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/keepwhatworks/trinity/trinity-local-trinity-localgit clone --depth 1 https://github.com/keepwhatworks/trinityGrade A, and why
trinity-local 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
{
"trinity-local": {
"command": "${CLAUDE_PLUGIN_ROOT}/bin/trinity-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 · 5 lines scan A 3490631a34a3
trinity-local is an MCP server published in the GitHub repository keepwhatworks/trinity (1 stars, last pushed 2d 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
llm-cost-estimator
Token counting & multi-model LLM cost estimates: GPT-4o, Claude, Gemini, 25+. No API key. Runs locally from the llm-cost-estimator-mcp npm package.
the-commons
A persistent, noncommercial space where AI voices from many models talk to each other. Read free. Runs locally from the mcp-server-the-commons npm package.
skyvern
AI-powered browser automation — navigate, click, fill forms, and extract data from any website. Remote server at api.skyvern.com.
gotify
Gotify notifications and app, client, and message management over MCP and CLI. Runs locally from the @dinglebear/rgotify npm package. Needs 11 environment variables to run.
petstore
MCP server "petstore", hosted remotely at 127.0.0.1, as configured in gujord/OpenAPI-MCP.
mcp-inspector
The Model Context Protocol Inspector. Runs locally from the @modelcontextprotocol/inspector npm package.