M
MCP Directory CURATED DIRECTORY
904 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.

DimensionDbxQuery and manage 70+ databases from AI agents via connections already configured in DBXMCP ClickHouseConnect ClickHouse to your AI assistantsChEMBL MCP ServerUnofficial MCP server providing advanced access to the ChEMBL chemical database
FMRS57 / 100 · C79 / 100 · B75 / 100 · B
Reliability8 / 2012 / 2012 / 20
Security and permissions10 / 2018 / 2016 / 20
Maintenance14 / 2017 / 2014 / 20
Documentation13 / 2017 / 2018 / 20
Setup experience12 / 2015 / 2015 / 20
Best for
  • Developers already using DBX desktop, web, or Docker with connections configured
  • Teams working across many different database engines who want one consistent MCP access point
  • Users who want a lightweight (20 MB) client without Java or Python runtime dependencies
  • Teams already using ClickHouse who want AI assistants to access data directly.
  • Scenarios requiring fast, read-only data queries and schema exploration.
  • Drug discovery and computational chemistry researchers
  • Bioinformatics teams needing ChEMBL data through AI assistants
  • Developers comfortable with Node.js or Docker
Not for
  • Users without an existing DBX installation or configured connections, since the MCP server itself does not manage new database credentials — it relies on connections already set up in DBX
  • Users who specifically need an MCP server maintained by a database vendor (e.g. the MySQL, PostgreSQL, or MongoDB projects themselves) rather than DBX's own client wrapper
  • Environments with strict no-write automation requirements where operators cannot verify the current DBX centralized MCP access-mode policy
  • Scenarios requiring write access to the database without explicit opt-in.
  • Production environments with stringent security requirements that avoid default permission settings.
  • 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
  • Access to database connection credentials already configured in DBX
  • Ability to execute SQL according to the mode selected in DBX Settings → MCP (read_only / safe_write / high_risk_write)
  • DBX_WEB_URL (and DBX_WEB_PASSWORD if password login is enabled) for Web/Docker deployments
  • DBX_DATA_DIR pointing to the data directory containing dbx.db for Windows portable builds
  • Node.js >= 18 when run via npx (or use the Node-free precompiled native binary instead)
  • Requires read-only access to ClickHouse database (default).
  • Optional: write access via CLICKHOUSE_ALLOW_WRITE_ACCESS.
  • Optional: destructive operations via CLICKHOUSE_ALLOW_DROP.
  • 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
  • If the access mode is set to Data read/write or Full access, the AI agent can modify or delete data in connected databases
  • Insufficiently reviewed AI-generated SQL could execute unintended write operations against production databases
  • The legacy DBX_MCP_ALLOW_WRITES=0 environment variable only enforces read-only behavior until a central MCP policy has been saved for the first time — after that it no longer applies, so operators must track policy state
  • DBX_WEB_PASSWORD is stored in plaintext in client configuration, so config files should be protected
  • If write access is enabled, AI might make unintended modifications.
  • If DROP access is enabled, data deletion could occur accidentally.
  • Credentials may be exposed via environment variables.
  • 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 Code, Cursor, WindsurfClaude DesktopClaude Desktop
Tools0427