F
licenseNot graded
qualityC
maintenanceProvides access to PyTorch CI/CD analytics data including workflows, jobs, test runs, and log analysis through an MCP interface.
4
-
furiosa-dashboard-mcp
Related Servers
Alternatives to furiosa-dashboard-mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityBmaintenanceEnables pulling test data, inspecting telemetry channels, running analysis, and writing results back from any MCP client.MIT
- FlicenseNot gradedqualityDmaintenanceEnables querying Google Search Console data, Core Web Vitals, and PageSpeed insights from the terminal or via MCP tools.-
- FlicenseNot gradedqualityBmaintenanceEnables querying and retrieving materials data from the Materials Project via MCP tools, supporting search, lookup, comparison, and export.1-
- FlicenseNot gradedqualityBmaintenanceExposes Jenkins CI/CD capabilities as MCP tools, including job management, builds, pipelines, and Terraform/GCP log inspection.-
- AlicenseNot gradedqualityDmaintenanceEnables querying Swarmia's Export API for engineering metrics including pull request analytics, DORA metrics, investment balance, and effort reporting through an MCP interface.8MIT
TDQS
A3.7/5.0
Scored across 9 tools
Disambiguation3/5
The data-retrieval tools are distinct, but the five URL-builder tools blur together: get_ir_viewer_url vs get_ir_viewer_compare_url and get_tc_viewer_url vs get_tactic_debug_url are easy to confuse. The descriptions help clarify the differences, but an agent could still pick the wrong viewer builder without careful reading.
Naming Consistency4/5
Tool names are mostly consistent snake_case verb_noun forms (list_*, get_*, compare_*), which is predictable. Minor deviations exist in the URL-builder cluster, especially build_ir_view_recipe_url using 'build' instead of 'get' and the inconsistent 'tc' abbreviation vs full 'tactic'.
Tool Count4/5
Nine tools is a reasonable, well-scoped count for a benchmark dashboard MCP. However, build_ir_view_recipe_url is explicitly a draft/proposed contract with no working renderer, so one tool is currently more speculative than functional.
Completeness4/5
The core read-only workflow is covered: listing benchmarked commits, querying summaries, fetching full summary details, comparing commits, and generating viewer URLs. Minor gaps include no way to enumerate available contexts/clouds/tests directly and no get-commit-by-sha tool, but agents can work around these from the existing list tools.
Maintenance
ActivityMaintained
ResponsivenessSyncing