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/CSOAI-ORG/mitre-atlas-mcpWrote 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/csoai-org/mitre-atlas-mcp/mitre-atlas-mcp)<a href="https://agentmods.dev/mcp/csoai-org/mitre-atlas-mcp/mitre-atlas-mcp"><img src="https://agentmods.dev/badge/mcp/csoai-org/mitre-atlas-mcp/mitre-atlas-mcp/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/csoai-org/mitre-atlas-mcp/mitre-atlas-mcp"><img src="https://agentmods.dev/badge/mcp/csoai-org/mitre-atlas-mcp/mitre-atlas-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mitre-atlas-mcp 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 12d 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
{
"mitre-atlas-mcp": {
"command": "uvx",
"args": [
"mitre-atlas-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.
- 12d ago First seen · 8 lines scan A 22c11e77d9b7
mitre-atlas-mcp is an MCP server published in the GitHub repository CSOAI-ORG/mitre-atlas-mcp (0 stars, last pushed 2mo 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
dora-nis2-crosswalk-mcp
DORA × NIS2 Crosswalk MCP — map Regulation (EU) 2022/2554 obligations to Directive (EU) 2022/2555 Article 21-23 measures, and vice versa. For EU banks, insurers, payment institutions, crypto-asset service providers, and their CTPPs (critical ICT third-party providers). Dual-compliance scoring + HMAC-signed…
releaseguard
Scan a dataset or model directory for PII and secrets, redact what you find, and package a public-release bundle with a Hugging Face dataset/model card and an EU AI Act Art. 53(1)(d) training-data summary -- generated from the scan, not hand-written. Runs locally from the releaseguard-cli Python package.
faker-ai-mcp
MCP server for faker ai. Features fake person, fake company, fake dataset. From MEOK AI Labs. Runs locally from the faker-ai-mcp Python package.
json-ai-mcp
AI-powered json ai MCP server for agents. Supports validate json, transform json, diff json. By MEOK AI Labs. Runs locally from the json-ai-mcp Python package.
keyword-extractor-ai-mcp
Keyword Extractor Ai tools for AI agents. Capabilities: extract keywords, extract phrases, topic classification. Built by MEOK AI Labs. Runs locally from the keyword-extractor-ai-mcp Python package.
rag-knowledge-graph-mcp
Rag Knowledge Graph automation via MCP. Includes index document, rag query, add graph edge. By MEOK AI Labs. Runs locally from the rag-knowledge-graph-mcp Python package.