MCPBridge Server (RBG-WebDesign/MCPBridge-Server) is an MCP server listed on the M8ven Trust Index. It scores 60 out of 100, grade C. It declares 122 tools. No publisher has claimed this listing.

C
Caution
60/100

MCPBridge Server

Enables AI coding agents to control and interact with Unreal Engine 4.27 editor through MCP protocol, translating tool calls into HTTP commands for the in-editor plugin.

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

RBG-WebDesign

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

Install from

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
⚠️
Known vulnerabilities in dependencies: 3 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
// tools this server exposes122 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

actor_spawn

Spawn an actor from an asset path at a given location/rotation/scale. Returns validation results by default.

actor_duplicate

Duplicate an existing actor with an optional offset. Returns validation results by default.

actor_delete

Delete actors by name or name pattern (supports * and ? wildcards).

actor_modify

Change an actor's location, rotation, scale, mesh, or visibility. Returns validation results by default.

actor_organize

Move actors into World Outliner folders.

actor_snap_to_socket

Snap one actor to another actor's named socket.

batch_spawn

Spawn multiple actors in one call. Each spawn definition uses the same format as actor_spawn.

placement_validate

Check actors for gaps, overlaps, and alignment issues.

blueprint_inspect
blueprint_add_variable

Add a member variable to a Blueprint, then compile and save.

blueprint_remove_variable

Remove a member variable from a Blueprint, then compile and save.

blueprint_set_variable_default

Set a member variable's default value, then compile and save.

blueprint_add_function
blueprint_remove_function

Remove a user function graph by name, then compile and save.

blueprint_add_event_dispatcher

Create an event dispatcher (multicast delegate) with an optional parameter signature, then compile and save.

blueprint_remove_event_dispatcher

Remove an event dispatcher by name, then compile and save.

blueprint_add_interface

Implement a Blueprint Interface on a Blueprint, then compile and save.

blueprint_remove_interface

Remove an interface implementation (deletes its generated function graphs), then compile and save.

blueprint_component_remove

Remove a component (SCS node) from a Blueprint; children re-parent to the removed node's parent. Compiles and saves.

blueprint_component_rename

Rename a component (SCS node) on a Blueprint, then compile and save.

blueprint_node_add
blueprint_node_delete

Delete a node by GUID (links broken first), then compile and save.

blueprint_node_move

Move a node to a new graph position, then compile and save.

blueprint_node_set_enabled

Enable or disable a node by GUID, then compile and save.

blueprint_pins_connect
blueprint_pins_break

Break all links on a single pin of a node, then compile and save.

blueprint_list

List Blueprint assets with optional filtering by path, name, and parent class.

blueprint_info

Get detailed Blueprint structure: components, variables, functions, event graphs, parent chain.

blueprint_create

Create a new Blueprint class with optional components and variables.

blueprint_compile

Compile a Blueprint and return success/failure with error details. Success means the compile ran, check 'compiled' and 'had_errors' for actual result.

blueprint_document

Generate a human-readable text summary of a Blueprint's structure, variables, and components.

blueprint_build_from_json
anim_blueprint_build_from_json
blueprint_build_from_description
material_instance_create
material_instance_set_params

Set scalar/vector/texture parameters on an existing material instance, then save.

data_table_create
data_table_fill_from_json

Replace an existing DataTable's rows from DataTable JSON, then save. Returns the resulting row names.

audio_component_add
level_new
game_template_create
cpp_class_create
cpp_build
job_status
job_list

List all background jobs started in this editor session, newest first.

job_cancel

Cancel a running background job (terminates its subprocess).

pp_volume_spawn

Spawn a PostProcessVolume with full settings control. Supports bloom, exposure, color grading, DOF, chromatic aberration, grain, vignette, motion blur, SSR, lens flare, and more.

pp_volume_modify

Modify an existing PostProcessVolume's settings. Settings merge with existing values.

pp_preset

Apply a named post-processing preset. Creates or updates a PP volume. Presets: horror, cyberpunk, noir, dream, underwater, surveillance, vhs_glitch, damage, drunk, frozen, nuclear, sepia, cinematic, neon, thermal.

camera_shake_blueprint

Create a CameraShake Blueprint asset with oscillation parameters. Shake presets: explosion, hit, earthquake, gunfire, footstep, ambient, electric_shock, glitch_shake. Or set individual rot_pitch/yaw/roll_amp/freq, loc_x/y/z_amp/freq, fov_amp/freq values.

camera_shake_play

Play a camera shake during PIE. Requires PIE to be running.

camera_shake_spawn

Spawn a CameraShakeSourceActor in the level. Emits shake within inner/outer radius during PIE.

