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/anunanuuu-wq/grantguardWrote 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/anunanuuu-wq/grantguard/grantguard)<a href="https://agentmods.dev/mcp/anunanuuu-wq/grantguard/grantguard"><img src="https://agentmods.dev/badge/mcp/anunanuuu-wq/grantguard/grantguard/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/anunanuuu-wq/grantguard/grantguard"><img src="https://agentmods.dev/badge/mcp/anunanuuu-wq/grantguard/grantguard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
grantguard 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 9d 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
{ "grantguard": { "command": "uvx", "args": [ "grantguard" ] } }
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.
- 9d ago First seen · 8 lines scan A 6b01cc6cbaea
grantguard is an MCP server published in the GitHub repository anunanuuu-wq/grantguard (0 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
mcp-guardian
Security, cost, and health governance proxy for MCP infrastructure. Runs locally from the @mcp-guardian/server npm package. Needs 3 environment variables to run.
haldir
The guardian layer for AI agents — scoped sessions, AES-256-GCM secrets, hash-chained audit, policy proxy. Runs locally from the haldir Python package.
agence
AI governance MCP server — policy enforcement, skills, memory, multi-LLM consensus. Runs locally from the @l-agence/mcp-server-agence npm package. Needs 1 environment variable to run.
pseolint
Penalty-risk audit for programmatic SEO sites: verdict, risk score, and a fix manifest. Runs locally from the @pseolint/mcp npm package. Needs 2 environment variables to run.
cgr-capture
MCP server that captures agent judgments and outcomes as CGR substrate on GRAFOMEM Cloud. Runs locally from the grafomem-cgr Python package. Needs 6 environment variables to run.
arifos-mcp
mcp-name: io.github.ariffazil/arifos | .ariffazil/arifos | arifOS v1!2026.7.26 — Constitutional AI Governance Kernel. 8 kernel ABI capabilities → 6 public tools (arifverbnoun, generated from arifosmcp/abi/capabilityregistry.json), dynamic F1-F13 enforcement via ConstitutionKernel + FloorEvaluator, VAULT999 immutable…