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/chicogong/ffvoice-engineWrote 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/chicogong/ffvoice-engine/ffvoice)<a href="https://agentmods.dev/mcp/chicogong/ffvoice-engine/ffvoice"><img src="https://agentmods.dev/badge/mcp/chicogong/ffvoice-engine/ffvoice/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/chicogong/ffvoice-engine/ffvoice"><img src="https://agentmods.dev/badge/mcp/chicogong/ffvoice-engine/ffvoice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ffvoice 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 1mo 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
{
"ffvoice": {
"command": "uvx",
"args": [
"ffvoice"
],
"env": {}
}
}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.
- 1mo ago First seen · 9 lines scan A 85f0112b580d
ffvoice is an MCP server published in the GitHub repository chicogong/ffvoice-engine (3 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
dialogue-transcriber
Transcribe interviews and panel discussions, identify who said what via speaker-embedding clustering, and relabel speakers in an interactive web UI. Runs locally from the dialogue-transcriber Python package.
local-mcp
MCP server "local-mcp", hosted remotely at localhost, as configured in microsoft/OpenAIWorkshop.
lean-explore
MCP server "lean-explore", hosted remotely at www.leanexplore.com, as configured in lean-explore/lean-explore.
augent
MCP server "augent" as configured in AugentDevs/augent. Launched with augent-mcp.
financial-analyst
MCP server "financial-analyst" as configured in mahak867/ai-projects-hub. Runs /FULL/PATH/TO/server.py with python. Needs 1 environment variable to run.
iterm-tmux
MCPretentious - Universal Terminal MCP. High-performance terminal automation for iTerm2 (WebSocket) and tmux (control mode). Cross-platform support with cursor position, colors, and layered screenshots. Runs locally from the mcpretentious npm package.