camera_shake_trigger

Spawn a C++ ShakeTriggerActor: plays camera shake when the player overlaps its trigger box during PIE. Python builds, C++ executes -- the reliable pattern.

console_effect

Toggle rendering features via console commands. Commands: freeze_rendering, show_fps, screen_percentage, temporal_aa, fxaa, motion_blur, bloom, eye_adaptation, tonemapper, ssr, ao, dof, aa_quality, shadow_quality, view_distance_quality, post_process_quality.

input_mapping_add
input_mapping_remove

Remove action or axis mappings. Omit 'key' to remove every key bound to the name.

input_preset_apply
gameplay_framework_create
project_settings_maps
camera_rig_create
blackboard_create

Create a BlackboardData asset with typed keys (Bool, Int, Float, String, Name, Vector, Rotator, Object, Class).

behavior_tree_create
ai_nav_rebuild

Rebuild navigation data in the loaded level (RebuildNavigation console command).

gameplay_pie_start
gameplay_pie_stop

End the current PIE session.

gameplay_telemetry_snapshot
gameplay_run_acceptance_tests
project_index_rebuild
project_index_query

Search the cached project intelligence index. Use this before editing to find existing assets, Blueprint structures, dependencies, and patterns.

project_semantic_diff
gameplay_pattern_search
level_actors

List actors in the current level with optional filters. Returns name, class, folder, and optionally transforms and components.

level_save

Save the current level and optionally all dirty assets.

level_outliner

Return the World Outliner folder tree structure with actor counts per folder.

material_list

List materials in the project with optional filtering by path, name, and type.

material_info

Get detailed information about a material: parameters, textures, parent chain.

material_create

Create a new material or material instance. Provide parent and type 'instance' for material instances.

material_apply

Apply a material to an actor's mesh component. Returns validation by default.

undo

Undo the last N operations using UE4's transaction system.

redo

Redo previously undone operations.

history_list

Show operation history with timestamps and parameters.

checkpoint_create

Create a named save point (level save + metadata snapshot).

checkpoint_restore

Restore to a named checkpoint by undoing operations since it was created.

batch_operations

Execute multiple tool calls in a single request with shared validation.

project_info

Return current UE project name, engine version, project path, content directory, and loaded level.

asset_list

List assets with optional filters. Returns asset paths, types, and names.

asset_info

Return detailed info for a single asset: type, bounds, material slots, LOD count.

asset_load_diagnostics

Diagnose asset loads, Blueprint generated classes, dependencies, referencers, and script class availability.

asset_save_many

Save only the explicit asset paths passed in. Safer than project-wide save-all.

project_enable_plugins

Enable one or more plugins in the current .uproject and report whether an editor restart is required.

input_mapping_info

Inspect Unreal input action and axis mappings. Use this to validate bindings like PF_Pause to Escape when physical key injection is unavailable.

prompt_generate
prompt_status
prompt_spec_list
widget_title_template
widget_title_card_create

Create a centered cinematic title-card Widget Blueprint with styled text, background treatment, and FadeIn/FadeOut animation specs.

widget_lower_third_create

Create a broadcast-style lower-third Widget Blueprint with styled title/subtitle text and FadeIn/FadeOut animation specs.

widget_build_from_json
test_connection

Ping the UE4 Python listener. Returns connection status, engine version, and project info.

python_proxy

Execute arbitrary Python code inside the UE4 editor. Has full access to the unreal module. Use for prototyping or operations not covered by dedicated tools.

22 further tools are not listed here. The complete surface is in the source.

// known CVEs in dependencies3 high

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

high@modelcontextprotocol/sdk@1.12.1GHSA-345p-7cg4-v4c7

@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse

high@modelcontextprotocol/sdk@1.12.1GHSA-8r9q-7v3j-jr4g

Anthropic's MCP TypeScript SDK has a ReDoS vulnerability

high@modelcontextprotocol/sdk@1.12.1GHSA-w48q-cv73-mx4w

Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

122/122 tools missing one or more hints — actor_spawn (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); actor_duplicate (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); actor_delete (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +119 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tool test coverage

79/122 tools referenced in tests (65%)

Write tests that reference each tool by name so every tool has at least one test.

Production dependencies are patched

0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.12.1 (high), @modelcontextprotocol/sdk@1.12.1 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 4 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/rbg-webdesign/mcpbridge-server?variant=verified)](https://m8ven.ai/mcp/rbg-webdesign/mcpbridge-server)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 157dafdbc1ce9cd22132e2f0bd91db57936c8a3a
code hash: ec13f741c9eb4b66222812b02b67e37021ecc9112312d0ff4653c69338e62a5f
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client