The GreptimeDB MCP Server enables AI assistants to query, analyze, and manage time-series data, logs, metrics, and traces in GreptimeDB through a secure, read-only interface.

Core Query Capabilities: Execute SQL queries (MySQL dialect, SELECT/SHOW/DESCRIBE only), PromQL-compatible TQL queries, and time-window aggregation queries with RANGE/ALIGN syntax. Multiple output formats available (CSV, JSON, Markdown) with configurable result limits and time ranges.

Schema & Resource Management: List all tables as browsable resources with greptime://<table>/data URIs, inspect table schemas (column names, types, constraints), and read table data through resource endpoints.

Pipeline Management: Create, test (dry-run), list, and delete data processing pipelines using YAML configurations. AI-assisted generation of pipeline configurations from log samples.

Specialized Analysis Templates: Access predefined prompts for log analysis with full-text search, metrics monitoring, PromQL-style queries (TQL EVAL), IoT device monitoring with TAG/FIELD semantics, distributed trace analysis for OpenTelemetry spans, and table diagnostics including region health and query optimization.

Query Analysis & Health: Analyze SQL/TQL query execution plans with EXPLAIN functionality for performance optimization, check database connection status and server version.

Security & Privacy: Automatically blocks all DDL/DML operations (DROP, DELETE, INSERT, UPDATE), dynamic SQL execution, and file system access. Masks sensitive data in columns matching patterns like password, api_key, credit_card, and ssn with configurable patterns.

Integration & Configuration: Seamlessly integrates with Claude Desktop and other MCP-compatible AI assistants. Configurable via environment variables or command-line arguments for connection details, HTTP/HTTPS API settings, timezone, connection pool size, and data masking options.