Skip to content

Create initial vally experiments for Azure MCP tool effectiveness. #3015

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
LarryOsterman wants to merge 5 commits into
base: main
Choose a base branch
from
Draft

Create initial vally experiments for Azure MCP tool effectiveness. #3015

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
e38f5b3
Added initial vally evaluations for eventhubs tools
LarryOsterman Jul 8, 2026
54a5b93
Added namespace-get tool evaluations; updated script
LarryOsterman Jul 8, 2026
3ee2446
Script supports multiple runs; Refactored script so that post-eval re…
LarryOsterman Jul 9, 2026
b7b6f0d
Enable execute mode on script
LarryOsterman Jul 9, 2026
6b6bc5d
PR feedback
LarryOsterman Jul 10, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions .vscode/cspell.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -406,14 +406,18 @@
"eastasia",
"eastus",
"eastus2euap",
"ehns",
"elicitations",
"enumerables",
"environmentcredential",
"eslintcache",
"esrp",
"esrprelpacmantest",
"evals",
"eventgrid",
"eventhouse",
"eventhub",
"eventhubs",
"exfiltration",
"fabmcp",
"fabricmcp",
Expand Down Expand Up @@ -485,6 +489,7 @@
"microbundle",
"microsoftdocs",
"midsole",
"mojibake",
"monitoredresources",
"msal",
"msrp",
Expand Down Expand Up @@ -601,6 +606,7 @@
"uniqueprefix",
"upns",
"usersession",
"vally",
"vectorizable",
"vectorizer",
"vectorizers",
Expand Down
4 changes: 4 additions & 0 deletions servers/Azure.Mcp.Server/CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,6 +50,10 @@ The Azure MCP Server updates automatically by default whenever a new release com
- `eventhubs namespace-get` now correctly supports subscription-wide listing when `--resource-group` is omitted, and treats a whitespace resource group as not provided for robust scope handling. [[#2961](https://github.com/microsoft/mcp/pull/2961)]
- `foundryextensions resource-get` routing and terminology were clarified to improve namespace tool selection confidence, and validation now fails fast when `--resource-name` is provided without `--resource-group`. [[#2961](https://github.com/microsoft/mcp/pull/2961)]

### Other Changes

- Added a [vally](https://microsoft.github.io/vally) evaluation harness under `servers/Azure.Mcp.Server/tests/Vally` with a first experiment for the `eventhubs_eventhub_get` and `eventhubs_namespace_get` tools. A discovery-based runner script (`Invoke-VallyEval.ps1`) walks the directory for evaluations organized by area (namespace subfolder) and tool (`<tool>.experiment.yaml`). Each experiment runs a shared eval spec (`<tool>.eval.yaml`) as two variants—baseline (without the Azure MCP server) and treatment (with it)—to isolate the server's contribution. Both variants are graded identically on task outcome using outcome-based LLM-judge graders, ensuring a fair comparison regardless of whether the baseline succeeds through other means (e.g. Azure CLI). Each area may supply `New-*Resources.ps1` / `Remove-*Resources.ps1` provisioning scripts (auto-discovered and run per area); the Event Hubs pair creates the required resources (tagged with `DeleteAfter` as a clean-up safety net, with local auth disabled for Safe Secrets Standard compliance) and deletes them afterwards.

## 3.0.0-beta.21 (2026-06-23)

### Features Added
Expand Down
3 changes: 3 additions & 0 deletions servers/Azure.Mcp.Server/tests/Vally/.gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
# Vally run artifacts (trajectories, results.jsonl, eval-results.md, etc.)
.vally-results/
vally-results/
Loading