What is prompt-compass?

A local prompt-routing and safety checker for deciding whether requests should use local or cloud models, while checking for personal data and jailbreak risks.

Use it to inspect prompts, choose local or cloud routing, and flag PII or jailbreak concerns.

It helps catch privacy and prompt-manipulation risks before a request is sent to a model. It also makes routing decisions consistent.

prompt-compass — MCP server for Claude Code and Codex by rishabhmpc

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/rishabhmpc/prompt-compass-mcp

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

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/rishabhmpc/prompt-compass-mcp/prompt-compass/github.svg)](https://agentmods.dev/mcp/rishabhmpc/prompt-compass-mcp/prompt-compass)

Your own site

<a href="https://agentmods.dev/mcp/rishabhmpc/prompt-compass-mcp/prompt-compass"><img src="https://agentmods.dev/badge/mcp/rishabhmpc/prompt-compass-mcp/prompt-compass/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/rishabhmpc/prompt-compass-mcp/prompt-compass"><img src="https://agentmods.dev/badge/mcp/rishabhmpc/prompt-compass-mcp/prompt-compass.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 unknown No closer match found in the catalogue.

Security

Grade A, and why

prompt-compass 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.

server.json · 12 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

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 · 12 lines scan A 594df0f31869

Subscribe to this mod's changes

prompt-compass is an MCP server published in the GitHub repository rishabhmpc/prompt-compass-mcp (0 stars, last pushed 1mo ago), with no licence file. 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.

AI Safety Data and AI Prompting Security gemini-cli-extension mcp-server model-context-protocol prompt-routing

opik-mcp

Interact with Opik prompts, traces, datasets and metrics through the Model Context Protocol. Runs locally from the opik-mcp npm package. Needs 3 environment variables to run.

comet-ml/opik-mcp · not measured

meta-prompt-mcp

An MCP server that acts as a Prompting Oracle — advice from official Prompting Guides. Runs locally from the meta-prompt-mcp Python package.

kapillamba4/meta-prompt-mcp · not measured

mercury-spec-ops

Modular MCP server for dynamic prompt generation and software development analysis tools. Runs locally from the @n0zer0d4y/mercury-spec-ops npm package.

n0zer0d4y/mercury-spec-ops · not measured

claude-prompts-mcp

Reusable prompt templates, multi-step workflow chains, and quality gates for any MCP client. Runs locally from the claude-prompts npm package.

minipuft/claude-prompts-mcp · not measured

prism-mcp

Persistent session memory for AI coding agents that never leaves your machine — including the on-device model that reasons over it. Restores your prior decisions, open TODOs, and changed files across sessions; adds associative recall of related past work. Runs locally from the prism-mcp-server npm package. Needs 1…

dcostenco/prism-coder · not measured

openrouter-multimodal

Chat with 300+ LLMs via OpenRouter. Analyze and generate images, audio, and video from MCP. Runs locally from the @stabgan/openrouter-mcp-multimodal npm package. Needs 13 environment variables to run.

stabgan/openrouter-mcp-multimodal · not measured