Connection check
local install
redash-mcp
Connect Redash to Claude -- query data, manage dashboards, and run SQL with natural language.
Tools
24
GitHub stars
1
Installs / wk
385
Licence
MIT
Transport
stdio
Last checked
never
Tools & capabilities
24 toolsRead from the published package source — this server runs locally, so there is no endpoint to query. Names are taken from the code, not observed at runtime, and descriptions are often absent.
add_widget
from source
Add a saved query Add a saved query
archive_query
from source
Archive a saved query, removing it from active query lists. This is Redash Archive a saved query, removing it from active query lists. This is Redash
create_alert
from source
Create an alert that watches a saved query and fires when a chosen result column crosses a threshold (e.g., daily_signups less than 10). Behavior: creates the alert and returns its… Create an alert that watches a saved query and fires when a chosen result column crosses a threshold (e.g., daily_signups less than 10). Behavior: creates the alert and returns its id and name. Usage: get the query_id from list_queries and confirm the exact column name with get_query / get_query_result first. The alert evaluates the query
create_dashboard
from source
Create a new, empty dashboard. Behavior: creates the dashboard and returns its id, name, and slug. Usage: after creating it, populate it with charts using add_widget, passing visua… Create a new, empty dashboard. Behavior: creates the dashboard and returns its id, name, and slug. Usage: after creating it, populate it with charts using add_widget, passing visualization ids obtained from get_query. To list or inspect existing dashboards instead, use list_dashboards / get_dashboard.
create_query
from source
evaluate_queries
from source
Build and run an accuracy test suite for SQL generation on a data source. Behavior: action Build and run an accuracy test suite for SQL generation on a data source. Behavior: action
fork_query
from source
Fork (duplicate) an existing saved query into a new, independently editable copy, leaving the original unchanged. Behavior: creates the copy and returns its new id and name. Usage:… Fork (duplicate) an existing saved query into a new, independently editable copy, leaving the original unchanged. Behavior: creates the copy and returns its new id and name. Usage: find the query_id to fork with list_queries; use this when you want to experiment with or adapt a query without modifying the original.
get_alert
from source
Get the full detail of a single alert. Behavior: returns the alert Get the full detail of a single alert. Behavior: returns the alert
get_bird_config
from source
View BIRD SQL configuration and status. View BIRD SQL configuration and status.
get_dashboard
from source
Get a dashboard Get a dashboard
get_query
from source
Get the full definition of a saved query. Behavior: returns the query Get the full definition of a saved query. Behavior: returns the query
get_query_result
from source
Run an existing saved query by its ID and return the latest results. Behavior: executes the query as stored in Redash and returns up to max_rows rows as a markdown table or JSON, w… Run an existing saved query by its ID and return the latest results. Behavior: executes the query as stored in Redash and returns up to max_rows rows as a markdown table or JSON, with the column list and a truncation note. Usage: find the query_id with list_queries or get_query. Unlike run_query, this executes already-saved SQL rather than ad-hoc SQL, so the safety guard does not apply.
get_table_columns
from source
Get the column names and data types for one or more tables in a data source. Accepts a single table or a comma-separated list of tables. Use this to confirm exact column names and… Get the column names and data types for one or more tables in a data source. Accepts a single table or a comma-separated list of tables. Use this to confirm exact column names and types before writing SQL with run_query or smart_query. Returns each table
list_alerts
from source
List all alerts configured in Redash. Behavior: returns an array where each alert has id, name, current state (ok / triggered / unknown), last_triggered_at, its linked query (id, n… List all alerts configured in Redash. Behavior: returns an array where each alert has id, name, current state (ok / triggered / unknown), last_triggered_at, its linked query (id, name), and threshold options. Usage: use this to discover alert_ids, then call get_alert for one alert
list_dashboards
from source
List dashboards in Redash, most recently updated first. Behavior: returns a paginated array where each item has id, name, slug, and created/updated timestamps. Usage: use this to d… List dashboards in Redash, most recently updated first. Behavior: returns a paginated array where each item has id, name, slug, and created/updated timestamps. Usage: use this to discover a dashboard
list_data_sources
from source
List connected data sources (id, name, type). Call this first to get data_source_id. List connected data sources (id, name, type). Call this first to get data_source_id.
list_queries
from source
List saved (named) queries in Redash, most recently updated first. Behavior: returns a paginated array where each item has id, name, description, data_source_id, and updated_at. Us… List saved (named) queries in Redash, most recently updated first. Behavior: returns a paginated array where each item has id, name, description, data_source_id, and updated_at. Usage: use this to discover query_ids, then call get_query for a query
list_tables
from source
List tables in a data source. Use keyword to filter by name. Verify table names here before writing SQL. List tables in a data source. Use keyword to filter by name. Verify table names here before writing SQL.
manage_few_shot_examples
from source
Manage the few-shot examples that smart_query uses to generate more accurate SQL. Behavior: action Manage the few-shot examples that smart_query uses to generate more accurate SQL. Behavior: action
manage_keyword_map
from source
Manage keyword-to-table-name mappings. After inspecting the schema with list_tables, register domain-specific mappings to improve smart_query table-matching accuracy. e.g., { Manage keyword-to-table-name mappings. After inspecting the schema with list_tables, register domain-specific mappings to improve smart_query table-matching accuracy. e.g., {
run_query
from source
smart_query
from source
submit_query_feedback
from source
Record whether the SQL produced for a question was correct, so smart_query improves over time. Behavior: stores an up/down rating; when you rate Record whether the SQL produced for a question was correct, so smart_query improves over time. Behavior: stores an up/down rating; when you rate
update_query
from source