databricks-mcp-server-by-cdata
Provides a local, read-only Model Context Protocol (MCP) server that exposes Databricks data through CData’s JDBC driver as MCP tools (e.g., get_tables, get_columns, run_query) for LLM clients like Claude Desktop.
Score Breakdown
⚙ Agent Friendliness
🔒 Security
Security posture is constrained by local stdio operation (reduces network exposure) but secrets/credentials are placed into a local .prp file (not described how stored/handled). The README does not document TLS requirements, auth scopes/granularity, or safe query controls (e.g., SQL injection protections at the MCP layer). Because run_query executes provided SQL, agent-driven query composition should be treated as a risk (data exfiltration within the allowed Databricks permissions).
⚡ Reliability
Best When
You want a local MCP integration for read-only querying of Databricks via CData JDBC and you can run the server on the same machine as the MCP client.
Avoid When
You need robust server-side controls for query safety, multi-tenant isolation, or a network-accessible API; also avoid if you cannot provide/handle JDBC driver licensing and connection configuration securely.
Use Cases
- • Allow an LLM to query live Databricks data using natural language without writing SQL
- • Discover available Databricks tables/columns via MCP tools
- • Run read-only SQL SELECT queries through an MCP tool interface
Not For
- • Internet-facing or remote MCP access (server uses stdio and is intended to run locally)
- • Use cases requiring full CRUD or write/update/delete operations
- • Environments that require an HTTP API, webhooks, or centralized API gateways
Interface
Authentication
README notes OAuth may require browser authentication when testing the JDBC connection string, but does not describe MCP-level auth. The MCP server relies on the JDBC driver configuration in the .prp file.
Pricing
No pricing numbers are provided for this repository itself; it depends on CData JDBC driver licensing and potentially CData’s managed MCP offerings.
Agent Metadata
Known Gotchas
- ⚠ Server uses stdio; only works with MCP clients running on the same machine.
- ⚠ Tool outputs are described as CSV; agents may need to parse CSV reliably.
- ⚠ No explicit mention of rate limiting, pagination, or query size limits; large queries may fail or time out depending on Databricks/JDBC driver behavior.
Alternatives
Full Evaluation Report
Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for databricks-mcp-server-by-cdata.
AI-powered analysis · PDF + markdown · Delivered within 30 minutes
Package Brief
Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.
Delivered within 10 minutes
Score Monitoring
Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.
Continuous monitoring
Scores are editorial opinions as of 2026-04-04.