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.
npx agentmods add mcp/mateob6/claude-voice-interaction/razgit clone --depth 1 https://github.com/Mateob6/claude-voice-interactionWrote 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/mateob6/claude-voice-interaction/raz)<a href="https://agentmods.dev/mcp/mateob6/claude-voice-interaction/raz"><img src="https://agentmods.dev/badge/mcp/mateob6/claude-voice-interaction/raz.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
raz 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 4d 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
{ "raz": { "command": "uvx", "args": [ "raz" ] } }
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.
- 4d ago First seen · 8 lines scan A f1b828fe539e
raz is an MCP server published in the GitHub repository Mateob6/claude-voice-interaction (0 stars, last pushed 16d 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
memo
MCP server "memo" as configured in jagoff/memo. Launched with memo-mcp. Needs 10 environment variables to run.
noisy-coding
MCP server "noisy-coding" as configured in noisy/noisy-coding. Runs in Docker (docker.io/noisy/noisy-coding:2.13.3). Needs 1 environment variable to run.
mcp
MCP server "mcp", hosted remotely at mcp.speko.ai, as configured in SpekoAI/mcp.
mcp-macos-toolkit
MCP server "mcp-macos-toolkit" as configured in ContractorKeith/mcp-macos-toolkit. Runs locally from the mcp-macos-toolkit npm package.
mcp-mlx-launcher
MCP server "mcp-mlx-launcher" as configured in globalpocket/mcp-mlx-launcher. Runs locally from the mcp-mlx-launcher Python package.
brain
SHELET-compliant cognitive prosthetic for AI agents — 25 stratified MCP skills with structural citation discipline. Runs locally from the brain-mcp Python package. Needs 1 environment variable to run.