vision.close_project

Forget a project path from the session map (does not delete files).

SERVERVisionmcp SOURCEjoshuahickscorp/visionmcp

Medium RISK CLASS

Category Write

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/visionmcp/vision.close-project.md

WHAT IT DOES

What vision.close_project does on Visionmcp

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

RISK

Why vision.close_project is rated Medium

The tool modifies the in-memory/session mapping by removing a project path entry. This is a reversible write-like operation (the project can be re-added), not a destructive one since files are explicitly preserved. Severity is low as it only affects session state.

From the tool's definition 'Forget a project path from the session map' — modifies session state by removing an entry; 'does not delete files' confirms no destructive file-system action.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs vision.close_project safely

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

vision.close_project Rate-limited

vision.close_project 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": {
    "vision.close_project": {
      "limits": [
        {
          "counter": "vision.close_project_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 Visionmcp, apply this rule, and every vision.close_project call is checked against it from then on.

FAQ

Questions about vision.close_project

What does the vision.close_project tool do? +

Forget a project path from the session map (does not delete files). It is categorised as a Write tool in the Visionmcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on vision.close_project? +

Register the Vision MCP server in PolicyLayer and add a rule for vision.close_project: 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 Visionmcp. Nothing to install.

What risk level is vision.close_project? +

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

Can I rate-limit vision.close_project? +

Yes. Add a rate_limit block to the vision.close_project 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 vision.close_project completely? +

Set action: deny in the PolicyLayer policy for vision.close_project. 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 vision.close_project? +

vision.close_project is provided by the Vision MCP server (joshuahickscorp/visionmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Vision, and thousands of servers like it.

This server

All 376 Vision tools →

Across the catalogue

create_project on Stitch MCP Server → The MCP Attack Database →

Guides

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