Overdare MCP (Seungpyo1007/overdare-mcp) is an MCP server listed on the M8ven Trust Index. It scores 56 out of 100, grade D. It declares 25 tools. No publisher has claimed this listing.
An MCP server that enables AI agents to browse, create, edit, and script in OVERDARE Studio, and to run playtests.
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
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
Seungpyo1007
Source: Glama
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.
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.
overdare_recipeoverdare_screenshotCapture the live Studio viewport / running game and return the image so you can visually verify the scene. Great for 'visual-first' iteration: change something, then look.
overdare_assetsList the curated OVERDARE Asset Drawer catalog (official UI screens + a PvP combat template) so you can pick a KNOWN-GOOD id to import with overdare_asset_import. Guessing an id is dangerous (a bad id hangs Studio). No Studio call; safe anytime.
overdare_asset_importImport an Asset Drawer model into the level by id (a full UI screen, the combat template, etc.). It lands under Workspace — relocate with overdare_move_instance (UI -> StarterGui). DANGER: a wrong id permanently HANGS Studio. Pick ids from overdare_assets, STOP the playtest, then set confirmStopped=…
overdare_image_importImport a local image file (PNG/JPG) into the asset manager and return the created asset id — use it as Image/Decal content (e.g. on an ImageLabel or a Texture). STOP the playtest first. Not subject to the bad-id hang (no id input).
overdare_create_partCreate a persistent Part in the editor (not runtime) by editing the .ovdrjm and reloading. Use for real, saveable map geometry. STOP any playtest first. Position/size/color scale to the world (character height ~160; baseplate is huge).
overdare_create_instanceCreate a persistent instance of any class in the editor by editing the .ovdrjm (e.g. Folder, Model, MeshPart, Part). STOP any playtest first. `props` accepts position/size/color/anchored/meshId, plus `raw` for verbatim fields.
overdare_delete_instancePermanently delete an instance by GUID by editing the .ovdrjm and reloading. STOP any playtest first. (For scripts, prefer overdare_rpc script.delete.)
overdare_update_instanceModify an existing instance's properties (and/or rename it) by GUID — edits the .ovdrjm and reloads. STOP any playtest first. Use after import/create to tweak material, color, size, transparency, etc. `props` is the same shape as overdare_create_instance.
overdare_move_instanceReparent an instance under a new parent — edits the .ovdrjm and reloads. STOP any playtest first. Essential after overdare_asset_import (imports land under Workspace; move UI to "StarterGui").
overdare_create_instancesBulk-create multiple instances under one parent in a single edit (one reload). STOP any playtest first. Best for classes already present in the project (e.g. Part); for novel classes, import a template first. Max 50.
overdare_read_instanceRead an instance's properties from the saved project (.ovdrjm) — fills the gap left by the absent instance.read RPC. Returns the node's fields (Material, Size, CFrame, Transparency, …) plus a summary of its children. Pair with overdare_update_instance to change them. (Reads the saved file — overdare…
overdare_script_readRead an existing script's Luau source from the saved project (.ovdrjm) — fills the gap left by the absent script.read RPC. Use before overdare_script_edit to see what you're changing.
overdare_findSearch the project tree by name substring and/or class, returning matching nodes with guid + dotted path. Far more practical than overdare_browse on large projects (e.g. after importing the TPA combat template).
overdare_script_editReplace an existing script's Luau source (and/or toggle Enabled) by editing the .ovdrjm and reloading — fills the gap left by the absent script.edit RPC. STOP any playtest first. Use TABS for indentation. (To create a NEW script use overdare_script_add.)
overdare_duplicate_instanceDuplicate an existing instance (and its whole subtree) with fresh GUIDs by editing the .ovdrjm and reloading. STOP any playtest first. Great for replicating a built platform or decorated model. Internal weld/ref links aren't remapped (fine for parts/models/scripts/UI).
overdare_rc_search_assetsSearch OVERDARE's Unreal asset library (StaticMesh, Texture2D, etc.) via Remote Control. Use to find 3D meshes/textures by name or class. e.g. classNames=['StaticMesh'], query='tree'.
overdare_rc_callCall a UFunction on an Unreal object via Remote Control (advanced, low-level). objectPath is a UObject path; functionName + parameters per the UFunction signature.
overdare_rc_propertyRead or write a property on an Unreal object via Remote Control. Omit `value` to read; provide it to write.
overdare_rc_describeDescribe an Unreal object (its properties/functions) via Remote Control.
overdare_rc_batchRun several Unreal Remote Control requests in one round-trip (PUT /remote/batch). Each item is {URL, Verb, Body?}. Advanced/low-level — efficient for bulk property reads/writes on UObjects.
overdare_rc_pythonRun an Unreal Python command in the editor (ExecutePythonCommand) via Remote Control. EXPERIMENTAL — OVERDARE's build may omit/sandbox the Python plugin; this tool first probes availability (read-only) and refuses if absent. NOTE: Python acts on the live Unreal level, NOT the saveable Lua/.ovdrjm la…
overdare_rc_list_actorsIntrospect a live Unreal object via Remote Control describe (EXPERIMENTAL, low-level). The OVERDARE world/level object path is build-specific — pass objectPath to inspect a known object. For the game DataModel tree, use overdare_browse instead.
overdare_statusDiagnostic: report what's reachable and configured — Studio RPC (13377), UE Remote Control (30010), Unreal Python availability, the resolved project file, and OVERDARE_PROJECT_DIR. Call this first when something isn't working, or to confirm the environment before building. (May take a few seconds if…
overdare_rpcLow-level escape hatch: call any Studio RPC method with raw params. Use for methods without a dedicated tool or to probe the protocol. Verified methods: level.browse/apply/save.file/publish, script.add, instance.delete, game.play/stop/screenshot. (Note: instance.read/upsert/move and script.read/edit…
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
MCP_HOSTMCP_PORTOVERDARE_PROJECT_DIRSTUDIO_HOSTSTUDIO_PORTSTUDIO_RPC_HOSTlocalhost Studio RPC hostSTUDIO_RPC_PORT13377 Studio RPC portSTUDIO_RPC_TIMEOUT_MS30000 Per-call timeoutUE_RC_HOSTUE_RC_PORTUE_RC_TIMEOUT_MSTool 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
25/25 tools missing one or more hints — overdare_recipe (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); overdare_screenshot (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); overdare_assets (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +22 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 inputs are validated
23/25 tool handlers declare input schemas (92%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
24/25 tool handlers wrap calls in try/catch (96%)
Wrap each tool handler body in try/catch and return a structured error response.
License file
No license file
Add a LICENSE file (MIT, Apache-2.0, etc.).
Tests exist
No test files found
Add tests that exercise each declared tool.
Production dependencies are patched
0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.12.0 (high), @modelcontextprotocol/sdk@1.12.0 (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.
[](https://m8ven.ai/mcp/seungpyo1007/overdare-mcp)?variant=verified from the URL.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