Query and analyze metrics, logs, and traces stored in GreptimeDB using SQL, TQL, and RANGE queries. Built for developers integrating observability data into AI workflows via the Model Context Protocol.
io.github.GreptimeTeam/greptimedb-mcp-server
Local install
STDIO
No auth required
How models use it and what it is built for.
Query and analyze metrics, logs, and traces stored in GreptimeDB using SQL, TQL, and RANGE queries. Built for developers integrating observability data into AI workflows via the Model Context Protocol.
Local install — runs as a subprocess.
Configuration this server reads at startup.
GreptimeDB host address
GreptimeDB MySQL protocol port (default: 4002)
Database username
Database password
Database name to connect to
Session timezone (default: UTC)
Connection pool size (default: 5)
HTTP API port for pipeline management (default: 4000)
HTTP protocol for pipeline API: http or https (default: http)
Enable sensitive data masking (default: true)
Additional column name patterns for data masking (comma-separated)
Enable audit logging for tool invocations (default: true)
Where to find authoritative docs and source for Greptimeteam Greptimedb.
Paste any of these into Agent Studio after connecting Greptimeteam Greptimedb.
Common questions about connecting and running Greptimeteam Greptimedb.
What query languages does this MCP server support?
The server supports SQL, TQL (GreptimeDB's time-series query language), and RANGE queries for flexible metric, log, and trace analysis. All queries execute against your connected GreptimeDB instance.
How do I authenticate and connect to my GreptimeDB instance?
Set the environment variables GREPTIMEDB_HOST, GREPTIMEDB_PORT (default 4002), GREPTIMEDB_USER, GREPTIMEDB_PASSWORD, and GREPTIMEDB_DATABASE before launching the server. The server uses MySQL protocol on the specified port.
Does this server mask sensitive data in query results?
Yes, sensitive data masking is enabled by default (GREPTIMEDB_MASK_ENABLED=true). You can disable it by setting the environment variable to false if your use case doesn't require redaction.
Can I use this server with HTTPS and custom connection pools?
Yes. Set GREPTIMEDB_HTTP_PROTOCOL to 'https' for the HTTP pipeline API, and adjust GREPTIMEDB_POOL_SIZE (default 5) to tune concurrent connections. The HTTP API runs on port 4000 by default.
What timezone should I use for time-series queries?
Set GREPTIMEDB_TIMEZONE to your preferred timezone (default is UTC). This affects how timestamps are interpreted and displayed in query results, which is critical for accurate time-range analysis.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 30+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent StudioJudges Panel
45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
Addozhang Nexus
Query Sonatype Nexus Repository (OSS/Pro) for Maven, Python, and Docker artifacts
Cyanheads MCP Ts Template
TypeScript template for building MCP servers with declarative tooling, observability, and auth.
Chernistry Bernstein
Declarative agent orchestration for engineering teams