The Adaptavist Group LogoDocumentation

August 2026

Check out what's new for Venue.sh! New features, updates, bug fixes—it's all here!

Scorecard rules now use ordered tiers

25 August release

A scorecard rule is no longer a single criterion that every target either passes or fails. You define a stack of tiers. Each tier has its own description and criteria, and repository-content rules can give each tier its own file match. An entity or repository achieves a tier only if that tier and every lower one passed.

  • Tier achievement - The Scorecards list replaces the old Compliance Score chip and Pass / Fail column with a Tier achievement bar (how many targets reached each tier) and a Next target column (the first unmet tier and its description).
  • Entity page - Open a catalog entity's Scorecards tab to see that entity's own stepper and next-target progress, not the rule-wide totals.
  • Repository content - Build tiers with category templates, assisted generation from the tier's description, or by hand. Preview still evaluates every tier against the same fetched snapshot.
  • Missing files fail - If a repository-content tier's file match finds nothing, that tier fails. It does not skip the rest of the stack.

Open Scorecards to create or edit a multi-tier rule, then check the list and a catalog entity's Scorecards tab. See Scorecards and Expressions for how evaluation works.

MCP tools advertise how they behave

25 August release

Tools on the Venue MCP Endpoint now include annotation hints. Your MCP client can treat most Venue tools as read-only and idempotent. A few stay closed-domain: user info, template JSON Schema, and template validation.

These are hints for the client. They do not change what the tools do when you call them. The hints include:

  • read-only - The tool is read-only and does not modify data.
  • destructive - The tool may modify data (e.g., update or delete).
  • idempotent - The tool is idempotent and can be called multiple times without changing the result.
  • open-world - The tool may access data outside of the Venue.sh data model (e.g., external APIs or the internet).

See Venue MCP Endpoint for how to connect Cursor, Claude Desktop, or another MCP client.

Fixes and improvements

25 August release

  • Skills in entity pages - Skills now appear on entity pages, not only in the Skills tab.
  • MCP Apps - The Venue.sh MCP Server now exposes MCP Apps, so AI clients (e.g., Claude, Claude Desktop, VS Code GitHub Copilot) can visualize entity data and click through to the entity page.
  • Consistent dates - Timestamps across the dashboard now use MMM d, yyyy or MMM d, yyyy, hh:mm:ss a. Relative phrases such as "3 minutes ago" are gone, including on agent, MCP server, skills, and plugin entity tabs.
  • Settings copy - AI Settings now describes general AI usage for your organization, rather than repository summaries alone. See Settings and AI Settings.

Create and manage your own API keys

19 August release

Generate personal API keys from Settings, without waiting on a Venue.sh administrator.

  • Self-service creation - Open Settings and create a key with an optional expiry.
  • Reveal once - Venue.sh shows the key once, at creation. Copy it then.
  • Revoke anytime - Remove a key you no longer need.
  • One active key at a time - Creating a new key revokes your existing one, so only the newest key stays valid.

See Settings for where to find your account options.

Connect with the updated MCP protocol

19 August release

The Venue MCP Endpoint now speaks the 2026-07-28 MCP protocol revision.

  • Streamable HTTP transport - The primary transport for MCP clients on the current spec.
  • Legacy endpoint redirect - Venue.sh redirects clients still calling the older /sse endpoint, so most integrations keep working untouched.
  • Cache hints - Static resources such as the tools catalog now declare cache lifetimes, so your AI tool refetches them less often.

If your AI tool cannot follow redirects, update it to call /mcp directly. See Venue MCP Endpoint for connection details.

Fixes and improvements

19 August release

  • TechDocs navigation - Fixed a crash that could occur when a project's mkdocs.yml listed both index.md and README.md for the same folder. We also published a TechDocs authoring guide covering this and other common navigation pitfalls.
  • Archived agents - You can no longer edit an archived agent, so its configuration stays locked until you restore it.

Validate repository content with Scorecards

06 August release

Use repository-content rules to verify that required files exist, or that matching files contain the configuration you expect.

  • Repository targeting - Apply a rule to selected repositories or repositories linked to specific catalog entities.
  • Three ways to author - Start from a category template, describe your goal for assisted generation, or write match and content expressions by hand.
  • Live preview - Review matching files and pass or fail outcomes before you save a rule.
  • Catalog visibility - See repository-content results alongside other Scorecards results on a repository's catalog page.
  • Clearer expressions - Use shared operators for file paths, file names, extensions, existence checks, and file content.

For example, you can check whether package.json exists, whether a repository contains unit tests, or whether configuration files include an expected setting.

See Scorecards for the available authoring methods and Expressions for syntax and examples.

Apply shared metadata during repository imports

06 August release

When you import multiple repositories, set the metadata they share from one place during the configuration step.

  • Bulk metadata - Set shared Kind, Owner, Lifecycle, Namespace, and Tags values for every selected repository.
  • Non-destructive updates - Venue.sh applies only the bulk fields you filled in, so empty fields leave per-repository values alone.
  • Per-repository control - Keep editing individual rows after applying shared values.

See Importing Repos for the complete import workflow.

Explore Development Insights more easily

06 August release

  • Dashboard descriptions - Read each dashboard's description in the dashboard list.
  • Assistant answers - Ask about DORA, Engineering Overview, and Engineering Throughput and Cycle metrics in natural language.
  • Filter-aware results - Name a project, time range, priority, issue type, or DORA report year in your prompt to scope the answer.

For example:

  • "What is our deployment frequency this quarter?"
  • "How does our lead time for changes compare to last month?"
  • "Summarize throughput and cycle time for the platform project."

You need Development Insights read permission and the feature enabled for your organization. See Development Insights and Assistant for details.

More reliable Assistant and dashboards

06 August release

  • Visible reasoning - When you use a supported Claude model with thinking enabled, the thinking panel appears while the response streams.
  • Stable dashboard sections - Development Insights dashboards no longer fail while restoring saved collapsed-section preferences.
  • Consistent controls - Development Insights date controls now follow the surrounding layout instead of holding a fixed height.

Search documentation

Start typing to search the docs.