/ 100

7 days ago

npm

sensorium-mcp

MCP server for remote control of AI assistants via Telegram

→ andriyshevchenko/remote-copilot-mcp· npm: sensorium-mcp· listed on npm

Is this your MCP?

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

npm

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings

🚨

Secret credentials may flow to a network call

1 flow detected: TELEGRAM_TOKEN. We can’t prove the destination matches the brand the credential belongs to.

⚠️

Known vulnerabilities in dependencies: 1 high

Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.

🔐

You'll be asked for 4 credentials: CLAUDE_CODE_OAUTH_TOKEN, MCP_HTTP_SECRET, OPENAI_API_KEY, TELEGRAM_TOKEN

These are read from process.env at runtime. Make sure you trust where they’ll be sent.

// required environment variables

This server reads these from process.env. You'll be asked to provide them before it can run.

configAUTONOMOUS_MODE— No false Enable autonomous agent behavior

configCLAUDE_CLI_CMD

🔐 secretCLAUDE_CODE_OAUTH_TOKEN

configCLAUDE_MODEL

configCLAUDE_WORKER_MODEL

configCODEX_EXE

configCODEX_MODEL

configCONSOLIDATION_ENABLED— No true Set to false to disable sending episodes to OpenAI for consolidation

configCONSOLIDATION_MODEL— No gpt-4o OpenAI model for memory consolidation

configCOPILOT_MODEL

configDMN_ACTIVATION_HOURS— No 4 Hours of idle before DMN reflection fires

configMCP_HTTP_BIND— No 127.0.0.1 Bind address for HTTP server

configMCP_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.

🔐 secretMCP_HTTP_SECRET— No — Shared secret for HTTP transport auth (recommended when MCP_HTTP_PORT is set)

configMCP_START_COMMAND

configMEMORY_SOURCE_THREAD_ID

configMEMORY_TARGET_THREAD_ID

configNARRATIVE_MODEL— No — Model for narrative generation (falls back to CONSOLIDATION_MODEL)

🔐 secretOPENAI_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.

configPRUNING_ENABLED

configPRUNING_SAMPLE_SIZE

configREFLECTION_ENABLED

configREFLECTION_MODEL— No — Model for reflection pipeline (falls back to CONSOLIDATION_MODEL)

configSELF_UPDATE_ENABLED

configSELF_UPDATE_GRACE_MS

configSELF_UPDATE_MIN_UPTIME_MS

configSELF_UPDATE_POLL_INTERVAL_MS

configTELEGRAM_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.

🔐 secretTELEGRAM_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.

configVOICE_ANALYSIS_URL— No — Voice emotion analysis microservice URL

configWAIT_TIMEOUT_MINUTES— No 1440 How long wait_for_instructions blocks (minutes)

// full audit trail

The full breakdown of what we checked, the deductions that landed, the network hosts, the dependency advisories, and concrete fix guidance is available to verified publishers.

// improvement guidance — verified publishers only

We have 3 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.

// embed badge in your README

[![M8ven Score](https://m8ven.ai/badge/mcp/sensorium-mcp-gfnp7a)](https://m8ven.ai/mcp/sensorium-mcp-gfnp7a)

commit: 5f881caa1361afb9d68b930edd64ca5cad8ed18d

code hash: 3e419e395e6f38df0247c32e33451ddc1cf143df8818167e136dfe891f224102

verified: 5/29/2026, 11:27:47 AM

view raw JSON →