Project status, config INI files, and C++ source inspection. Actions: - get_status: Check server mode and editor connection - set_project: Switch project. Params: projectPath - get_info: Read .uproject file details - read_config: Read INI config. Params: configName (e.g. 'Engine', 'Game') - searc...
Risk signalsAccepts freeform code/query input (query) · Accepts file system path (directory) · Accepts raw HTML/template content (content) · High parameter count (29 properties)
Part of the Ue server.
Free to start. No card required.
AI agents invoke project to trigger processes or run actions in Ue. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
project can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
{
"version": "1",
"default": "deny",
"tools": {
"project": {
"limits": [
{
"counter": "project_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full Ue policy for all 22 tools.
These attack patterns abuse exactly the kind of access project gives an agent. Each links to the full case and the policy that stops it:
Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Project status, config INI files, and C++ source inspection. Actions: - get_status: Check server mode and editor connection - set_project: Switch project. Params: projectPath - get_info: Read .uproject file details - read_config: Read INI config. Params: configName (e.g. 'Engine', 'Game') - search_config: Search INI files. Params: query - list_config_tags: Extract gameplay tags from config - read_cpp_header: Parse a .h file. Params: headerPath - read_module: Read module source. Params: moduleName - list_modules: List C++ modules - search_cpp: Search .h/.cpp files. Params: query, directory? - read_engine_header: Parse a .h file from the engine source tree. Params: headerPath (relative to Engine/Source, or absolute) - find_engine_symbol: Grep engine headers for a symbol. Params: symbol, maxResults? - list_engine_modules: List modules in Engine/Source/Runtime - search_engine_cpp: Search engine .h/.cpp/.inl files across Runtime/Editor/Developer/Plugins. Params: query, tree? (Runtime|Editor|Developer|Plugins|all — default Runtime), subdirectory?, maxResults? (default 500) - set_config: Write to INI. Params: configName, section, key, value - build: Build C++ project. Params: configuration?, platform?, clean? - generate_project_files: Generate IDE project files (Visual Studio, Xcode, etc.) - create_cpp_class: Create a new native UCLASS in a project module. Uses the same engine template path as File → New C++ Class. Writes .h + .cpp; returns both paths plus needsEditorRestart (true unless Live Coding successfully hot-reloaded). Params: className (no prefix), parentClass? (default UObject; accepts short names like 'Actor' or /Script/<Module>.<Class> paths), moduleName? (default: first project module, use list_project_modules to pick), classDomain? ('public'|'private'|'classes', default public), subPath? - list_project_modules: List native modules in the current project (name, host type, source path). Feed moduleName from here into create_cpp_class. - live_coding_compile: Trigger a Live Coding compile (Windows only). Hot-patches method bodies of existing UCLASSes without editor restart — the fast inner loop for UFUNCTION implementations. Does NOT reliably register brand-new UCLASSes; use build_project + editor restart for those. Params: wait? (default false — fire and return 'in_progress'). - live_coding_status: Report Live Coding availability/state (available, started, enabledForSession, compiling). Helps choose between live_coding_compile and build_project. - write_cpp_file: Write a .h / .cpp / .inl file under the project's Source/ tree. Used to append UPROPERTYs/UFUNCTIONs or method bodies after create_cpp_class. Writes are scoped to Source/ for safety. Params: path (relative to Source/ or absolute within Source/), content (full file contents). After editing, call live_coding_compile (for existing classes) or build_project (for new classes). - read_cpp_source: Read a .cpp file from the project Source/ tree. Companion to read_cpp_header for round-trip edits. Params: sourcePath (relative to Source/ or absolute). - add_module_dependency: Add a module to a target module's Build.cs dependency array. Params: moduleName (the Build.cs to edit — must exist in the project), dependency (module name to add, e.g. 'UMG'), access? ('public'|'private', default 'private'). Creates the corresponding AddRange block if missing. Rebuild required afterward. - add_cpp_member: Append a UPROPERTY/UFUNCTION declaration to an existing UCLASS header inside the access specifier you choose. Idempotent: if a declaration containing the same memberName is already present, returns existed:true. Params: headerPath (relative to Source/ or absolute), declaration (full multi-line UPROPERTY(...) / UFUNCTION(...) block plus its single-line member or function signature), memberName (the identifier the declaration introduces - used for idempotency), access? ('public'|'protected'|'private', default 'public').. It is categorised as a Execute tool in the Ue MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Ue MCP server in PolicyLayer and add a rule for project: 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 Ue. Nothing to install.
project is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the project 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 project. 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.
project is provided by the Ue MCP server (ue-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 22 Ue 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.