Prompt Compass is answering right now. Last checked 6 min ago. 51 installs a week from npm. Last commit 1 Aug 2026.
Decision-only prompt routing and firewall checks for local/cloud routing, PII and jailbreak risk.
Today is the operative word: we check Prompt Compass every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 6 min ago.
claude mcp add prompt-compass --transport http https://api.mpcfintech.com/mcp
https://api.mpcfintech.com/mcp
[mcp_servers.prompt-compass]
url = "https://api.mpcfintech.com/mcp"
{
"mcpServers": {
"prompt-compass": {
"url": "https://api.mpcfintech.com/mcp"
}
}
}
{
"servers": {
"prompt-compass": {
"type": "http",
"url": "https://api.mpcfintech.com/mcp"
}
}
}
This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://api.mpcfintech.com/mcp | streamable-http | sign-in | 659 ms | 6 min ago |
Multi-agent LLM security layer detecting prompt injection and jailbreaks.
Local MCP server for AI coding safety: risk checks, sessions, checkpoints, and fix prompts.
Real-time MCP & A2A prompt-injection, jailbreak, and tool-schema poisoning firewall for AI agents.
Local-first MCP server for LLM output verification — risk signals, injection and PII checks.
Read-only local evidence checks for product records, feed snapshots, and dimensions.
Paid remote MCP for LLM security scans, jailbreak checks, analytics, checkout, and readiness.
U.S. law library for AI: court decisions, statutes, court rules and citation checks. Read-only.
Local-first Mac meeting memory: promises, decisions, people, the next-call brief. Read-only.
Answers built from our own checks of this server.