Decide whether to proceed with a task given current usage. Returns proceed/downgrade/abort. Call BEFORE producing large responses, doing huge file reads, or starting expensive operations.
AI agents call should_proceed to retrieve information from Mcp Token Saver without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool reads subscription and usage data to inform decision-making, but does not itself execute, modify, delete, or move money. It is a guard rail that consults state; the actual expensive operations are triggered separately by the agent.
From the tool's definition Tool returns decision signals (proceed/downgrade/abort) based on querying current usage state. No modification, deletion, or execution of external operations occurs.
Documented attack patterns abuse exactly the kind of access should_proceed gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Token Saver, and nothing reaches the server without passing your rules. This is the rule we recommend for should_proceed:
{
"version": "1",
"default": "deny",
"tools": {
"should_proceed": {}
}
}should_proceed is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Decide whether to proceed with a task given current usage. Returns proceed/downgrade/abort. Call BEFORE producing large responses, doing huge file reads, or starting expensive operations. It is categorised as a Read tool in the Mcp Token Saver MCP Server, which means it retrieves data without modifying state.
Register the Mcp Token Saver MCP server in PolicyLayer and add a rule for should_proceed: 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 Mcp Token Saver. Nothing to install.
should_proceed is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the should_proceed 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 should_proceed. 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.
should_proceed is provided by the Mcp Token Saver MCP server (talap-creator/mcp-token-saver). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Token Saver, 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.
5 Mcp Token Saver tools catalogued and risk-classified — across an index of 43,000+ MCP servers.