Back to Browse
Free
Server data from the Official MCP Registry
Compress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals.
About
Compress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals.
How to Install
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-base76-research-lab-token-compressor": {
"args": [
"token-compressor-mcp"
],
"command": "uvx"
}
}
}Security Report
5.2
Moderate5.2Moderate RiskThis is a well-designed MCP server for prompt compression that integrates with local Ollama models. The code demonstrates good security practices with no authentication issues (appropriate for local-only operation), proper error handling with graceful fallbacks, and permissions that match its purpose. Some minor code quality issues exist around hardcoded model names and broad exception handling. Supply chain analysis found 8 known vulnerabilities in dependencies (1 critical, 7 high severity). Package verification found 1 issue.
Scanned 8 files · 13 findings
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
Permissions Required
This plugin requests these system permissions. Most are normal for its category.
Reviews
No reviews yet
Be the first to review this server!