AI Sec Watch
AI security intelligence platform tracking LLM vulnerabilities, agentic AI security risks, AI agent attacks, AI privacy incidents, and AI safety research. Daily intelligence on generative AI threats and large language model exploits.
https://aisecwatch.comOpens ChatGPT on the web or desktop and asks it to use the WebMCP tools available here.
Connect straight to this server’s public endpoint.
https://aisecwatch.com/api/mcpWe add this server to your workspace, then open Studio — saved access, one connection to many servers, with a history of what ran.
Last probed Sep 14, 2026 · aisecwatch.com
4tools discovered
Search Issues
Search AI/LLM security issues with filters. Returns a list of matching issues with title, severity, CVE ID, summary, and source URL. Use this to look up recent vulnerabilities, research, or news on a topic.
Get Issue
Fetch full details for a single issue by its UUID. Returns the complete public field set including CVSS vector, EPSS score, CWE IDs, affected packages/vendors, attack types, and mitigation.
Scan Stack
Scan a developer's stack (list of package names and/or vendor names) against the issue database and return matching open security issues. Use this when a user wants to check whether their dependencies have known AI/LLM security problems.
Latest Digest
Get the latest daily AI/LLM security TLDR digest as Markdown. Use this to summarize recent activity without running multiple searches.
Get your MCP into directories
A working endpoint is step one. Directory coverage is the coordinated launch across ChatGPT, Claude, Cursor, the MCP Registry, and community indexes.
Directory coverage for brandsAI security intelligence platform tracking LLM vulnerabilities, agentic AI security risks, AI agent attacks, AI privacy incidents, and AI safety research. Daily intelligence on generative AI threats and large language model exploits.
Use the MCP endpoint listed on this page in your MCP client configuration. One-click install pills support Claude, Cursor, VS Code, and other hosts. Copy the remote MCP URL if your client needs a manual entry.
Operate AI Sec Watch? Verify ownership to take over this directory entry.
This server appears in the MCPBundles directory. Verify you operate it to take over the listing — name, description, logo, contact email, and skill content. We email a 6-digit code to a maintainer address your server publishes in /.well-known/security.txt or /.well-known/mcpbundles.json. Free, takes about a minute.
MCPBundles probed 4 tools on the live server. The tool list on this page reflects what was discovered at the last refresh — connect your client to see the full set available to your session.
No provider sign-in was required during MCPBundles' probe. Your client may still need MCPBundles credentials depending on how you connect.
MCPBundles is an independent platform built on the open Model Context Protocol standard. Not affiliated with Anthropic PBC or Claude.