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/s0fractal/warrantWrote 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/s0fractal/warrant/mcp-server-warrant)<a href="https://agentmods.dev/mcp/s0fractal/warrant/mcp-server-warrant"><img src="https://agentmods.dev/badge/mcp/s0fractal/warrant/mcp-server-warrant/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/s0fractal/warrant/mcp-server-warrant"><img src="https://agentmods.dev/badge/mcp/s0fractal/warrant/mcp-server-warrant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
warrant 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 10d 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
{
"warrant": {
"command": "uvx",
"args": [
"warrant-verify"
],
"env": {
"WARRANT_STORE": "",
"WARRANT_KEY": "",
"WARRANT_ACTOR": ""
}
}
}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.
- 10d ago First seen · 13 lines scan A dd16c963c1f6
warrant is an MCP server published in the GitHub repository s0fractal/warrant (5 stars, last pushed today), 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
matrixscroll
MCP server for signed machine-action records, offline tool-surface checks, and SSX360 USB signer support. Runs locally from the matrixscroll Python package.
universal_research
MCP server "universalresearch" as configured in mp-juns/universal-research-mcp. Launched with universal-research serve --no-auto-index.
universal-research-mcp
Governed MCP for provenance-first research memory, evidence re-verification, and controlled canonical ingestion. Runs locally from the universal-research-mcp Python package.
notarize
Canonical trace format and verifier for agent execution attestation. Runs locally from the notarize-ai Python package.
ai-audit-trail
Cryptographically verifiable audit trail for AI systems — Ed25519 signed, hash-chained Decision Receipts with ISO 42001 / NIST AI RMF compliance mappings. Runs locally from the ai-audit-trail Python package.
krait-solodit
MCP server "krait-solodit" as configured in ZealynxSecurity/krait. Runs mcp-servers/solodit/build/index.js with node.