Roblox Executor MCP Server
An MCP server that enables AI agents to execute Lua code, inspect scripts, spy on remotes, and interact with running Roblox game clients, including support for mobile executors on Android and iOS.
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
vonsalt
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.
get-client-capabilitiesReturns the capability profile of the active Roblox client, including executor name, platform (mobile/desktop), and which APIs are available (loadstring, request, WebSocket, decompile, getscripts, firesignal, etc.). Use this to determine which tools will work on the connected client, especially for …
list-clientsList connected Roblox game clients with clientId and session metadata. Use before set-active-client when multiple clients are connected or the target client is unknown.
set-active-clientRoute future Roblox tool calls to the specified connected client. Use list-clients first if you need available clientIds.
execute-fileExecute a local .luau or .lua file in the active Roblox client without returning output. Use get-data-by-code instead when you need returned values. To verify the effect, follow up with a small get-console-output (low limit) or a targeted get-data-by-code probe.
executeExecute Luau in the active Roblox client without returning output. Use get-data-by-code instead when you need returned values. To verify the effect, follow up with a small get-console-output (low limit) or a targeted get-data-by-code probe.
click-buttonClick a Roblox TextButton or ImageButton by firing its GUI signals. Use when direct UI activation is needed inside the active client.
type-text-boxEnter text into a Roblox TextBox by path. Can simulate keystrokes or set Text directly based on useKeyPress.
get-console-outputRead recent Roblox developer console logs from the active client. Use limit and logsOrder to control volume and ordering.
get-data-by-codeExecute Luau in the active Roblox client and return serialized raw Lua values. Prefer the specialized tools (search-instances, get-descendants-tree, get-script-content, script-grep) for exploration; use this only for small, targeted value probes. The code must return values; do not manually JSON-enc…
get-descendants-treeExplore the structure under a Roblox instance. Defaults to a compact summary (child/class counts); set summaryOnly=false for the full tree. Use search-instances for selector-based filtering.
get-game-infoGet current Roblox place and universe metadata such as PlaceId, GameId, and PlaceVersion.
get-script-contentGet decompiled source for a Roblox script by path, script proxy, or getter code. Use startLine/endLine for a focused range when the full script is large.
script-grepSearch decompiled Roblox scripts with JavaScript regex or literal string matching. Use for exact identifiers or code patterns; use semantic-search-scripts when behavior is known but names are not.
search-instancesSearch Roblox instances with QueryDescendants selector syntax. Use for class, name, tag, property, and attribute queries against a chosen root.
semantic-search-scriptsFind decompiled Roblox scripts by behavior using enriched semantic cards plus exact lexical signals. Use when exact identifiers are unknown; use script-grep for precise text or regex.
remote-spyInspect and control Cobalt remote-spy state. Cobalt loads automatically. Use operation=list before changing a remote. block/unblock prevents or permits matching calls; ignore/unignore only changes whether matching calls are logged. Remote names are exact for state changes; list.nameFilter is a case-…
list-roblox-windowsList visible Roblox OS windows with PIDs. Use before screenshot-window when multiple Roblox windows may be open.
screenshot-windowCapture an actual OS screenshot of a Roblox window via Windows APIs. Returns a downscaled JPEG to limit vision-token cost. Provide pid when multiple windows are open; secondary servers relay capture to the primary host.
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
ws: Memory exhaustion DoS from tiny fragments and data chunks
ws: Uninitialized memory disclosure
ANSICONBUN_BINBUN_INSTALLCUSTOM_AI_API_KEYCUSTOM_AI_API_VERSION2023-06-01 API versionCUSTOM_AI_BASE_URLCUSTOM_AI_MAX_TOKENSCUSTOM_AI_MODELclaude-sonnet-4-20250514 Model nameCUSTOM_AI_THINKING_BUDGETCUSTOM_AI_THINKING_ENABLEDfalse Enable thinking displayConEmuANSIHOSTMCP_AUTH_TOKENgetgenv(). = "your-token"MOCK_TAILSCALE_IPMSYSTEMNO_COLORPROGRAMFILESPROGRAMFILES(X86)ROBLOX_MCP_SERVER_NAMETERM_PROGRAMWT_SESSIONXDG_CONFIG_HOMEXDG_DATA_HOMEPORTTool 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
18/18 tools missing one or more hints — get-client-capabilities (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list-clients (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); set-active-client (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +15 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
15/18 tool handlers declare input schemas (83%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
Only 4/18 tool handlers wrap calls in try/catch (22%)
Wrap each tool handler body in try/catch and return a structured error response.
Tests exist
No test files found
Add tests that exercise each declared tool.
Shell command execution
3 child_process calls — runs shell commands
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Production dependencies are patched
0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.25.1 (high), @modelcontextprotocol/sdk@1.25.1 (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.
[](https://m8ven.ai/mcp/vonsalt/mcp-mobile)?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