read_project

Read a CutPilot project, its assets, tracks, items, captions, markers, and validation state.

SERVERCutpilot SOURCEHellotravisss/cutpilot

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/cutpilot/read-project.md

WHAT IT DOES

What read_project does on Cutpilot

AI agents call read_project to retrieve information from Cutpilot without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why read_project is rated Low

This tool performs data retrieval only. It queries and returns information about an existing project and its components without creating, modifying, deleting, or executing any operations.

From the tool's definition Tool name is 'read_project' and description explicitly states 'Read a CutPilot project' — retrieves project structure, assets, tracks, items, captions, markers, and validation state with no side effects.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs read_project safely

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

read_project Allowed

read_project is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "read_project": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

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

FAQ

Questions about read_project

What does the read_project tool do? +

Read a CutPilot project, its assets, tracks, items, captions, markers, and validation state. It is categorised as a Read tool in the Cutpilot MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on read_project? +

Register the Cutpilot MCP server in PolicyLayer and add a rule for read_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 Cutpilot. Nothing to install.

What risk level is read_project? +

read_project is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit read_project? +

Yes. Add a rate_limit block to the read_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 read_project completely? +

Set action: deny in the PolicyLayer policy for read_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 read_project? +

read_project is provided by the Cutpilot MCP server (Hellotravisss/cutpilot). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Cutpilot, and thousands of servers like it.

This server

All 219 Cutpilot tools →

Across the catalogue

read_input_file on 0gzk →claude_read_file on Claude Bridge → The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →