PluginBench
MCP Server
Active

Prompt Compass MCP Server

io.github.rishabhmpc/prompt-compass

RepositoryRegistry
How to choose

What this kind of tool is for

  • Scan a repository or dependency tree for known vulnerabilities.
  • Audit secrets, permissions, or headers during a pre-release review.
  • Have your agent explain a suspicious script or config before you run it.

How to compare servers like this

Failure mode:
Vulnerability reports are probabilistic; read findings as leads to verify, not verdicts.
Data leaving the box:
Check whether files or code are uploaded anywhere before scanning anything private.
Maintenance signal:
Security rulesets age fast; stale tools miss new classes of issue.
Report clarity:
The best tools say what is wrong, how sure they are, and how to fix it — verify findings yourself.

This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.

What is the Prompt Compass MCP server?

Decision-only prompt routing and firewall checks for local/cloud routing, PII and jailbreak risk.

How to install Prompt Compass

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • PROMPT_COMPASS_API_KEY
    required
    secret

    Prompt Compass API key from compass.mpcfintech.com.

~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "mcpServers": {
    "prompt-compass": {
      "command": "npx",
      "args": [
        "-y",
        "@mpcfintech/prompt-compass-mcp"
      ],
      "env": {
        "PROMPT_COMPASS_API_KEY": "<YOUR_PROMPT_COMPASS_API_KEY>"
      }
    }
  }
}

Related MCP servers

Hash, encode, UUID, password analysis for AI agents

0
TypeScript
MIT
View repository →

License check, outdated deps, security for AI agents

0
TypeScript
View repository →
ZEZettelForge logo

Agentic memory system for cyber threat intelligence with STIX graphs, actor aliasing, and offline RAG.

58
Python
MIT
View repository →

Security scanning for AI coding tools. Detects secrets, threat models, and runs pre-commit checks.

1
TypeScript
View repository →

Scores, compiles & optimizes prompts for any LLM. Zero AI calls inside. Freemium.

2
TypeScript
View repository →

Causal graph memory engine for AI agents with scoring, activation, and forgetting.

20
Python
AGPL-3.0
View repository →