A local safety layer for AI agents that checks tool calls before they run and can block them, pause them for human approval, or detect changes in agent behaviour.

Use it to enforce fixed rules around MCP calls, require approval for selected actions, and monitor whether an agent's behaviour is drifting.

It adds a checkpoint before an agent carries out an MCP tool action, helping prevent risky or unexpected operations from running automatically.

promptspeak — MCP server for Claude Code by chrbailey

Install

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.

Clone the repo

git clone --depth 1 https://github.com/chrbailey/promptspeak-mcp-server

Made for: Claude Code.

Or install promptspeak, the plugin that ships this one along with the rest of its 3 skills, 1 MCP server.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/mcp/chrbailey/promptspeak-mcp-server/promptspeak/github.svg)](https://agentmods.dev/mcp/chrbailey/promptspeak-mcp-server/promptspeak)

Your own site

<a href="https://agentmods.dev/mcp/chrbailey/promptspeak-mcp-server/promptspeak"><img src="https://agentmods.dev/badge/mcp/chrbailey/promptspeak-mcp-server/promptspeak/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.

Your own site · 80×15

<a href="https://agentmods.dev/mcp/chrbailey/promptspeak-mcp-server/promptspeak"><img src="https://agentmods.dev/badge/mcp/chrbailey/promptspeak-mcp-server/promptspeak.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

promptspeak 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.

.mcp.json · 8 lines

What it actually says

{
  "promptspeak": {
    "command": "npx",
    "args": [
      "promptspeak-mcp-server"
    ]
  }
}

Changes

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 · 8 lines scan A 3b9ead3ae561

Subscribe to this mod's changes

promptspeak is an MCP server published in the GitHub repository chrbailey/promptspeak-mcp-server (1 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.

Building agents Security agent-governance ai-governance mcp mcp-server model-context-protocol pre-execution-blocking

music-production-ai-mcp

Music Production Ai automation via MCP. Includes generate chord progression, detect tempo, find key. By MEOK AI Labs. Runs locally from the music-production-ai-mcp Python package.

CSOAI-ORG/music-production-ai-mcp · not measured

sql-builder-ai-mcp

Sql Builder Ai automation via MCP. Includes build select, build insert, explain query. By MEOK AI Labs. Runs locally from the sql-builder-ai-mcp Python package.

CSOAI-ORG/sql-builder-ai-mcp · not measured

dora-compliance-mcp

DORA (EU Digital Operational Resilience Act) compliance for AI agents. 5-pillar audit, incident classification, Article 28 Register of Information, TLPT readiness. Regulation (EU) 2022/2554. By MEOK AI Labs. Runs locally from the dora-compliance-mcp Python package.

CSOAI-ORG/dora-compliance-mcp · not measured

qidi-printer-mcp

QIDI 3D Printer MCP server. Controls QIDI 4 Max Combo via Moonraker REST API. Tools: printer status, temperatures, start/pause/resume/cancel print, list files, send gcode, preheat. Built by MEOK AI Labs. Runs locally from the qidi-printer-mcp Python package.

CSOAI-ORG/qidi-printer-mcp · not measured

iso-42001-ai-mcp

AI-powered iso 42001 ai MCP server for agents. Supports audit management system, assess ai risk, generate policy template. By MEOK AI Labs. Runs locally from the iso-42001-ai-mcp Python package.

CSOAI-ORG/iso-42001-ai-mcp · not measured

cra-compliance-mcp

EU Cyber Resilience Act (Regulation 2024/2847) compliance for AI agents. Product classification, Annex I audit, SBOM generation, conformity assessment roadmap, vulnerability reporting readiness. For manufacturers of products with digital elements. By MEOK AI Labs. Runs locally from the cra-compliance-mcp Python…

CSOAI-ORG/cra-compliance-mcp · not measured