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/decimal-labs/decimalai-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/decimal-labs/decimalai-mcp/registry)<a href="https://agentmods.dev/mcp/decimal-labs/decimalai-mcp/registry"><img src="https://agentmods.dev/badge/mcp/decimal-labs/decimalai-mcp/registry.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
registry 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 7d 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
{
"registry": {
"command": "uvx",
"args": [
"decimalai-mcp"
],
"env": {
"DECIMAL_API_KEY": ""
}
}
}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.
- 7d ago First seen · 11 lines scan A 27e5bb3d2f16
registry is an MCP server published in the GitHub repository decimal-labs/decimalai-mcp (1 stars, last pushed 2d 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
multivon-mcp
MCP server exposing multivon-eval + pdfhell as agent-callable tools. Drop into Claude Desktop, Cursor, Cline, or any MCP-compatible AI coding agent. Runs locally from the multivon-mcp Python package.
seo
Spot keyword demand rising or fading. Trend volume and growth signals. Free key at trendsmcp.ai. Remote server at seo.api.trendsmcp.ai.
council
Multi-model consensus: 2-6 frontier LLMs answer, an independent judge synthesises one answer. Runs locally from the tokonomix-council-mcp npm package. Needs 1 environment variable to run.
presentation-md
MCP server exposing all 14 presentation-md tools (render/export/audit/judge/scaffold/share/deploy/import/preview) to any MCP-compatible AI agent. Runs locally from the @presentation-md/mcp-server npm package.
flashalpha
MCP server "flashalpha", hosted remotely at lab.flashalpha.com, as configured in FlashAlpha-lab/flashalpha-mcp.
kaidn-mcp
Explain fraud verdicts with evidence, surface account rings, and see who has burned other operators. Runs locally from the @kaidn/mcp npm package. Needs 4 environment variables to run.