AI agents use edit_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.
The tool modifies repository settings or properties reversibly. While 'edit' suggests Write-category operations, the medium severity reflects that repository edits could have significant impacts (e.g., changing permissions, visibility, or critical settings) but are typically reversible through subsequent edits or version control recovery.
From the tool's definition Tool name 'edit_repo' combined with description 'Edit a repository' indicates modification of repository configuration or metadata without deletion.
Documented attack patterns abuse exactly the kind of access edit_repo gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Forgejo, and nothing reaches the server without passing your rules. This is the rule we recommend for edit_repo:
{
"version": "1",
"default": "deny",
"tools": {
"edit_repo": {
"limits": [
{
"counter": "edit_repo_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} edit_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.
Free to start. No card required.
Edit a repository. 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.
Register the Forgejo MCP server in PolicyLayer and add a rule for edit_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.
edit_repo is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the edit_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.
Set action: deny in the PolicyLayer policy for edit_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.
edit_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.
Start from Forgejo, 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.
103 Forgejo tools catalogued and risk-classified — across an index of 43,000+ MCP servers.