# Promptspeak

> Pre-execution governance for AI agents. Intercepts MCP tool calls before execution with deterministic blocking, human-in-the-loop holds, and behavioral drift detection.

## Facts
- Page: https://tashan.sh/capability/pkg-chrbailey-promptspeak-mcp-server
- tashan id: pkg:@chrbailey/promptspeak-mcp-server
- Source: https://github.com/chrbailey/promptspeak-mcp-server
- npm: https://www.npmjs.com/package/@chrbailey/promptspeak-mcp-server
- Type: npm
- Category: security
- tashan score: 35.0 / 100
- Adoption: 29.0
- Upkeep: 44.0
- Freshness: 59.0
- Evidence coverage: 100% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- npm downloads: 119/week
- License: MIT
- Official: no

## Install

```sh
claude mcp add chrbailey-promptspeak-mcp-server -- npx -y @chrbailey/promptspeak-mcp-server
```

## Security audit
- Known advisories: 0
- Install-time script: none declared
- Build provenance: not attested
- Declared permission surface: credentials, database

Permissions are read from DECLARED dependencies only. Nothing is executed, so an empty result means "nothing declared", never "nothing possible".

---
Measured 2026-09-13 by tashan (https://tashan.sh) from public evidence. Scorer s5.