runtime

MCP tool from Arena Agent by IvanSkainet

runtime.probe / runtime.compat — Probe runtimes and show runtime × sandbox compatibility with known blockers and next actions

How to use it

runtime is exposed by the Arena Agent MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the runtime tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.

FULL ARENA AGENT LISTING

Other tools in Arena Agent (39)

admin

admin.run — Cross-platform admin escalation. Linux/macOS proxies to sudo

asr

asr.transcribe — Transcribe an audio file locally with whisper.cpp. Auto-conv

browser

browser.search — DuckDuckGo search via pure-Python (no chromium)

capability_gap

capabilitygap.record / capabilitygap.list / capabilitygap.resolve — Track missing bridge capabilities found during real scenarios

code

code.run — Execute agent-authored code under the operator's execution posture (composable fence); fail-closed, agent can't set the posture

code_artifact

codeartifact.read — Read a persisted Code Workbench artifact by runid and path

code_matrix

codematrix.run — Run up to 8 Code Workbench jobs sequentially under the current operator posture

code_project

codeproject.run / codeproject.lockverify / codeproject.promotetool — Run persistent projects, enforce dependency locks, or promote recipes/tests into tools

code_run

coderun.info / coderun.promotetool — Inspect persisted runs or use a run as provenance for a promoted tool

code_session

codesession.exec / codesession.artifacts — Execute stateful Python sessions and persist session files/artifacts

desktop

desktop.ocr — Run OCR on a fresh desktop screenshot and return recognized

desktop_app

desktopapp.clickwindowrelative / desktopapp.screenshotwindow — Resolve a real window, then click or screenshot relative to that window for less brittle GUI scenarios

document

document.structure — Structure OCR/ASR/text into tasks or physics homework JSON

emulator

emulator.providers / emulator.list / emulator.start / emulator.stop / emulator.attach — Boot and stop Android emulators through whichever manager the host has (AVD, Genymotion, MuMu, Waydroid, or a host-declared one); post-boot control is plain ADB via mobile.. See docs/emulators.md

exec

exec.exec — Namespaced alias for exec. Run shell command outside bri

fs

fs.read — Read file contents (utf-8)

git

git.status — Show git status for a repository.

hooks

hooks.list — List configured hooks per event

image

image.preprocessforocr — Preprocess an image file for OCR

input_helper

inputhelper.click / inputhelper.key / inputhelper.launch / inputhelper.sendchatcommand — Route real hardware input through the Interactive Input Helper running in the user's desktop session (solves Session 0 limitation for Java Swing, LWJGL, and all GUI automation)

mcp

mcp.extcall — Call a tool on a registered external MCP server (Desktop-Commander, ScreenPilot, ...). Discover servers with mcp.extservers and their tools with mcp.exttools

mcp_server

mcpserver.create / mcpserver.test / mcpserver.install — Author, verify, and install an external MCP stdio server

memory

memory.recall — Find relevant facts/snapshots/sessions by query (TF score),

mission

mission.autopilotstart / mission.autopilotreport / mission.run — Execute bounded mission tool chains with persisted progress and flight records, or run persisted missions

mobile

mobile.preflight / mobile.devices — Preflight Android/ADB readiness and list connected devices

net

net.http — Typed HTTP client. Only http/https to public hostnames (inhe

ocr

ocr.extract — Run OCR on any image file and return text + word boxes

plan

plan.create — Create a structured execution plan for a goal, with suggeste

react

react.run — Run a bounded reason-act-observe loop using safe observation

reflect

reflect.run — Reflect on a prior react/planning run and produce concerns,

relay

relay.check / relay.reply / relay.send — Operator mailbox: read instructions left from the Dashboard or a terminal, answer them, or ask a question mid-task. Queued, not pushed — the agent has to look.

scenario

scenario.run / scenario.promotefromhistory — Execute scenarios or promote successful runs/history into reusable scenarios

secrets

secrets.list — List available secret keys (values never returned).

service

service.autostartstatus / service.autostartrepair — Diagnose or repair bridge autostart setup

skill

skill.list — List available agent skills

subagent

subagent.spawn — Spawn isolated subagent for delegated work; returns summary

sudo

sudo.run — Run a command through 'sudo -n <cmd>' (non-interactive). Req

sys

sys.status — Bridge/services/funnel status

watch

watch.files — List, add, or remove file watchers that emit realtime file c