MCP server with persistent memory, voice understanding, multi-thread orchestration, and remote control via Telegram for AI assistants.
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.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
Vite Vulnerable to Arbitrary File Read via Vite Dev Server WebSocket
Vite has an `server.fs.deny` bypass with an invalid `request-target`
Vite Vulnerable to Path Traversal in Optimized Deps `.map` Handling
Vite's server.fs.deny bypassed with /. for files under project root
vite allows server.fs.deny bypass via backslash on Windows
process.env. You'll be asked to provide them before it can run.AUTONOMOUS_MODE— No false Enable autonomous agent behaviorCLAUDE_CLI_CMDCLAUDE_CODE_OAUTH_TOKENCLAUDE_MODELCLAUDE_WORKER_MODELCODEX_EXECODEX_MODELCONSOLIDATION_ENABLED— No true Set to false to disable sending episodes to OpenAI for consolidationCONSOLIDATION_MODEL— No gpt-4o OpenAI model for memory consolidationCOPILOT_MODELDMN_ACTIVATION_HOURS— No 4 Hours of idle before DMN reflection firesMCP_HTTP_BIND— No 127.0.0.1 Bind address for HTTP serverMCP_HTTP_PORT— Fill in at minimum TELEGRAM_TOKEN and TELEGRAM_CHAT_ID. Add OPENAI_API_KEY for voice and memory consolidation features. Set (e.g. 3847) to enable multi-thread agent spawning.MCP_HTTP_SECRET— No — Shared secret for HTTP transport auth (recommended when MCP_HTTP_PORT is set)MCP_START_COMMANDMEMORY_SOURCE_THREAD_IDMEMORY_TARGET_THREAD_IDNARRATIVE_MODEL— No — Model for narrative generation (falls back to CONSOLIDATION_MODEL)OPENAI_API_KEY— Fill in at minimum TELEGRAM_TOKEN and TELEGRAM_CHAT_ID. Add for voice and memory consolidation features. Set MCP_HTTP_PORT (e.g. 3847) to enable multi-thread agent spawning.PRUNING_ENABLEDPRUNING_SAMPLE_SIZEREFLECTION_ENABLEDREFLECTION_MODEL— No — Model for reflection pipeline (falls back to CONSOLIDATION_MODEL)SELF_UPDATE_ENABLEDSELF_UPDATE_GRACE_MSSELF_UPDATE_MIN_UPTIME_MSSELF_UPDATE_POLL_INTERVAL_MSTELEGRAM_CHAT_ID— Fill in at minimum TELEGRAM_TOKEN and . Add OPENAI_API_KEY for voice and memory consolidation features. Set MCP_HTTP_PORT (e.g. 3847) to enable multi-thread agent spawning.TELEGRAM_TOKEN— Fill in at minimum and TELEGRAM_CHAT_ID. Add OPENAI_API_KEY for voice and memory consolidation features. Set MCP_HTTP_PORT (e.g. 3847) to enable multi-thread agent spawning.VOICE_ANALYSIS_URL— No — Voice emotion analysis microservice URLWAIT_TIMEOUT_MINUTES— No 1440 How long wait_for_instructions blocks (minutes)[](https://m8ven.ai/mcp/andriyshevchenko-sensorium-mcp-jsp6g7)