T-1002observedactive1 evidence record
Tool Discovery
Enumerate available tools and their schemas via MCP tools/list or equivalent discovery endpoints
Tactic
Reconnaissance (Stage 1)
Map the target agent's attack surface, capabilities, and behavioral boundaries
Attack Class
MCP-EXPLOIT
Attacking Model Context Protocol server configurations, tool registrations, and inter-server trust
Evidence
observed
Confirmed in real-world production systems or internet-wide exposure assessments.
DVAA Validation
Reproductions in Damn Vulnerable AI Agent, the OpenA2A intentionally-broken agent for kill-chain validation.
ToolBot tools/list
Honeypot Coverage (AgentPwn)
Queued
In scope for honeypot observation; trap page or telemetry hook not yet built.
Fake MCP tools/list endpoint not yet wired.
Evidence Source Breakdown
Shodan
1 record
Evidence Timeline
Shodan
Shodan May 12, 2026 sweep: 1,322 exposed mcp services indexed
May 12, 2026
Detection (HackMyAgent)
Live1 live · 0 queued
MCP-011
npx hackmyagent secure --ciLive = check implemented in hackmyagent; queued = declared, not yet implementedDefense (OASB Controls)
Live1 live · 0 queued
How to Cite
AI Agent Threat Matrix T-1002 (Tool Discovery). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-1002