Walk-forward validation: splits data into n folds, detects overfitting.
AI agents invoke walk_forward_test to trigger actions in Momentum. 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.
Walk-forward testing actively executes a series of backtests across rolling time windows, performing computational operations that depend on arguments (number of folds, strategy parameters). It does not simply retrieve static data (Read), nor does it modify or delete data (Write/Destructive), nor does it move money (Financial).
From the tool's definition 'Walk-forward validation: splits data into n folds, detects overfitting' — runs a computational validation process over historical data folds, executing iterative backtesting cycles
Documented attack patterns abuse exactly the kind of access walk_forward_test 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 walk_forward_test:
{
"version": "1",
"default": "deny",
"tools": {
"walk_forward_test": {
"limits": [
{
"counter": "walk_forward_test_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}walk_forward_test 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.
Walk-forward validation: splits data into n folds, detects overfitting. It is categorised as a Execute tool in the Momentum MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Momentum MCP server in PolicyLayer and add a rule for walk_forward_test: 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.
walk_forward_test 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 walk_forward_test 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 walk_forward_test. 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.
walk_forward_test 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.