Medium Risk

fork_project

Forks an existing project

How to control fork_project ↓

What fork_project does on Keyshade

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

Medium Risk

Why fork_project needs a policy

Forking creates a new copy of a project, which is a reversible write operation. However, in a secrets management platform, forking a project could duplicate sensitive secrets and configurations, making the blast radius high if misused by an AI agent.

From the tool's definition Forks an existing project

Documented attack patterns abuse exactly the kind of access fork_project gives an agent:

How to control fork_project

PolicyLayer is an MCP gateway — it sits between your AI agents and Keyshade, and nothing reaches the server without passing your rules. This is the rule we recommend for fork_project:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "fork_project": {
      "limits": [
        {
          "counter": "fork_project_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

fork_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.

  1. Create a free account and register Keyshade — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about fork_project

What does the fork_project tool do? +

Forks an existing project. It is categorised as a Write tool in the Keyshade MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on fork_project? +

Register the Keyshade MCP server in PolicyLayer and add a rule for fork_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 Keyshade. Nothing to install.

What risk level is fork_project? +

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

Can I rate-limit fork_project? +

Yes. Add a rate_limit block to the fork_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 fork_project completely? +

Set action: deny in the PolicyLayer policy for fork_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 fork_project? +

fork_project is provided by the Keyshade MCP server (keyshade-xyz/keyshade-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Keyshade tool call.

Start from Keyshade, 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.

44 Keyshade tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.