Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": true
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
extensions
{
  "io.modelcontextprotocol/ui": {}
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
list_pull_requestsA

List pull requests matching search criteria.

Returns PR summaries with id, title, status, web_url, and more.

Args: project: Azure DevOps project name. creator_id: Optional GUID to filter by PR creator. reviewer_id: Optional GUID to filter by reviewer. status: PR status filter (default "all"). repository_id: Optional repository ID for repo-scoped queries. top: Maximum number of results (default 50). working_directory: Optional path for ADO context resolution.

query_work_itemsA

Query work items via WIQL and return enriched data.

Executes a WIQL query and returns work item summaries with id, title, state, type, and effort tracking fields.

Args: project: Azure DevOps project name. wiql: WIQL query string. top: Optional maximum number of results. working_directory: Optional path for ADO context resolution.

list_commitsB

List git commits from a local repository.

Returns commit summaries with sha, message, author, date, and repo name. No ADO connection is needed.

Args: repo_path: Absolute path to the local git repository. authors: Optional list of author names/emails to filter by. since: Optional date string to filter commits after (e.g. "2026-01-01"). max_count: Maximum number of commits to return (default 100).

analyze_pr_commentsA

Analyze all comment threads on a PR.

Fetches threads, categorizes by status, and extracts author statistics for a structured overview.

Args: pr_url_or_id: A full PR URL or numeric PR ID. working_directory: Optional path for context resolution.

post_pr_commentA

Post a new comment thread to a PR.

Creates a new comment thread with the specified content and status.

Args: pr_url_or_id: A full PR URL or numeric PR ID. comment_text: Comment body text. status: Thread status (default "active"). working_directory: Optional path for context resolution.

reply_to_pr_commentA

Reply to an existing comment thread.

Adds a reply to a specific thread on a PR.

Args: pr_url_or_id: A full PR URL or numeric PR ID. thread_id: Existing thread ID to reply to. comment_text: Reply body text. working_directory: Optional path for context resolution.

resolve_pr_commentsA

Batch-resolve PR comment threads.

Sets thread status to the target status for a list of thread IDs. Uses partial-success semantics — individual thread errors don't fail the entire batch.

Args: pr_url_or_id: A full PR URL or numeric PR ID. thread_ids: Thread IDs to resolve. status: Target thread status (default "fixed"). working_directory: Optional path for context resolution.

post_pr_commentsA

Batch-post comments to a PR with optional file/line positioning.

Each comment dict has keys: content: str (required) file_path: str | None (optional — anchors to file) line_number: int | None (optional — anchors to line, requires file_path) status: str (optional — default "active")

Iteration context is auto-resolved. Comments are positioned on the latest iteration.

dry_run=True validates and returns what would be posted.

Args: pr_url_or_id: A full PR URL or numeric PR ID. comments: List of comment dicts to post. dry_run: If True, validate without posting. working_directory: Optional path for context resolution.

post_rich_commentsA

Batch-post structured review comments with severity, type, and formatting.

Each comment dict has keys: comment_id: str (required — unique identifier) title: str (required — short heading) content: str (required — comment body) severity: str (optional — "info","suggestion","warning","error","critical") comment_type: str (optional — "general","line","file","suggestion","security","performance") file_path: str | None (optional — anchors to file) line_number: int | None (optional — anchors to line, requires file_path) suggested_code: str | None (optional) reasoning: str | None (optional) business_impact: str | None (optional) tags: list[str] (optional) status: str (optional — default "active") parent_thread_id: int | None (optional — reply to existing thread)

String severity/comment_type values are coerced to enums at this layer. Invalid values return an ActionableError listing valid options.

dry_run=True validates and shows what would be posted without calling the API. filter_self_praise=True (default) removes praise comments authored by the caller.

Args: pr_url_or_id: A full PR URL or numeric PR ID. comments: List of comment dicts to post. dry_run: If True, validate without posting. batch_size: Number of comments per API batch (default 5). filter_self_praise: If True, filter out self-praise comments. working_directory: Optional path for context resolution.

establish_pr_contextA

Create reusable PR context from a URL or numeric ID.

Parses a full PR URL or resolves a numeric PR ID using cached repository context.

Args: pr_url_or_id: A full Azure DevOps PR URL or a numeric PR ID. working_directory: Optional path for context resolution when using a numeric ID.

create_pull_requestB

Create a new pull request via the Azure DevOps SDK.

Constructs a PR from branch names with optional title, description, and draft mode.

