← Back to directory
COMPARE UP TO 4 SERVERS

Compare MCP servers

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

DimensionUniFi Access MCPManage UniFi Access through MCP.CompartmentEncrypted, fully offline long-term memory for AI agents
FMRS61 / 100 · C75 / 100 · B
Reliability9 / 2012 / 20
Security and permissions14 / 2016 / 20
Maintenance13 / 2014 / 20
Documentation12 / 2018 / 20
Setup experience13 / 2015 / 20
Best for
  • Home-automation or small-organization administrators using UniFi Access.
  • Users who need AI-assisted access to a local UniFi Access controller.
  • Deployments able to maintain a local UniFi administrator or service account.
  • 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 who only have a Ubiquiti SSO cloud account and cannot provide a local controller account.
  • Users needing Network or Protect functionality; those are separate servers in the repository.
  • Environments where AI workflows must not access door, credential, or visitor data.
  • 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
  • Requires the UniFi controller IP address or hostname.
  • Requires a local UniFi administrator or service-account username and password.
  • The account should have permissions for the required access-management operations.
  • A UniFi API key may be used optionally; the source labels it experimental.
  • 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
  • Door, credential, and visitor operations can affect real physical access.
  • Controller credentials and API keys are sensitive and must be protected.
  • UNIFI_VERIFY_SSL defaults to false, which can reduce TLS certificate-validation protection.
  • Incorrect permissions or requests may cause unintended access-configuration changes.
  • 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 Desktop, Codex, OpenClawClaude Desktop, Claude Code, Hermes Agent, OpenClaw, Cursor, VS Code, Codex, Gemini CLI, Cline, Roo Code, Zed, OpenCode, LM Studio, AnythingLLM, BoltAI, Goose, Kiro
Tools014