Manage an app's repo (content-addressed code snapshots). Actions: - "push": Push a small set of files (≤1 MB total over MCP — for larger repos shell out to butterbase repo push). Files are { path, content_base64 } pairs. Server computes sha and runs prepare → upload → commit. - "pull_latest": Fet...
Risk signalsAccepts file system path (files[].path) · Bulk/mass operation — affects multiple targets
Part of the Mcp server.
Free to start. No card required.
AI agents may call manage_repo to permanently remove or destroy resources in Mcp. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. PolicyLayer blocks destructive tools by default and requires explicit human approval before enabling them.
Without a policy, an AI agent could call manage_repo in a loop, permanently destroying resources in Mcp. There is no undo for destructive operations. PolicyLayer blocks this tool by default and only allows it when a human explicitly approves the action.
Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.
{
"version": "1",
"default": "deny",
"hide": [
"manage_repo"
]
}See the full Mcp policy for all 47 tools.
These attack patterns abuse exactly the kind of access manage_repo gives an agent. Each links to the full case and the policy that stops it:
Other destructive tools across the catalogue. The same approach applies to each: deny by default, or require human approval.
Manage an app's repo (content-addressed code snapshots). Actions: - "push": Push a small set of files (≤1 MB total over MCP — for larger repos shell out to butterbase repo push). Files are { path, content_base64 } pairs. Server computes sha and runs prepare → upload → commit. - "pull_latest": Fetch the latest snapshot's manifest (does not write files locally). Returns { snapshot_id, files: [{ path, sha256, size, downloadUrl }] } — agents fetch each downloadUrl directly. - "status": Returns { app_id, pinned_snapshot_id?, remote_latest_snapshot_id?, file_count }. No working-tree comparison (the server has no working tree). - "list_snapshots": List snapshot history newest-first. - "wipe": Delete every snapshot and blob, then null repo_latest_snapshot. Irreversible. Parameters by action: push: { action: "push", app_id, files: [{ path, content_base64 }], message? } pull_latest: { action: "pull_latest", app_id } status: { action: "status", app_id } list_snapshots: { action: "list_snapshots", app_id } wipe: { action: "wipe", app_id } Auth matrix: writes (push, wipe) require app owner. Reads (pull_latest, status, list_snapshots) work for owner or anonymously on a public app; private+non-owner gets 404.. It is categorised as a Destructive tool in the Mcp MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP server in PolicyLayer and add a rule for manage_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 Mcp. Nothing to install.
manage_repo is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the manage_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 manage_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.
manage_repo is provided by the MCP server (@butterbase/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 47 Mcp tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.