request_feature

SERVERLocal SOURCElocal-mcp

Medium RISK CLASS

Category Write

Parameters 21 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/com-local-mcp-local-mcp/request-feature.md

WHAT IT DOES

What request_feature does on Local

AI agents use request_feature to create or update resources in Local, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Local environment.

Parameter	Type	Required	Description
`confirm`	boolean	—	Must be true to submit. Without it, shows a preview.
`feature`	string	Yes	What the user wants LMCP to do — a capability, tool, or integration.

Parameters from the server's own tool schema.

RISK

Why request_feature is rated Medium

This tool creates/submits new data (a feature request record) and modifies user state (engagement rank), making it a Write operation. It has minimal blast radius—worst case is unsolicited feature requests or minor privacy exposure of machine ID/email if the user hasn't explicitly consented. No financial, destructive, or code execution impact. Severity is low because the operation is reversible and low-impact.

From the tool's definition Tool submits a feature request (creates data), sends machine ID and optional account email to LMCP team, and affects user's engagement rank. Described as 'Submit a feature request' and explicitly notes the request 'is sent' to the team.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs request_feature safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Local, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For request_feature, this is the rule to start with:

request_feature Rate-limited

request_feature 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "request_feature": {
      "limits": [
        {
          "counter": "request_feature_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Local, apply this rule, and every request_feature call is checked against it from then on.

FAQ

Questions about request_feature

What does the request_feature tool do? +

Submit a feature request to the LMCP team — a new capability, a tool that doesn't exist yet, or an app/integration the user wishes LMCP supported. Ask the user first, then call with confirm=true. Without confirm, returns a preview. The request is sent with your machine ID and (if set) your account email so the team can follow up — not anonymous. Tip: requesting features raises the user's LMCP engagement rank. It is categorised as a Write tool in the Local MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does request_feature accept? +

request_feature accepts 2 parameters: confirm, feature. Required: feature. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on request_feature? +

Register the Local MCP server in PolicyLayer and add a rule for request_feature: 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 Local. Nothing to install.

What risk level is request_feature? +

request_feature is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit request_feature? +

Yes. Add a rate_limit block to the request_feature 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.

How do I block request_feature completely? +

Set action: deny in the PolicyLayer policy for request_feature. 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.

What MCP server provides request_feature? +

request_feature is provided by the Local MCP server (local-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Local, and thousands of servers like it.

This server

All 234 Local tools →

Across the catalogue

The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →