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/Thru-Echoes/TRACEWrote 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/thru-echoes/trace/trace)<a href="https://agentmods.dev/mcp/thru-echoes/trace/trace"><img src="https://agentmods.dev/badge/mcp/thru-echoes/trace/trace/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/thru-echoes/trace/trace"><img src="https://agentmods.dev/badge/mcp/thru-echoes/trace/trace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
trace 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
{
"trace": {
"command": "uvx",
"args": [
"--from",
".",
"--with",
"openai",
"--with",
"numpy",
"--with",
"fastembed",
"--refresh-package",
"trace-mcp",
"trace-mcp"
],
"env": {
"TRACE_PROJECT": "trace-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.
- 4d ago Changed 5bced76ea1bd
- 1mo ago First seen · 21 lines scan A adf43307a458
trace is an MCP server published in the GitHub repository Thru-Echoes/TRACE (25 stars, last pushed 4d 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 2026-08-30.
Other mcp servers, from other repositories
novyx-mcp
MCP tools for Novyx governed actions, shared memory, audit, rollback, and evidence workflows. Local SQLite memory works zero-config; hosted governance and approvals use Novyx Cloud. Runs locally from the novyx-mcp Python package.
paceproof
Verifies Ed25519-signed attestation records and builds audit reports via MCP tools. Runs locally from the paceproof-cli npm package.
evermint-mcp
Mint tamper-evident receipts for AI agent actions. The notary layer for agent-to-agent transactions. Runs locally from the evermint-mcp npm package. Needs 1 environment variable to run.
agent-harness-kit
Another Handler Knex. Runs locally from the ahk npm package.
agentic-observability
Agent tracing, cost tracking, anomaly detection for LLM agents. Runs locally from the agentic-observability-mcp npm package.
compliance-shield
ZATCA, UAE CT, EU AI Act regulatory compliance for AI agents. Runs locally from the compliance-shield-mcp npm package.