. Runs locally from the dsh-continuity Python package.
url-manager-mcp
URL Manager MCP Server — Agent-first web link collection & knowledge management. Runs locally from the url-manager-mcp Python package. Needs 2 environment variables to run.
decision_table
MCP server "decisiontable" as configured in tetracoralla/decision-table. Runs ./server/index.mjs with node.
mindraw_mcp
MCP server "mindrawmcp" as configured in 17lang/mindraw4agent. Launched with bash ./scripts/start-mcp.sh.
woven
MCP server "woven" as configured in Ducksss/LifeHack-2026. Runs ./node_modules/tsx/dist/cli.mjs with node. Needs 2 environment variables to run.
agent-audit
Turn Lighthouse audits into coding-agent fix packs for Claude Code, Cursor, and Copilot. Runs locally from the @fullstackdegen/agent-audit npm package.