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.

DimensionMirageA unified virtual filesystem that lets AI agents use bash across cloud storage, SaaS, and databases.Obsidian Web MCPSecure remote access to your Obsidian vault over HTTPS with OAuth 2.0 authentication.
FMRS47 / 100 · D68 / 100 · C
Reliability6 / 209 / 20
Security and permissions8 / 2016 / 20
Maintenance10 / 2014 / 20
Documentation12 / 2017 / 20
Setup experience11 / 2012 / 20
Best for
  • AI agent developers who already use bash and want one filesystem interface instead of many SDKs/MCPs
  • Workflows that need to pipe data between S3, Google Drive, Slack, OneDrive/SharePoint, and similar backends
  • Teams embedding an agent workspace directly inside a Python/TypeScript app (FastAPI, Express, etc.)
  • Users who want secure remote access to their Obsidian vault from any device.
  • Integrating Claude.ai (web) or mobile with Obsidian.
  • Those needing concurrent writes with Obsidian Sync without file conflicts.
Not for
  • Simple single-service use cases that don't need a unified cross-backend interface
  • Non-macOS/Linux environments where FUSE-based mounts aren't supported
  • High-security scenarios requiring fine-grained, per-action permission control rather than a general bash execution interface
  • Users who only need local stdio MCP access without remote capabilities.
  • Those unwilling to set up an OAuth password or use a Cloudflare Tunnel.
  • Users with extremely high security requirements who distrust network exposure (though encrypted).
Required permissions
  • Access credentials or API tokens for each mounted backend (e.g., OneDrive, SharePoint, S3, Slack, Gmail)
  • Local filesystem read/write access (for RAM/Disk resources and caching)
  • Outbound network access to reach remote backend APIs
  • Read and write files in the directory specified by VAULT_PATH.
  • Perform file operations (move, delete with soft delete to .trash).
  • Create daily notes, write binary files.
  • Maintain an in-memory frontmatter index, potentially modifying index files.
  • Access the network (for Cloudflare Tunnel, heartbeat URLs).
Risks and side effects
  • A single bash-like execution interface can let an agent broadly read, copy, or overwrite data across every mounted, potentially sensitive backend
  • Content pulled in from mounted sources (e.g., Slack messages, email) carries prompt-injection risk that could influence subsequent agent behavior
  • Index and file caches (default TTL 10 minutes / default 512MB) can serve stale data until they expire
  • Once credentials are configured for a workspace, an agent may end up with broader cross-service access than intended for a given task
  • Credential leakage: exposed OAuth password or MCP token could allow unauthorized access.
  • Path traversal mitigation is not infallible; keep updated.
  • Extension system is not sandboxed; loading untrusted extensions could be risky.
  • Audit log is best-effort and not tamper-evident; records may be dropped at runtime.
  • Misconfiguration may cause the server to fail to start or expose vulnerabilities.
Supported clientsClaude CodeClaude Desktop, Claude Mobile, Claude Web
Tools120