Release Notes

July 14, 2026

A clearer error when a dataset is queried mid-deployment.

Better error when querying a dataset that's being redeployed — Asking for a dataset's content while it is being (re)deployed now returns a clear "the dataset is being redeployed — retry in about a minute" message instead of a generic backend error

Protection against accidentally overwriting a dataset's data.

Duplicate view name guardrail — Creating or deploying a dataset now fails fast if another dataset in the same workspace already uses the same view name, instead of silently overwriting that dataset's data on the next run. The error names the conflicting dataset (name and ID) so you can rename one or choose a different view name.

Easier dashboard filters, clearer errors, and steadier service when something upstream hiccups.

Build filtered dashboards in one step — beem_build_dashboard can now add a project/category filter (and image widgets) directly, so you no longer have to create the dashboard and then wire the filter up separately
Filters just work — Filter type values are accepted in any capitalization, and filter widgets are automatically given enough height to show their dropdown, fixing the "invisible filter" problem
Clearer filter guidance — The tool now explains that a filter controls only the charts you link to it (so you know to connect all of them) and that detail tables linked to a filter stay empty until a value is picked
Clearer timeouts on large queries — When a dataset query is too large to start in time, you now get a clear "timed out before it could start — retry or use a smaller page size" message instead of a confusing unknown error
One slow operation no longer blocks the rest — If a single operation starts failing repeatedly, only that operation pauses briefly to recover; unrelated tools (like previewing a SQL query) keep working as normal
Friendlier dashboard widget errors — Building a dashboard with a chart type used where a widget type belongs now returns a clear explanation of what to use instead, rather than a generic failure
Cleaner "not found" for missing items — Requesting a resource that doesn't exist now returns a tidy not-found response instead of an internal error

Connector deployment config — New tool to view an organization's Terraform connector config: the endpoint specs, pagination, schedules, and infrastructure behind your REST API and other connectors. Complements the existing source config, which only covers ingestion. You can pull the whole config or narrow to a single connector type or connector. Secret values are never shown — only the references to where they're stored.

More resilient connections — Your session now survives server restarts and updates. If the server restarts mid-conversation, the connection picks back up instead of dropping with a "session terminated" error, so you can keep working without reconnecting
Dashboard widget fix — Heading, text, and filter widgets created through the MCP are now always saved with the right settings, so dashboards no longer open to a blank page
Chart validation — Charts created through the MCP are now checked against the settings each chart type needs, so a misconfigured chart is caught up front with a clear explanation instead of silently failing to display
Remove widgets — New tool to delete a widget from a dashboard when it was added by mistake or is no longer needed

Fewer dropped sessions — Idle connections now stay active much longer, so stepping away and coming back no longer interrupts your session with a "session terminated" message

Clearer validation errors — Calling a tool without a required input now returns an immediate, specific message about what's missing, instead of failing partway through with a confusing error
Security updates — Upgraded dependencies to resolve security advisories

Query result fix — Datasets that returned no rows in certain formats now display their data correctly
More reliable results — Queries against older datasets no longer fail on incomplete records

Improved stability — Fixed memory issues that could slow down the service and cause periodic restarts, so the connection stays fast and steady

Major update with composite tools, richer responses, and interactive views.

Composite tools — 10 new high-level tools that combine multiple operations into single steps: beem_workspace_overview, beem_dataset_details, beem_explore_schema, beem_search, beem_pipeline_health, beem_create_and_deploy_dataset, beem_create_and_deploy_dataset_test, beem_deploy_and_wait, beem_build_dashboard, and beem_await_operation
Edit dataset schedule — New beem_edit_dataset_schedule tool lets you add, change, or remove a dataset's automatic refresh schedule in one step — no need to manually redeploy
Deep links in every response — Tool results now include clickable "Open in BEEM" links for datasets, dashboards, flows, sources, and other entities, taking you straight to the right page in the web app
Interactive cards — Supporting clients (Claude Desktop, claude.ai, Cursor, VS Code Copilot) now render rich HTML cards with status indicators, row counts, and action buttons alongside tool results
Server-side polling — Long-running operations (deploys, queries) now poll server-side with a circuit breaker, eliminating repeated client round-trips
Smarter error messages — Tool errors now include actionable hints and suggested next steps instead of raw error codes
Security hardening — Added rate limiting, persistent client registrations across restarts, and cache TTL enforcement

Landing page — Visiting the server URL in a browser now shows a branded page with setup instructions and links to documentation

Reliability improvements, a new tool, and longer sessions.

Source configuration tool — New beem_get_organization_source_config tool lets you inspect your organization's source configuration (e.g. Tempo, Procore), with optional filtering by source and table key
Improved dataset test reliability — Dataset test creation now self-heals when the backend returns an incorrect resource identifier, matching existing behavior for datasets
Auth improvement — Sessions now stay active as long as you use BEEM at least once every 7 days
Reliability & observability — Added error tracking, usage analytics, and automated status page incident management to improve service quality and transparency
Security fixes

Initial release of the BEEM MCP Server — connect your AI assistant to the BEEM data platform.

Explore your data — Browse workspaces, folders, datasets, and data sources using natural language
Query datasets — Retrieve rows from any dataset or preview SQL results before committing changes
Build SQL views — Create datasets, write SQL queries, and deploy them as live views with scheduling
Data quality testing — Create and run tests against your datasets to validate data integrity
Monitor pipelines — Check pipeline execution history, identify failures, and review DPU usage
Manage dashboards — Create dashboards, add widgets, and build visualizations from your datasets
Track data flows — View how datasets connect to destinations through flows
Works everywhere — Available on Claude.ai, Claude Desktop, Claude Code, GitHub Copilot, ChatGPT, and any MCP-compatible client