AlekseiMarchenko/central-intelligence

v0.1.2 Security

This release includes 1 security fix for security teams reviewing exposed deployments.

Published 2mo AI Agents & Assistants

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

This release patches 1 known CVE

Affected surfaces

auth rce_ssrf

Summary

AI summary

Fix critical SQL injection vulnerability in recall queries.

Full changelog

What's New

Security Hardening

Fix critical SQL injection vulnerability in recall queries
Add IP-based rate limiting on key creation (5/hour/IP)
Restrict CORS to configured origins
Add 64KB request body size limit
Add key revocation endpoint (DELETE /keys/revoke)
Remove internal error details from API responses
Add input length limits on all user-provided strings

MCP Registry

Published to official MCP Registry (io.github.AlekseiMarchenko/central-intelligence)
Listed on Glama.ai
Submitted to mcp.so and awesome-mcp-servers

API Docs

Interactive HTML docs at /docs
Machine-readable JSON spec at /docs/json

Install

npx central-intelligence-cli signup
npx central-intelligence-cli init claude

Or add manually to ~/.claude/settings.json:

{
  "mcpServers": {
    "central-intelligence": {
      "command": "npx",
      "args": ["-y", "central-intelligence-mcp"],
      "env": { "CI_API_KEY": "your-key" }
    }
  }
}

Security Fixes

Fix critical SQL injection vulnerability in recall queries

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track AlekseiMarchenko/central-intelligence

Get notified when new releases ship.

About AlekseiMarchenko/central-intelligence

Persistent memory for AI agents. Five tools (remember, recall, context, forget, share) with semantic search via vector embeddings and agent/user/org scoping. Works with Claude Code, Cursor, Windsurf, and any MCP client.

All releases →