← Back to directory
COMPARE UP TO 4 SERVERS

Compare MCP servers

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

DimensionDeepChatLocal-first open-source AI agent desktop client unifying LLM providers, MCP, Skills, and ACP agentsBasic MemoryYour AI never forgets again.
FMRS52 / 100 · D72 / 100 · B
Reliability7 / 2010 / 20
Security and permissions6 / 2015 / 20
Maintenance15 / 2016 / 20
Documentation13 / 2017 / 20
Setup experience11 / 2014 / 20
Best for
  • Users who want a single desktop app that unifies many cloud LLM providers (OpenAI, Anthropic, Gemini, DeepSeek, etc.) and local Ollama models
  • Users who need to connect to multiple external MCP tool services with local-first storage and inspectable session history (Tape/Trace)
  • Users who want to reuse Agent Skills built for Claude Code, Cursor, Windsurf, and similar tools
  • Developers who want coding-focused ACP agents integrated into the same chat-style model selector
  • 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 MCP server to add into Claude Desktop or another AI client's config (DeepChat is an MCP client/host, not a server to be added elsewhere)
  • Users who want a lightweight CLI-only tool rather than a full Electron desktop application
  • Users needing a native mobile app (currently Windows/macOS/Linux desktop only; mobile access is indirect, via remote control)
  • 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
  • Local file system read/write access for session Tape storage, Skills files (imported from folders/ZIP/URL), and app configuration
  • Ability to spawn local subprocesses, used to run stdio-based MCP services and the bundled Node.js runtime
  • Network access to call cloud LLM APIs, search services (e.g. Brave Search), and SSE/StreamableHTTP MCP services
  • Remote-control bot credentials (Telegram/Feishu/QQBot/Discord/WeChat iLink tokens) used to bind and remotely operate desktop sessions
  • Local Ollama management access to download, deploy, and run local models
  • 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
  • Third-party MCP services connected via stdio run as local processes under the user's permissions — only install MCP services from trusted sources
  • Imported Skills may include optional scripts that execute with the app's permissions once enabled — vet the source before enabling
  • If a remote-control bot token is leaked, an attacker could remotely control the local session, switch models, or read pending interactions via the messaging app
  • Some search functionality works by simulating user browsing of search engines, which may raise terms-of-service considerations for target sites
  • The README describes encryption/obfuscation interfaces as "reserved" capabilities — verify what is actually enabled in a given release before relying on it
  • 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