AgentSUMO
MCP server for LLM-driven SUMO traffic simulation, scenario design, and result analysis.
Verdict not yet evaluated for this tool. The hybrid eval runs adversarial cases first; coverage rolls out as the corpus expands (15 of 150 labels to graduation). Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: hybrid eval, four-state verdict, honest limits.
SUMO_HOMEAbsolute path to the local SUMO installation directory (must contain bin/, share/, tools/).
AGENTSUMO_MCP_OUTPUT_BASEBase directory for simulation outputs (networks, trips, results). Defaults to the current working directory.
Ephemeral data sandbox for AI workflows with guardrails and security
Run Python code in a secure sandbox without local setup. Declare inline dependencies and execute s…
Driven Intent Negotiation — Contract-Oriented Deterministic Executable Runtime DinCoder brings the…