mp_wire_rpc
Insert (or replace) an @rpc(...) annotation above a function in an existing GDScript, so it can be called across the network. If the function does not exist, a stub is appended carrying the annotation. Operates on the on-disk file (save the script in the editor first if it has unsaved changes). D...
This record as markdown: /tools/breakpoint-mcp/mp-wire-rpc.md
What mp_wire_rpc does on Breakpoint
AI agents use mp_wire_rpc to create or update resources in Breakpoint, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Breakpoint environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
mode | string | — | Who may call it: 'authority' (default) or 'any_peer' |
path | string | Yes | res:// .gd script to modify |
channel | integer | — | Transfer channel (default 0) |
confirm | boolean | — | Skip the confirmation prompt (auto-approve) |
function | string | Yes | Function name to annotate (a stub is created if absent) |
call_local | boolean | — | Also invoke locally on the caller (default false → call_remote) |
transfer_mode | string | — | Transfer mode: 'unreliable' (default), 'unreliable_ordered', or 'reliable' |
Parameters from the server's own tool schema.
Why mp_wire_rpc is rated Medium
An AI agent can call mp_wire_rpc faster than any human can review: one bad instruction and it creates or modifies resources in Breakpoint by the hundred, each call as confident as the last.
Risk signalsAccepts file system path (path)
Attacks that exploit this kind of access
The rule that runs mp_wire_rpc safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Breakpoint, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For mp_wire_rpc, this is the rule to start with:
mp_wire_rpc 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Breakpoint, apply this rule, and every mp_wire_rpc call is checked against it from then on.
Questions about mp_wire_rpc
Insert (or replace) an @rpc(...) annotation above a function in an existing GDScript, so it can be called across the network. If the function does not exist, a stub is appended carrying the annotation. Operates on the on-disk file (save the script in the editor first if it has unsaved changes). DESTRUCTIVE (rewrites the .gd file) — gated. It is categorised as a Write tool in the Breakpoint MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
mp_wire_rpc accepts 7 parameters: mode, path, channel, confirm, function, call_local, transfer_mode. Required: path, function. The full parameter table on this page comes from the server's own tool schema.
Register the Breakpoint MCP server in PolicyLayer and add a rule for mp_wire_rpc: 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 Breakpoint. Nothing to install.
mp_wire_rpc 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 mp_wire_rpc 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 mp_wire_rpc. 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.
mp_wire_rpc is provided by the Breakpoint MCP server (breakpoint-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Breakpoint, and thousands of servers like it.
This server
Across the catalogue