Publish a strategy ZIP to Hub server (auto-runs backtest)
AI agents use strategy_publish to create or update resources in OpenFinClaw CLI — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your OpenFinClaw CLI environment.
Publishing a strategy to a Hub server is fundamentally a Write operation—it creates or uploads data to a persistent remote location. While backtests are triggered automatically, the tool's core function is not destructive (no deletion/overwrite), not financial (no money movement), and not Execute in the sense of arbitrary code—it's a structured artifact upload.
From the tool's definition Tool name 'strategy_publish' and description 'Publish a strategy ZIP to Hub server (auto-runs backtest)' indicate creation/modification of data on a remote server.
Documented attack patterns abuse exactly the kind of access strategy_publish gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OpenFinClaw CLI, and nothing reaches the server without passing your rules. This is the rule we recommend for strategy_publish:
{
"version": "1",
"default": "deny",
"tools": {
"strategy_publish": {
"limits": [
{
"counter": "strategy_publish_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}strategy_publish stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Publish a strategy ZIP to Hub server (auto-runs backtest). It is categorised as a Write tool in the OpenFinClaw CLI MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the OpenFinClaw CLI MCP server in PolicyLayer and add a rule for strategy_publish: 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 OpenFinClaw CLI. Nothing to install.
strategy_publish is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the strategy_publish 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 strategy_publish. 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.
strategy_publish is provided by the OpenFinClaw CLI MCP server (mirror29/openfinclaw-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from OpenFinClaw CLI, 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.
21 OpenFinClaw CLI tools catalogued and risk-classified — across an index of 43,000+ MCP servers.