#1 on dbt Labs' ADE Workbench · 94% AI acceptance rate · 10X engineering velocity
MCP
Add Paradime to Any Client
Add Paradime to Any Client
Add Paradime to Any Client
One endpoint. Bearer auth. Works with Claude, Claude Code, Cursor, GitHub Copilot, and any MCP-compatible client - configure once and your full data context travels with you everywhere.
One endpoint. Bearer auth. Works with Claude, Claude Code, Cursor, GitHub Copilot, and any MCP-compatible client - configure once and your full data context travels with you everywhere.
Paradime MCP
Kiro
Claude
Cursor
OpenCode
Github
CoCo
Available tools
EveryToolYouNeed.ZeroTab-Switching.
Onceconnected,yourclienthasaccesstoalltoolsbelow.
run_terminal_command
Execute a shell command in the workspace terminal.
search_files_and_directories
Search for files and directories in the workspace.
read_file
Read the contents of a file.
ripgrep_search
Search for content in files using ripgrep.
write_file
Creates a new file with specified content.
replace_in_file
Replace content in an existing file.
rename_file
Rename or move a file.
execute_web_search
Perform a web search query.
extract_url_content
Extract web content from a URL.
perplexity_search
AI-powered real-time search via Perplexity.
search_paradime_docs
Search the Paradime Help documentation.
get_paradime_doc_page
Fetch the content of a Paradime Help documentation page.
get_column_level_lineage
Retrieve column-level data lineage.
search_catalog
Search the data catalog.
run_sql_query
Execute a SQL query against the data warehouse.
list_snowflake_metadata
Browse databases, schemas, tables, and columns in Snowflake.
get_query_performance_stats_snowflake
Analyze Snowflake query performance statistics.
list_redshift_metadata
Browse databases, schemas, tables, and columns in Redshift.
list_trino_metadata
Browse catalogs, schemas, tables, and columns in Trino.
list_bigquery_metadata
Browse projects, datasets, tables, and columns in BigQuery.
get_query_performance_stats_bigquery
Analyze BigQuery query performance statistics.
list_databricks_metadata
Browse catalogs, schemas, tables, and columns in Databricks.
list_sqlserver_metadata
Browse databases, schemas, tables, and columns in SQL Server.
list_clickhouse_metadata
Browse databases, tables, and columns in ClickHouse.
list_fabric_metadata
Browse databases, schemas, tables, and columns in Fabric.
list_duckdb_metadata
Browse schemas, tables, and columns in DuckDB.
list_bolt_schedules
List all active Bolt schedules in the workspace.
trigger_bolt_schedule_run
Manually trigger a Bolt schedule run.
retry_bolt_run
Retry a Bolt run.
retry_latest_bolt_schedule_run
Retry the latest run of a Bolt schedule.
get_bolt_run_logs
Get the logs for a Bolt run.
create_pull_request
Create a pull request on GitHub.
read_pull_request
Read details of a pull request.
list_pull_requests
List pull requests on GitHub.
get_jira_issue
Fetch details of a Jira issue.
get_confluence_page
Read the content of a Confluence page.
get_linear_issue
Fetch details of a Linear issue.
list_linear_issues
List Linear issues filtered by state, assignee, status or priority.
search_notion
Search for pages and databases.
fetch_notion_page
Fetch the content of a Notion page.
get_notion_page_comments
Get comments on a Notion page.
search_google_drive_files
Search for a file in Google Drive.
read_google_doc
Read the content of a Google Document.
read_google_sheet
Read the content of a Google Sheet.
list_workspaces
List all workspaces available in the workspace.
switch_workspace
Switch the current workspace.
The Agent Hub
GitHub for Data Engineering Agents.
Start with seven production-ready reference agents from Paradime. Fork them, customize the prompt and toolset, then publish your version to your team's catalog.
When a pipeline fails, the Commander spawns parallel sub-agents to read logs, profile the warehouse, and notify owners — then posts a structured incident report with a proposed fix to Slack.
Auto-retries with smart backoff, isolates the failing model, generates a targeted fix in an isolated sandbox, and re-runs only what's downstream. Closes the loop with a PR for review.
Hunts idle warehouses, unclustered tables, and runaway queries. Files a weekly PR with commits that compound — typically 20–40% off the Snowflake bill in the first quarter.
Watches source schemas. When upstream changes, it diffs the structure, updates source definitions, regenerates staging models, runs tests, and opens a PR before anything downstream breaks.
Generates column-level descriptions, model docs, and lineage notes grounded in real query patterns. Bi-directional sync keeps your yaml, Confluence pages, and data catalog aligned.
Audits your dbt™ project for missing tests, infers what each model actually needs from its lineage and column types, and proposes the tests in a PR — no busywork, no boilerplate.
Reviews every dbt™ pull request for SQL anti-patterns, breaking schema changes, missing tests, and lineage impact. Posts inline comments and approves only when the model is production-ready.
*dbt® and dbt Core® are federally registered trademarks of dbt Labs, Inc. in the United States and various jurisdictions around the world. Paradime is not a partner of dbt Labs. All rights therein are reserved to dbt Labs. Paradime is not a product or service of or endorsed by dbt Labs, Inc.
*dbt® and dbt Core® are federally registered trademarks of dbt Labs, Inc. in the United States and various jurisdictions around the world. Paradime is not a partner of dbt Labs. All rights therein are reserved to dbt Labs. Paradime is not a product or service of or endorsed by dbt Labs, Inc.
*dbt® and dbt Core® are federally registered trademarks of dbt Labs, Inc. in the United States and various jurisdictions around the world. Paradime is not a partner of dbt Labs. All rights therein are reserved to dbt Labs. Paradime is not a product or service of or endorsed by dbt Labs, Inc.