← Back to directory
COMPARE UP TO 4 SERVERS

Compare MCP servers

Compare scores, permissions, risks, and fit in one decision-focused table.

DimensionVideoNote MCPVideo links → multi-format notesCompartmentEncrypted, fully offline long-term memory for AI agents
FMRS53 / 100 · D75 / 100 · B
Reliability8 / 2012 / 20
Security and permissions9 / 2016 / 20
Maintenance11 / 2014 / 20
Documentation14 / 2018 / 20
Setup experience11 / 2015 / 20
Best for
  • Individual users who want structured, multi-format notes from a single video link quickly
  • Users working in Claude Code who are willing to have the current conversation Agent write notes directly
  • Note workflows that combine speech transcription, visual understanding, danmaku, and comments from multiple sources
  • Users who need task management, multi-video parallelism, and batch output
  • Individuals or teams who prioritise privacy and offline operation and do not want data leaving the machine
  • Users who share memory across multiple MCP clients such as Claude Code, Claude Desktop, Hermes Agent, OpenClaw, Cursor, Codex and Gemini CLI
  • Scenarios that need encrypted storage, a hash-chained audit log and verifiable vault migration
  • Users who want low-latency recall, a bundled embedding model and no extra LLM calls inside the memory layer
Not for
  • Users whose clients do not support MCP / Claude Code Skill (the source only describes a Claude Code Skill and MCP Server form)
  • Users who do not want to install local dependencies such as FFmpeg and whisper or download videos
  • Scenarios needing a hosted backend service rather than local execution (this project requires no backend service to start)
  • Users who need cloud multi-device sync or a hosted team memory service; moving between machines means locking the vault and copying the file
  • Users who expect the server itself to run an LLM that extracts facts and decides what to remember; Compartment explicitly keeps no LLM inside and leaves that to the host model
  • Users who cannot keep a passphrase safe or who need a recovery path if it is lost, since Compartment never generates a password, seed or recovery phrase
  • Deployments that require network transports such as SSE or streamable-http; this server is stdio only and opens no ports
Required permissions
  • Read video links and download the corresponding media locally into task directories (note_results/{task_id}/raw/)
  • Write generated artifacts locally (transcripts, notes, screenshots, frames, subtitle exports, etc.) into note_results/{task_id}/gen/
  • Read and write the local SQLite database video_note.db (video_tasks global task index)
  • Invoke local components such as FFmpeg and whisper
  • Optional platform QR-code login (Bilibili, Douyin, etc.) and optional fallback LLM API key configuration
  • Read and write the vault file under the user's home directory, by default ~/.compartment/memory.vault, and its sibling settings file
  • Access the session directory holding the unlock credential (configurable with COMPARTMENT_SESSION_DIR), which also carries the shared embedding process's Unix socket
  • Optionally use the macOS keychain (compartment unlock --keychain is an explicit opt-in, and it survives reboots)
  • Write or merge an mcpServers entry into each MCP client's own configuration file, taking a byte-exact backup first
  • Install a PostToolUse hook for Claude Code that captures memory files the agent writes
  • Serve a read-only dashboard on 127.0.0.1 behind a one-time random URL token
Risks and side effects
  • Downloads video, cover, and other media files, consuming local disk space (cleanup keeps configuration and models by default)
  • whisper transcription runs locally, so speed and resource use depend on machine performance
  • Optionally enabling the fallback LLM requires providing an API key, creating key-management risk
  • Platform QR-code login stores session state, involving account-credential risk
  • Cleanup operations may delete task data; check first with cleanup(task_id, dry_run=True)
  • A leaked passphrase means the encrypted content can be decrypted; Compartment generates no recovery phrase and cannot recover a lost passphrase
  • Enabling the memory_unlock tool places the passphrase in the model's context, which is why it is off by default
  • If a 2FA keyfile is lost, for example a USB stick, the vault cannot be opened even with the passphrase
  • `export --plaintext` writes the vault as unencrypted JSONL, so that file must be handled carefully
  • Memory content can come from untrusted sources; recall wraps memories with a notice that they are stored data and content can be marked quarantined, but the host agent must still treat memory as data to limit prompt-injection risk
  • The capture hook and client integration write into the user's own settings files, although the implementation backs up and merges rather than replacing
Supported clientsClaude CodeClaude Desktop, Claude Code, Hermes Agent, OpenClaw, Cursor, VS Code, Codex, Gemini CLI, Cline, Roo Code, Zed, OpenCode, LM Studio, AnythingLLM, BoltAI, Goose, Kiro
Tools614