AI agents invoke generate to trigger actions in Spiral MCP 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.
Calling a remote AI model to generate text is an external operation with side effects (API calls, compute usage, potential content generation). It is not a simple read/query of existing data, nor does it write/modify stored data. It falls under Execute as it triggers an external process.
From the tool's definition "Generate text using a Spiral model" — triggers an external language model inference operation whose output depends on the prompt/arguments supplied.
Documented attack patterns abuse exactly the kind of access generate gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Spiral MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for generate:
{
"version": "1",
"default": "deny",
"tools": {
"generate": {
"limits": [
{
"counter": "generate_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}generate 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.
Generate text using a Spiral model. It is categorised as a Execute tool in the Spiral MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Spiral MCP Server MCP server in PolicyLayer and add a rule for generate: 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 Spiral MCP Server. Nothing to install.
generate 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 generate 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 generate. 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.
generate is provided by the Spiral MCP Server MCP server (jxnl/spiral-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Spiral MCP 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.
4 Spiral MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.