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/arcaputo3/mcp-server-whisperWrote 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/arcaputo3/mcp-server-whisper/whisper)<a href="https://agentmods.dev/mcp/arcaputo3/mcp-server-whisper/whisper"><img src="https://agentmods.dev/badge/mcp/arcaputo3/mcp-server-whisper/whisper/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/arcaputo3/mcp-server-whisper/whisper"><img src="https://agentmods.dev/badge/mcp/arcaputo3/mcp-server-whisper/whisper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
whisper 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
{
"whisper": {
"command": "uv",
"args": [
"run",
"mcp-server-whisper"
],
"env": {
"OPENAI_API_KEY": "${OPENAI_API_KEY}",
"AUDIO_FILES_PATH": "${AUDIO_FILES_PATH}"
}
}
}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 · 13 lines scan A 8e69ec00060c
whisper is an MCP server published in the GitHub repository arcaputo3/mcp-server-whisper (60 stars, last pushed 4mo 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 2026-08-30.
Other mcp servers, from other repositories
openosint
AI-powered OSINT agent, MCP server, and CLI. Interactive REPL + 19 tools. Anthropic Claude or local Ollama. For authorized security research use only. Runs locally from the openosint Python package. Needs 5 environment variables to run.
multisim-mcp
Unofficial MCP server for NI Multisim Automation API. Runs locally from the multisim-mcp Python package. Needs 1 environment variable to run.
yaml-workflow
A lightweight workflow engine for CI/CD pipelines, data processing, and DevOps automation — define tasks in YAML, run anywhere. Runs locally from the yaml-workflow Python package.
mcp-fns-calc
A local MCP server for Russian tax calculations and checks of taxpayer status. It uses a hosted API for fiscal-status checks and needs an access token.
cfast-mcp
MCP server for CFAST (Fire and Smoke Transport), built on top of PyCFAST. Runs locally from the cfast-mcp Python package.
pyeye
MCP server "pyeye" as configured in okeefeco/pyeye-mcp. Runs locally from the ${CLAUDE_PROJECT_DIR:-.} Python package.