Researchers Discover 253 Security flaws Across 343 AI Agent Tools in MCP Servers

What happened

Researchers have identified 253 verified security vulnerabilities affecting 343 AI agent (AI that carries out multi-step tasks rather than answering one question) tools across 118 Model Context Protocol (MCP) servers. Read Researchers Discover 253 Security Vulnerabilities Across 343 AI Agent Tools in MCP Servers By Divya October 13, 2026 Share Facebook Twitter Pinterest WhatsApp Researchers have identified 253 verified security vulnerabilities affecting 343 AI agent tools across 118 Model Context Protocol (MCP) servers.

These vulnerabilities expose weaknesses in how software processes arguments generated by large language models (LLMs). The findings are based on an evaluation of 273 open-source MCP servers containing 3,405 tools, using a new fuzzing framework called […] The post Researchers Discover 253 Security Vulnerabilities Across 343 AI Agent Tools in MCP Servers appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform .

The findings are based on an evaluation of 273 open-source MCP servers containing 3,405 tools, using a new fuzzing framework called ToFu. This study, titled “ToFu: Exploiting and Fuzzing the LLM–Orchestrator–Tool Trust Boundary,” was published on arXiv on October 9, 2026 , and authored by researchers from Pennsylvania State University, Université Montpellier, and Dartmouth College.

The reported issues include arbitrary path traversal, log injection, data exfiltration, and command bypass. The figures reflect different measurement units and do not represent competing vulnerability totals.