M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
COMPARE UP TO 4 SERVERS

Compare MCP servers

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

DimensionAgEnDRun a fleet of AI coding agents from your phone.Basic MemoryYour AI never forgets again.
FMRS30 / 100 · D72 / 100 · B
Reliability6 / 2010 / 20
Security and permissions6 / 2015 / 20
Maintenance6 / 2016 / 20
Documentation6 / 2017 / 20
Setup experience6 / 2014 / 20
Best for
  • Developers and teams who want to monitor and command AI coding agents from anywhere.
  • Users who need to run multiple long-running tasks with automatic crash recovery.
  • Users who prefer Telegram or Discord as their control interface.
  • Privacy-conscious developers who want local data storage.
  • Researchers who need AI-assisted management of large note collections.
  • Users of Markdown editors like Obsidian.
Not for
  • Users looking for an officially maintained MCP server (AgEnD is not an official product).
  • Users who need native Windows support (only macOS and Linux are supported).
  • Users who want new features without breaking changes (new features are in pre-alpha agend-terminal).
  • Users needing cloud sync and mobile access (unless using the paid cloud service).
  • Minimalists who want zero configuration.
  • Scenarios requiring large-scale vector databases and complex retrieval (local SQLite may be insufficient).
Required permissions
  • All CLI backends run with --dangerously-skip-permissions (or equivalent), meaning agents can execute arbitrary code.
  • Access to the file system, network, and command execution is required.
  • Optional: Groq API key for voice message transcription.
  • Read and write to the local filesystem (default: ~/basic-memory).
  • Perform file and directory operations (create, edit, delete).
  • Access local SQLite database (or Postgres/Milvus if configured).
Risks and side effects
  • Agents run with full permissions, posing security risks from mistakes or malicious instructions.
  • Cost risk: Without daily spending limits, agents might incur unexpected charges.
  • The project is in maintenance mode, so new features are not developed and vulnerabilities may remain unfixed.
  • Tools have write operations that may unintentionally modify or delete notes.
  • Edit operations may overwrite existing content, though there are protections.
  • Semantic search and reranking features may require model downloads, adding latency.
  • Local data backups are the user's responsibility.
Supported clientsClaude Desktop, Claude Code, Codex, Cursor, VS Code, ChatGPT, Obsidian
Tools021