Turns an Agent client into a local-first workbench with tools for files, grep, patching, commands, web search fallback, memory recall, and model-backed agent tasks.
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.
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
process.env. You'll be asked to provide them before it can run.LLM_API_KEY— empty Optional model API key.LLM_BASE_URL— empty Optional OpenAI-compatible base URL for Agent tasks.LLM_MODEL— provider default Optional model name.OPENAI_API_KEYOPENAI_BASE_URLOPENAI_MODELUBW_AGENT_CONCURRENCY— 20 Concurrent Agent tasks inside pipeline.UBW_AGENT_MAX_PIPELINE_TASKS— 100 Pipeline task cap.UBW_AGENT_STAGGER_MS— 0 Delay between pipeline tasks.UBW_AGENT_TASK_HISTORY_LIMIT— 1000 Managed sidecar task record cap.UBW_AGENT_TASK_TIMEOUT_MS— 300000 Agent task timeout.UBW_AGENT_TEMPERATUREUBW_CONFIG— package example config Path to a custom main config JSON.UBW_MEMORY_MAX_FILE_BYTESUBW_MEMORY_MAX_LOCAL_FILESUBW_MEMORY_TIMEOUT_MSUBW_MEMORY_URL— empty Optional external memory/vector service endpoint.UBW_PROFILE— admin Active profile.UBW_PROFILES— package example profiles Path to a custom profile/deny JSON.UBW_ROOTS— Allowed filesystem roots, separated by ;.UBW_SIDECAR_MODE— managed managed, inprocess, or external.UBW_SIDECAR_PORT— 0 Managed sidecar port; 0 means auto-pick.UBW_SIDECAR_STARTUP_TIMEOUT_MSUBW_SIDECAR_URL— empty External sidecar URL when using external mode.UBW_TRANSPORTUBW_WORKER_MAX_FILE_BYTES— 2000000 Per-file worker scan cap.UBW_WORKER_MIN_PARALLEL_FILES— 1 Minimum candidate files before parallel grep.UBW_WORKER_POOL_ENABLED— 1 Enable CPU worker pool for local bulk work.UBW_WORKER_POOL_SIZE— CPU-parallel fs.grep through a local worker pool. By default it uses available machine parallelism; set only when you want to limit it.[](https://m8ven.ai/mcp/haoyun18881-beep-universal-brute-workpack-1mlb7i)