Greptimedb MCP Server

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/greptimeteam-greptimedb-mcp-server

About

Use cases: monitoring-observability, database-access

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Tools

10 read · 3 write · 2 delete · 1 not yet classified

Secrets

1 (API keys, tokens or passwords)

Install scripts

None found

Runs as

Python package

Tools (16)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• create_dashboard

  Create or update a Perses dashboard definition in GreptimeDB. Overwrites any dashboard already stored under this name. Refused unless the server runs with write mode enabled.

• create_pipeline

  Create a new pipeline in GreptimeDB. Stores a new version of the pipeline; it does not replace existing ones. Refused unless the server runs with write mode enabled.

• delete_dashboard

  Delete a Perses dashboard definition from GreptimeDB. Irreversible, and refused unless the server runs with write mode enabled.

• delete_pipeline

  Delete a specific version of a pipeline from GreptimeDB. Irreversible, and refused unless the server runs with write mode enabled.

• describe_table

  Get a table profile: schema, semantic metadata, sample rows, and guidance. Use it when deciding how to query an unfamiliar table. When the right table is not known yet, search_table_semantics first; describing candidates one by one is slower than querying the data. The semantic profile says what the table means, not what its data says. signal_type is metric, log, trace, or event; source and source_version name the ingestion protocol; pipeline names the schema that shaped the rows; semantic_options carries signal-specific facts such as metric type and unit. metadata_quality describes how the …

• dryrun_pipeline

  Test a pipeline with sample data without writing to the database. You can test a pipeline in two ways: - Provide 'pipeline' with inline YAML configuration - Provide 'pipeline_name' to test a previously saved pipeline Args: pipeline: Pipeline YAML configuration (inline) pipeline_name: Name of saved pipeline (mutually exclusive with pipeline) data: Test data in JSON/NDJSON format data_type: Optional content type (e.g., 'application/x-ndjson')

• execute_sql

  Execute SQL query against GreptimeDB. Please use MySQL dialect. The general query entry point: use it for logs, traces, events, joins across tables, and metadata queries such as SHOW TABLES. For a plain metric time series prefer execute_tql, where the table name is the metric name and PromQL states rate, increase and quantile directly. Qualify a table as `schema.table` to read a database other than the one this server connected to; the account needs read permission on it. Read-only by default. When the server runs with write mode enabled (--allow-write / GREPTIMEDB_ALLOW_WRITE), destructive…

• execute_tql

  Execute TQL query for time-series analysis. TQL is PromQL-compatible. Use it for metric tables, where the table name is the metric name and the value columns are the PromQL fields. PromQL vector matching can combine metrics from different tables. Use execute_sql for log or event rows, trace analysis, and SQL JOINs. `metric{__schema__="other_db"}` reads a database other than the connected one. That matcher accepts `=` only. Returns at most 10000 rows, also bounded by a byte budget. JSON reports `truncated`; CSV and Markdown append a truncation notice. A shorter time range or fewer series cha…

• explain_query

  Analyze SQL or TQL query execution plan.

• health_check

  Check GreptimeDB connection status and server version.

• list_dashboards

  List all Perses dashboard definitions stored in GreptimeDB.

• list_pipelines

  List all pipelines or get details of a specific pipeline.

• query_range

  Execute time-window aggregation query using GreptimeDB's RANGE query syntax. The narrowest of the three query entry points. Use it for a window aggregation over a non-metric table, or an alignment PromQL cannot state; a metric time series is better served by execute_tql and anything else by execute_sql. `select` must carry at least one aggregate with its own RANGE, such as `avg(cpu) RANGE '5m'`, and `align` supplies the step between windows. A plain column list does not plan. `table` accepts `schema.table` to read a database other than the connected one. A larger align lowers resolution; ti…

• query_semantic_graph

  Query the semantic graph: which entities exist and which are related. Use view=summary when the entity and relationship types in this graph are not known yet; it reports them with the endpoint type pairs each relationship connects. With a type or an id already in hand, query entities or relationships directly. The window is required and half-open, [start_time, end_time), over observed_at. Derived observations use 60-second buckets. Declared edges instead reflect validity overlapping the window: observed_at is the later of the validity start and the window start, not a measured event time. r…

• search_table_semantics

  Find tables by observability concept when the right table name is unknown. Searches table names, semantic options, and entity declarations, and ranks tables by how many query terms they matched. Use it before describe_table when the schema is wide or table names do not say what they hold. It searches schema metadata only, never telemetry row values, so it can say which table holds Redis memory usage but not which row belongs to `Redis02`. It ranks on the values in that metadata, not on the schema's own key names, so search for `gauge` or `bytes` rather than `metric type`. Once it returns can…

Signals

Stars

29

Forks

12

Open issues

6

Contributors

5

Weekly downloads

140

Last commit

Oct 12, 2026 (17 days ago)

Last release

Oct 12, 2026 (17 days ago)

Last package publish

Oct 12, 2026 (17 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name

io.github.GreptimeTeam/greptimedb-mcp-server

Version

0.6.0

Auth

API key

Packages

pypi greptimedb-mcp-server

License

MIT

Repository

github.com/GreptimeTeam/greptimedb-mcp-server

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

Official MCP Registrygithub-graphql