Independent coverage, dated, with a boilerplate you can use.
Coverage
What others have written.
Ars Technica
Oct 5, 2026 · Dan Goodin, Senior Security Editor
“MCP for agent-to-agent comms may be the riskiest protocol you've never heard of”
The anchor piece. Quotes the founder directly, alongside Rapid7's Douglas McKee and X41's Markus Vervier.
Unite.AI
Oct 5, 2026
“Researcher Discloses Same MCP Flaw at Google, JPMorgan, Two Governments”
The Next Web
Oct 6, 2026 · Ana-Maria Stanciuc
“Google, JPMorgan and two governments fixed the same MCP flaw”
Tech Times
Oct 6, 2026 · Clayton Lewis
“Six Weeks After Google and JPMorgan Patched MCP Flaw, US Servers Stay Exposed”
Names the founder as "Chicago-based researcher and Cognivators founder."
Published research
Written and dated.
2026-08-26Preprint, Zenodo
Never Emitted: Reporter Attribution in GitHub's Machine-Readable Vulnerability Records
2026-05-24Preprint, Zenodo
Protocol Pivoting: Cross-Protocol Attack Escalation in Agentic AI Systems
2026-06-02IETF Internet-Draft, revision 00
Security Considerations for Model Context Protocol (MCP) Implementations in AI Agent Systems
2026-09-29dev.to
2026-05-23dev.to
2026-05-20dev.to
For journalists
Boilerplate.
Cognivators is a Chicago-based AI agent and MCP server security company. Its product, Agent Surface, maps what AI agents and MCP servers can reach and proves what an attacker could do with that access. It maintains mcp-safeguard, an open source MCP security scanner. The company was founded in Chicago, IL in September 2025 by Syed Anas Mohiuddin.
Contact: anas.syed@cognivators.com