AI agents invoke solve_model to trigger actions in Google OR-Tools server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes an external computational process (the OR-Tools constraint solver). It does not merely read data or write/modify stored data; it actively runs a solver engine whose resource consumption and outputs depend on the submitted model. No data is deleted and no money moves, but it triggers an external operation, placing it firmly in the Execute category.
From the tool's definition "Solve the current optimization model" — triggers the OR-Tools solver engine to run computations on a submitted model
Documented attack patterns abuse exactly the kind of access solve_model gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Google OR-Tools server, and nothing reaches the server without passing your rules. This is the rule we recommend for solve_model:
{
"version": "1",
"default": "deny",
"tools": {
"solve_model": {
"limits": [
{
"counter": "solve_model_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}solve_model stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Solve the current optimization model. It is categorised as a Execute tool in the Google OR-Tools server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Google OR-Tools server MCP server in PolicyLayer and add a rule for solve_model: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Google OR-Tools server. Nothing to install.
solve_model is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the solve_model rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for solve_model. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
solve_model is provided by the Google OR-Tools server MCP server (jacck/mcp-ortools). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Google OR-Tools server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
3 Google OR-Tools server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.