Log a trade conviction to the journal. Direction: long/short.
AI agents use log_conviction to create or update resources in Momentum — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Momentum environment.
This tool writes a trade conviction entry to a journal/log, which is a data creation/modification action. It records trading intent (long/short direction) but does not itself execute a trade or move money. It is reversible in the sense that journal entries can typically be deleted.
From the tool's definition Log a trade conviction to the journal
Documented attack patterns abuse exactly the kind of access log_conviction gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Momentum, and nothing reaches the server without passing your rules. This is the rule we recommend for log_conviction:
{
"version": "1",
"default": "deny",
"tools": {
"log_conviction": {
"limits": [
{
"counter": "log_conviction_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}log_conviction 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.
Log a trade conviction to the journal. Direction: long/short. It is categorised as a Write tool in the Momentum MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Momentum MCP server in PolicyLayer and add a rule for log_conviction: 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 Momentum. Nothing to install.
log_conviction 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 log_conviction 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 log_conviction. 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.
log_conviction is provided by the Momentum MCP server (mphinance/momentum-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Momentum, 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.
52 Momentum tools catalogued and risk-classified — across an index of 43,000+ MCP servers.