# build_graph Execute a BuildGraph XML script for CI/CD automation. Agent View of the PolicyLayer registry record for `build_graph`. HTML page: https://policylayer.com/tools/jjpxdev-unreal-mcp/build-graph ## Facts - Tool: `build_graph` - Server: Unreal (`@jjpxdev/unreal-mcp`) — https://policylayer.com/tools/jjpxdev-unreal-mcp.md - Install: `npx -y @jjpxdev/unreal-mcp` - Homepage: https://www.npmjs.com/package/@jjpxdev/unreal-mcp - Risk category: Execute (High risk) - Registry record: grade F, identity unverified - Server rate-limited: no - Parameters: 3 (2 required) - Recommended policy verdict: Rate-limited ## Parameters | Parameter | Type | Required | Description | | --- | --- | --- | --- | | `target` | object | yes | BuildGraph target to execute | | `script_path` | string | yes | Path to the BuildGraph XML script | | `additional_args` | array | no | Additional arguments | Parameters from the server's own tool schema. ## Example call (MCP tools/call, JSON-RPC 2.0) ```json { "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "build_graph", "arguments": { "target": {}, "script_path": "" } } } ``` ## Why build_graph is rated High BuildGraph scripts control compilation, packaging, and deployment workflows in Unreal Engine's build system. An AI agent with access to this tool could execute arbitrary build operations—compiling code, packaging builds, triggering deployments, or modifying artifacts—with unpredictable side effects depending on the provided XML script. From the tool's own definition: "'Execute a BuildGraph XML script for CI/CD automation' indicates the tool runs external scripts (BuildGraph XML) that trigger CI/CD pipelines and automated build processes whose effects depend on the script content and configuration." ## Use case AI agents invoke build_graph to trigger actions in Unreal. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started. ## Recommended policy (PolicyLayer) Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Unreal: ```json { "version": "1", "default": "deny", "tools": { "build_graph": { "limits": [ { "counter": "build_graph_rate", "window": "minute", "max": 10, "scope": "grant" } ] } } } ``` ## Other tools on Unreal (126) - `delete_actor` — Destructive — https://policylayer.com/tools/jjpxdev-unreal-mcp/delete-actor.md - `delete_asset` — Destructive — https://policylayer.com/tools/jjpxdev-unreal-mcp/delete-asset.md - `delete_material_expression` — Destructive — https://policylayer.com/tools/jjpxdev-unreal-mcp/delete-material-expression.md - `remove_graph_node` — Destructive — https://policylayer.com/tools/jjpxdev-unreal-mcp/remove-graph-node.md - `build_cook_run` — Execute — https://policylayer.com/tools/jjpxdev-unreal-mcp/build-cook-run.md - `build_plugin` — Execute — https://policylayer.com/tools/jjpxdev-unreal-mcp/build-plugin.md - `build_target` — Execute — https://policylayer.com/tools/jjpxdev-unreal-mcp/build-target.md - `call_preset_function` — Execute — https://policylayer.com/tools/jjpxdev-unreal-mcp/call-preset-function.md - `clean_project` — Execute — https://policylayer.com/tools/jjpxdev-unreal-mcp/clean-project.md - `compile_blueprint` — Execute — https://policylayer.com/tools/jjpxdev-unreal-mcp/compile-blueprint.md - `content_audit` — Execute — https://policylayer.com/tools/jjpxdev-unreal-mcp/content-audit.md - `cook_content` — Execute — https://policylayer.com/tools/jjpxdev-unreal-mcp/cook-content.md - `execute_console_command` — Execute — https://policylayer.com/tools/jjpxdev-unreal-mcp/execute-console-command.md - `execute_python` — Execute — https://policylayer.com/tools/jjpxdev-unreal-mcp/execute-python.md - `generate_lods` — Execute — https://policylayer.com/tools/jjpxdev-unreal-mcp/generate-lods.md - `package_project` — Execute — https://policylayer.com/tools/jjpxdev-unreal-mcp/package-project.md - `recompile_material` — Execute — https://policylayer.com/tools/jjpxdev-unreal-mcp/recompile-material.md - `reinit_niagara_system` — Execute — https://policylayer.com/tools/jjpxdev-unreal-mcp/reinit-niagara-system.md - `render_sequence` — Execute — https://policylayer.com/tools/jjpxdev-unreal-mcp/render-sequence.md - `reset_niagara_system` — Execute — https://policylayer.com/tools/jjpxdev-unreal-mcp/reset-niagara-system.md - `run_all_automation_tests` — Execute — https://policylayer.com/tools/jjpxdev-unreal-mcp/run-all-automation-tests.md - `run_automation_test` — Execute — https://policylayer.com/tools/jjpxdev-unreal-mcp/run-automation-test.md - `run_automation_tests_by_category` — Execute — https://policylayer.com/tools/jjpxdev-unreal-mcp/run-automation-tests-by-category.md - `run_editor_utility_blueprint` — Execute — https://policylayer.com/tools/jjpxdev-unreal-mcp/run-editor-utility-blueprint.md - `run_editor_utility_widget` — Execute — https://policylayer.com/tools/jjpxdev-unreal-mcp/run-editor-utility-widget.md - `run_gauntlet` — Execute — https://policylayer.com/tools/jjpxdev-unreal-mcp/run-gauntlet.md - `run_map_check` — Execute — https://policylayer.com/tools/jjpxdev-unreal-mcp/run-map-check.md - `run_stat_command` — Execute — https://policylayer.com/tools/jjpxdev-unreal-mcp/run-stat-command.md - `spawn_niagara_at_location` — Execute — https://policylayer.com/tools/jjpxdev-unreal-mcp/spawn-niagara-at-location.md - `spawn_niagara_attached` — Execute — https://policylayer.com/tools/jjpxdev-unreal-mcp/spawn-niagara-attached.md - …and 96 more: https://policylayer.com/tools/jjpxdev-unreal-mcp.md ## For agents This record is a snapshot. Live verdicts and the full registry: - Check every server in your MCP config at once: `npx -y policylayer stack` - Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md) - Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events` --- Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=jjpxdev-unreal-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/jjpxdev-unreal-mcp