create_repo

Create a new repository for the authenticated user

SERVERForgejo SOURCEsqcows/forgejo-mcp

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/sqcows-forgejo-mcp/create-repo.md

WHAT IT DOES

What create_repo does on Forgejo

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

RISK

Why create_repo is rated Medium

Creating a repository is a write operation that modifies the state of the Forgejo/Gitea instance by adding a new resource. It is not destructive (the action is reversible), not financial, and not an execute-style operation. The severity is medium because while repository creation is a persistent change, it does not have the blast radius of destructive operations or actions affecting multiple users/systems.

From the tool's definition Tool description states 'Create a new repository' — this creates new data (a repository) in a reversible manner. The authenticated user can delete or modify the repository after creation.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs create_repo safely

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

create_repo Rate-limited

create_repo 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": {
    "create_repo": {
      "limits": [
        {
          "counter": "create_repo_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 Forgejo, apply this rule, and every create_repo call is checked against it from then on.

FAQ

Questions about create_repo

What does the create_repo tool do? +

Create a new repository for the authenticated user. It is categorised as a Write tool in the Forgejo MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_repo? +

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

What risk level is create_repo? +

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

Can I rate-limit create_repo? +

Yes. Add a rate_limit block to the create_repo 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 create_repo completely? +

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

create_repo is provided by the Forgejo MCP server (sqcows/forgejo-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Forgejo, and thousands of servers like it.

This server

All 457 Forgejo tools →

Across the catalogue

create_task on 0rca Dojo MCP Server →create-task on Kanban MCP Server →create_package_backup on Android Forensics ADB MCP Server →create_project on Stitch MCP Server → The MCP Attack Database →

Guides

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