← Back to directory
COMPARE UP TO 4 SERVERS

Compare MCP servers

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

DimensionMCP Email ServerA multi-account MCP server for reading, searching, organizing, and sending email via IMAP and SMTPCompartmentEncrypted, fully offline long-term memory for AI agents
FMRS60 / 100 · C75 / 100 · B
Reliability8 / 2012 / 20
Security and permissions11 / 2016 / 20
Maintenance15 / 2014 / 20
Documentation14 / 2018 / 20
Setup experience12 / 2015 / 20
Best for
  • Individuals or teams who want to read/search/organize/send email directly from an MCP client
  • Users with multiple IMAP/SMTP accounts who want unified management
  • Users comfortable with uv/uvx and local credential setup who can configure their own mail accounts
  • 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 unwilling to store email passwords/credentials locally
  • Setups requiring OAuth (e.g., modern Gmail/Outlook auth) rather than username/password login, which the source material does not confirm is supported
  • Users wanting a fully cloud-hosted email service with no local configuration
  • 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
  • Stores and uses email account credentials (username/password) in local keyring or managed SQLite storage
  • Reads and searches mailbox content via IMAP
  • Sends email on the user's behalf via SMTP
  • Local filesystem access to read/write configuration (TOML file or SQLite database)
  • 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
  • Email credentials are stored locally (legacy TOML/keyring, or managed SQLite in V2); exposure of this storage could allow unauthorized mailbox access
  • Granting an AI client the ability to send email creates risk of unintended or malicious sends via prompt misuse
  • Migrating from legacy configuration to V2 involves credential import, which can hit conflicts or missing-credential issues if done incorrectly
  • 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, Claude Code, Hermes Agent, OpenClaw, Cursor, VS Code, Codex, Gemini CLI, Cline, Roo Code, Zed, OpenCode, LM Studio, AnythingLLM, BoltAI, Goose, Kiro
Tools014