Skip to main content
Glama
CarlxsMG

UEAgent

by CarlxsMG
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

set_bp_function_rpc

DestructiveIdempotent

Converts a Blueprint function into an RPC (Server, Client, NetMulticast, or NotReplicated), compiles it, and reads back net flags—enabling headless RPCs that take arguments.

Instructions

Turn a Blueprint FUNCTION into an RPC (rpc_type Server / Client / NetMulticast, or NotReplicated to undo it, plus reliable), then compile and read the FUNC_Net* flags back off the entry node. This is the ONLY headless way to author an RPC THAT TAKES ARGUMENTS: add_function_parameter cannot reach a custom event, so build the RPC as add_blueprint_function -> compile_blueprint -> add_function_parameter -> here. Engine limits that follow: a replicated function cannot return a value and cannot host latent nodes (put a Delay in a separate, parameterless custom event).

Returns: { blueprint_name, function_name, rpc_type, is_net, reliable, function_flags } -- re-read from the entry node's flags after compiling; rpc_type is the RESOLVED type, so compare it with what you asked for. Proof that the call really crosses the wire is not here: drive it in PIE and read the resulting state on the OTHER side.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
forceNoOptional. This command is REFUSED while a Play-in-Editor session is running: it either compiles a Blueprint (the reinstancer can retain a world, and CheckForWorldGCLeaks is Fatal -- it KILLS the editor) or writes to disk (Editor.AllowSavingAssetsDuringPIE=0 makes the engine refuse the write, so it would report success without writing a byte). Stop PIE and retry instead; force=true runs it anyway, at your own risk.
reliableNoMark the RPC reliable; ignored (and cleared) when rpc_type is NotReplicated; defaults to false
rpc_typeYesOne of "NotReplicated", "Server", "Client", "NetMulticast" (case-insensitive).
function_nameYesName of an existing FUNCTION graph on the Blueprint (a custom event has no entry node here and is refused).
blueprint_nameNoName (or full object path) of the Blueprint.
blueprint_pathNoAlias of `blueprint_name` (same value, same meaning). Accepted because sibling tools spell this parameter differently; prefer `blueprint_name`.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare the destructive/write profile, but the description adds substantial context beyond them: it compiles the Blueprint and writes to disk, re-reads FUNC_Net* flags after compiling, returns the RESOLVED rpc_type rather than the requested one, and warns that wire-crossing cannot be verified here (must be driven in PIE). No contradiction with readOnlyHint=false, destructiveHint=true, idempotentHint=true.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action, then workflow, engine limits, and return shape. Dense with no filler, though the run-on structure of the first and Returns sections is slightly heavy for the amount of information conveyed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex, no-output-schema, destructive authoring tool, the description supplies the return object, the resolved-vs-requested caveat, the required call ordering, and the engine constraints an agent needs. Nothing material is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so rpc_type, reliable, force, function_name, and the blueprint_name/blueprint_path alias are all fully documented in the schema. The description adds only the 'NotReplicated to undo it' nuance for rpc_type, so the schema carries the load and baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Turn a Blueprint FUNCTION into an RPC') and enumerates the target modes. It explicitly distinguishes itself from siblings by claiming to be 'the ONLY headless way to author an RPC THAT TAKES ARGUMENTS,' and names add_function_parameter and add_blueprint_function as the tools it does not replace.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit call sequence (add_blueprint_function -> compile_blueprint -> add_function_parameter -> here) plus the condition that selects it (add_function_parameter cannot reach a custom event). It also states follow-on engine limits that constrain when the result is usable (no return value, no latent nodes on a replicated function).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools