Checks or fixes Rust formatting and returns structured output.
AI agents invoke fmt to trigger actions in Http. 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.
Running a code formatter like rustfmt is an Execute-class action: it triggers an external tool/process. When in 'fix' mode it also modifies files (Write), but since it can execute processes and overwrite source files, Execute is the most appropriate category. Severity is medium because misuse could reformat or alter source code, though changes are typically reversible via version control.
From the tool's definition 'Checks or fixes Rust formatting' — the tool actively runs a formatter (likely `rustfmt`) which executes a process and may modify source files in place.
Documented attack patterns abuse exactly the kind of access fmt gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Http, and nothing reaches the server without passing your rules. This is the rule we recommend for fmt:
{
"version": "1",
"default": "deny",
"tools": {
"fmt": {
"limits": [
{
"counter": "fmt_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}fmt 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.
Checks or fixes Rust formatting and returns structured output. It is categorised as a Execute tool in the Http MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Http MCP server in PolicyLayer and add a rule for fmt: 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 Http. Nothing to install.
fmt 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 fmt 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 fmt. 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.
fmt is provided by the Http MCP server (@paretools/http). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Http, 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.
202 Http tools catalogued and risk-classified — across an index of 43,000+ MCP servers.