mcpField
P
Prompt Compass

Prompt Compass

Remote
mpcfintech.comSecurity0Updated 13w ago

About Prompt Compass

Prompt Compass is an MCP server that checks prompts and returns a routing or firewall decision without calling a model or taking action. It is for MCP-compatible AI clients that need checks for local or cloud routing, likely sensitive data, and jailbreak content.

Key features

  1. 01Classifies prompts for local or cloud routing
  2. 02Flags likely personal or sensitive data
  3. 03Detects likely jailbreak content
  4. 04Read-only, idempotent prompt-check tool

Use cases

  1. 01Check a prompt before routing it locally or to the cloud
  2. 02Flag sensitive data before forwarding a prompt
  3. 03Screen prompts for likely jailbreak content

MCP support

The server exposes the read-only `compass_check_prompt` tool, which returns a routing or firewall decision. It can connect locally with an API key or remotely over Streamable HTTP, with OAuth discovery supported by modern clients.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://api.mpcfintech.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Packages
npm@mpcfintech/prompt-compass-mcp1.0.1

Tools

Details

From the project README

Prompt Compass logo

Prompt Compass MCP

Prompt Compass gives MCP-compatible AI clients one decision-only tool for checking prompts before they are forwarded:

  • LOCAL_SAFE - suitable for the user's configured local-model route.
  • CLOUD_COMPLEX - suitable for the user's configured cloud-model route.
  • BLOCK_PII - contains likely personal or sensitive data.
  • JAILBREAK - contains likely prompt-injection or jailbreak content.

The MCP server does not call an AI model, choose a model provider, or execute actions. The host application remains in control.

Install

Requires Node.js 20 or newer and a Prompt Compass API key.

npx -y @mpcfintech/prompt-compass-mcp

Set the key as PROMPT_COMPASS_API_KEY. Keep it out of source control, screenshots, issue reports, and chat messages.

Clients supporting Streamable HTTP can instead connect to:

https://api.mpcfintech.com/mcp

Modern clients can discover Prompt Compass OAuth automatically from that URL. Choose Connect or Sign in, log in with your Prompt Compass account, and approve the single read-only prompt-check permission. No API key needs to be pasted into the client. Clients without OAuth support can still use Authorization: Bearer YOUR_PROMPT_COMPASS_API_KEY.

Detailed setup for Codex, ChatGPT desktop, Claude Code/Desktop, Cursor, Cline, Windsurf, Gemini CLI and Google Antigravity is in CLIENT_SETUP.md.

Exposed tool

compass_check_prompt

Input:

{ "prompt": "Text to check" }

The result is a routing/firewall decision only. The tool is marked read-only, non-destructive and idempotent.

Plans and keys

Create a Prompt Compass account and API key at:

https://compass.mpcfintech.com

The MCP connection uses the same quota and billing pool as the Prompt Compass REST API. There is no separate MCP surcharge.

Security and limitations

Prompt Compass is a decision aid, not a sandbox or security guarantee. Keep the host client's own permissions, confirmation prompts, provider policies and application-level validation enabled. Do not auto-approve third-party tools.

Agent Compass is not included in this release.

Test

npm install
npm test

The public test uses a local in-memory MCP transport and a simulated API response. It does not require a customer key.

Links

Copyright (c) Madanpotra Consultancy Private Limited.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.