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/l-x-t/ng-agentic/figma-desktopgit clone --depth 1 https://github.com/L-X-T/ng-agenticGrade A, and why
figma-desktop 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
{
"figma-desktop": {
"command": "npx",
"args": [
"-y",
"@pyroprompts/mcp-stdio-to-streamable-http-adapter"
],
"type": "stdio",
"env": {
"URI": "http://127.0.0.1:3845/mcp"
}
}
}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 · 13 lines scan A 0070f0930ae2
figma-desktop is an MCP server published in the GitHub repository L-X-T/ng-agentic (7 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
context7
Gives the agent up-to-date documentation and code examples for libraries and frameworks, fetched on demand so answers are not stuck at the model's training cutoff. Runs locally from the @upstash/context7-mcp npm package.
deepwiki
Lets the agent read DeepWiki's AI-generated documentation of any public GitHub repository and ask questions about a codebase. Runs locally from the deepwiki-mcp npm package.
playwright
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
elicit
Elicitation MCP server. Runs locally from the @blizzy/mcp-elicit npm package.
docs-langchain
MCP server "docs-langchain", hosted remotely at docs.langchain.com, as configured in langchain-ai/langchain.
reference-langchain
MCP server "reference-langchain", hosted remotely at reference.langchain.com, as configured in langchain-ai/langchain.