← Back to directory
COMPARE UP TO 4 SERVERS

Compare MCP servers

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

DimensionCrawlbase MCP ServerConnect AI agents to real-time web data with JS rendering and anti-bot protection.CompartmentEncrypted, fully offline long-term memory for AI agents
FMRS50 / 100 · D75 / 100 · B
Reliability8 / 2012 / 20
Security and permissions10 / 2016 / 20
Maintenance10 / 2014 / 20
Documentation12 / 2018 / 20
Setup experience10 / 2015 / 20
Best for
  • AI developers needing real-time web data.
  • Users integrating live data into Claude, Cursor, or Windsurf.
  • Scraping tasks requiring structured outputs (HTML, Markdown, screenshots).
  • Users needing async large-scale crawling with cloud storage.
  • 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
  • Scenarios not requiring real-time data and relying only on training data.
  • Users wanting fully local processing without external API dependencies.
  • Users needing complex custom crawler logic beyond simple fetching.
  • Strict compliance environments that do not allow third-party services.
  • 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 Crawlbase tokens (normal and JS) to access the API.
  • Network access: server must connect to Crawlbase services for crawling.
  • In HTTP mode, tokens can be provided via environment variables or request headers.
  • 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
  • Dependency on Crawlbase service availability and API limits.
  • Traffic to target sites may be blocked or violate their terms of service.
  • Misconfiguration or invalid tokens can cause failures.
  • Free tokens may have rate limits affecting large-scale use.
  • 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, Cursor, WindsurfClaude Desktop, Claude Code, Hermes Agent, OpenClaw, Cursor, VS Code, Codex, Gemini CLI, Cline, Roo Code, Zed, OpenCode, LM Studio, AnythingLLM, BoltAI, Goose, Kiro
Tools714