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/wyj-IIRtyj/localterminal-liteWrote 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/wyj-iirtyj/localterminal-lite/localterminal-mcp-lite)<a href="https://agentmods.dev/mcp/wyj-iirtyj/localterminal-lite/localterminal-mcp-lite"><img src="https://agentmods.dev/badge/mcp/wyj-iirtyj/localterminal-lite/localterminal-mcp-lite/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/wyj-iirtyj/localterminal-lite/localterminal-mcp-lite"><img src="https://agentmods.dev/badge/mcp/wyj-iirtyj/localterminal-lite/localterminal-mcp-lite.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
localterminal-mcp-lite 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 12d 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
{ "localterminal-mcp-lite": { "command": "npx", "args": [ "-y", "localterminal-mcp-lite" ] } }
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.
- 12d ago First seen · 9 lines scan A 191162798d1d
localterminal-mcp-lite is an MCP server published in the GitHub repository wyj-IIRtyj/localterminal-lite (4 stars, last pushed 16d ago), licensed Apache-2.0. 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
reporelay
Bounded local MCP access to one approved repository for AI read/search and structured handoffs. Runs locally from the reporelay-mcp npm package.
lightworker
MCP server "lightworker" as configured in ncepuee/LightWorker. Runs locally from the lightworker Python package.
obsidian-writer
MCP server "obsidian-writer" as configured in studentepercaso/obsidian-bridge. Runs ./dist/server.mjs with node.
obsidian
MCP server "obsidian" as configured in studentepercaso/obsidian-bridge. Runs ./dist/server.mjs with node.
obsidian-manager
MCP server "obsidian-manager" as configured in studentepercaso/obsidian-bridge. Runs ./dist/server.mjs with node.
mcp
Persistent memory for AI agents, governed by the human and stored on their own machine. Runs locally from the @mnemosyne_os/mcp npm package. Needs 2 environment variables to run.