Prompt Compass is answering right now. Last checked 10 min ago. 38 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.
Over the last week it answered 98.3% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 10 min ago.
claude mcp add prompt-compass --transport http https://api.mpcfintech.com/mcp
{
"mcpServers": {
"prompt-compass": {
"url": "https://api.mpcfintech.com/mcp"
}
}
}
[mcp_servers.prompt-compass]
url = "https://api.mpcfintech.com/mcp"
{
"mcpServers": {
"prompt-compass": {
"url": "https://api.mpcfintech.com/mcp"
}
}
}
{
"mcpServers": {
"prompt-compass": {
"url": "https://api.mpcfintech.com/mcp"
}
}
}
This one needs environment variables set before it will start:
PROMPT_COMPASS_API_KEY (Prompt Compass API key from compass.mpcfintech.com.).
The author declared them in the registry entry; get the values from the project itself.
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 | 653 ms | 10 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.
Task and project automation for local and self-hosted Mindwtr Cloud data; read-only by default.
Paid remote MCP for LLM security scans, jailbreak checks, analytics, checkout, and readiness.
Detect prompt injection, jailbreak, and social-engineering attacks in LLM agents.
Local-first biological memory for coding agents: recall, consolidation, and pre-action Guard checks.
Run local prompt regression checks from prompt-response logs in AI coding assistants.
Detect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM.
Answers built from our own checks of this server.