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/Davmunrey/TrazumWrote 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/davmunrey/trazum/mcp-trazum)<a href="https://agentmods.dev/mcp/davmunrey/trazum/mcp-trazum"><img src="https://agentmods.dev/badge/mcp/davmunrey/trazum/mcp-trazum/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/davmunrey/trazum/mcp-trazum"><img src="https://agentmods.dev/badge/mcp/davmunrey/trazum/mcp-trazum.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
trazum 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 8d 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
{
"trazum": {
"command": "npx",
"args": [
"-y",
"@trazum/mcp"
],
"env": {}
}
}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.
- 8d ago First seen · 10 lines scan A ade5c9161dc8
trazum is an MCP server published in the GitHub repository Davmunrey/Trazum (1 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 2026-08-31.
Other mcp servers, from other repositories
llmtrim
MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost. Runs locally from the @llmtrim/cli npm package.
context-guardian-mcp
MCP server + proxy that cuts cloud LLM costs 36-42% by indexing context locally with Ollama and giving agents precision retrieval tools instead of raw dumps. Runs locally from the context-guardian-mcp npm package.
promptlint-mcp
Static linter for AI prompts: contradictions, redundancy, ambiguity, and fluff. Runs locally from the promptlint-mcp npm package.
llm-router-mcp
MCP server that routes prompts across Claude, Gemini, and GPT-4o to minimise token cost. Runs locally from the llm-router-mcp npm package.
tierline
MCP server "tierline" as configured in jayj221/tierline. Runs locally from the tierline npm package.
penny
Inspect your data. Find the truth! Runs locally from the penny Python package.