← Back to directory
COMPARE UP TO 4 SERVERS

Compare MCP servers

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

DimensionArcadeDB MCP ServerBuilt-in MCP server for ArcadeDB multi-model databaseChEMBL MCP ServerUnofficial MCP server providing advanced access to the ChEMBL chemical database
FMRS37 / 100 · D75 / 100 · B
Reliability4 / 2012 / 20
Security and permissions5 / 2016 / 20
Maintenance15 / 2014 / 20
Documentation7 / 2018 / 20
Setup experience6 / 2015 / 20
Best for
  • AI integrations needing multi-model data support
  • Developers who want to query and manage databases directly from AI assistants
  • Applications using ArcadeDB as their backend database
  • Drug discovery and computational chemistry researchers
  • Bioinformatics teams needing ChEMBL data through AI assistants
  • Developers comfortable with Node.js or Docker
Not for
  • Users who don't need database functionality
  • MCP clients that require non-stdio transports (e.g., SSE or HTTP)
  • Users not interested in ArcadeDB itself and just want a generic database MCP
  • Production settings requiring official ChEMBL support (this is unofficial)
  • Users without a Node.js or Docker environment
  • General database tasks unrelated to ChEMBL
Required permissions
  • Database read and write access
  • Create and manage databases, indexes, and schemas
  • Execute queries and manage data models
  • Outbound network access to https://www.ebi.ac.uk/chembl/api/data
  • Read-only access to public API data; no authentication credentials required
Risks and side effects
  • Potential exposure of sensitive data if misconfigured
  • Database operations could lead to data loss or corruption; handle with care
  • As a database server, ensure network access control and authentication mechanisms are in place
  • Unofficial project with license marked NOASSERTION (README claims MIT); verify licensing yourself
  • Data accuracy depends on the ChEMBL REST API and the server's parsing may contain defects
  • 30-second request timeouts may constrain large batch queries
  • README inconsistency on tool count (22 vs 27) raises documentation reliability concerns
Supported clientsClaude DesktopClaude Desktop
Tools027