Args: source_branch: Source branch name (with or without refs/heads/). target_branch: Target branch name. Defaults to "main". title: Optional PR title. description: Optional PR description. is_draft: Whether to create as a draft PR. working_directory: Optional path for context resolution. work_item_ids: Optional list of work item IDs to link to the PR.

get_pr_file_changesA

List files changed in a PR with iteration metadata.

Returns a list of dicts, each with keys: path, change_type, change_tracking_id, iteration_id.

Uses the latest iteration.

Args: pr_url_or_id: A full PR URL or numeric PR ID. working_directory: Optional path for context resolution.

get_pr_file_contentsA

Fetch file contents for files changed in a PR.

Returns a list of dicts, each with keys: path, content, encoding, size_bytes. Files that fail to fetch are omitted from successes and included as error entries with ai_guidance.

If file_paths is None, fetches all changed files.

Args: pr_url_or_id: A full PR URL or numeric PR ID. file_paths: Optional list of specific file paths to fetch. exclude_extensions: Optional list of file extensions to skip (e.g. [".png", ".lock"]). Case-insensitive; leading dot optional. working_directory: Optional path for context resolution.

get_pr_authorA

Get the identity of a PR's creator.

Returns the display name, GUID, and email of the user who created the pull request.

Args: pr_url_or_id: A full PR URL or numeric PR ID. working_directory: Optional path for context resolution.

get_current_userA

Get the identity of the authenticated user.

Returns the display name and GUID of the user whose credentials are active for Azure DevOps operations. Useful for self-praise filtering, commit attribution, and permission checks.

Args: working_directory: Optional path for context resolution.

get_pull_requestA

Retrieve full PR metadata including reviewers, labels, and work items.

Args: pr_url_or_id: A full PR URL or numeric PR ID. working_directory: Optional path for context resolution.

update_pull_requestA

Update title and/or description of an existing PR.

Args: pr_url_or_id: A full PR URL or numeric PR ID. title: New title (optional). description: New description (optional). working_directory: Optional path for context resolution. work_item_ids: Optional list of work item IDs to link to the PR.

retarget_pull_requestA

Change the target branch of an existing PR.

Args: pr_url_or_id: A full PR URL or numeric PR ID. target_branch: New target branch name. working_directory: Optional path for context resolution.

set_pr_draft_statusA

Toggle a PR between draft and published state.

Args: pr_url_or_id: A full PR URL or numeric PR ID. is_draft: True to mark as draft, False to publish. working_directory: Optional path for context resolution.

abandon_pull_requestA

Abandon (close without merging) an existing PR.

Args: pr_url_or_id: A full PR URL or numeric PR ID. working_directory: Optional path for context resolution.

complete_pull_requestA

Complete (merge) a PR with configurable merge strategy.

Args: pr_url_or_id: A full PR URL or numeric PR ID. merge_strategy: One of: squash, noFastForward, rebase, rebaseMerge. delete_source_branch: Whether to delete the source branch after merge. transition_work_items: Whether to transition linked work items. merge_commit_message: Optional merge commit message. bypass_policy: Whether to bypass branch policies. bypass_reason: Required when bypass_policy is True. working_directory: Optional path for context resolution.

add_pr_reviewerA

Add a reviewer to a PR.

Args: pr_url_or_id: A full PR URL or numeric PR ID. reviewer_id: Azure DevOps identity GUID of the reviewer. is_required: Whether the reviewer is required. working_directory: Optional path for context resolution.

remove_pr_reviewerB

Remove a reviewer from a PR.

Args: pr_url_or_id: A full PR URL or numeric PR ID. reviewer_id: Azure DevOps identity GUID of the reviewer. working_directory: Optional path for context resolution.

list_pr_reviewersB

List all reviewers on a PR with vote details.

Args: pr_url_or_id: A full PR URL or numeric PR ID. working_directory: Optional path for context resolution.

add_pr_labelB

Add a label/tag to a PR.

Args: pr_url_or_id: A full PR URL or numeric PR ID. name: Label name. working_directory: Optional path for context resolution.

remove_pr_labelB

Remove a label from a PR.

Args: pr_url_or_id: A full PR URL or numeric PR ID. label_name: Label name to remove. working_directory: Optional path for context resolution.

list_pr_labelsB

List all labels on a PR.

Args: pr_url_or_id: A full PR URL or numeric PR ID. working_directory: Optional path for context resolution.

get_pr_work_itemsA

List work items linked to a PR (read-only).

Args: pr_url_or_id: A full PR URL or numeric PR ID. working_directory: Optional path for context resolution.

get_pr_review_statusA

Get comprehensive review status with vote invalidation detection.

Fetches PR details, reviewer votes, commit history, and detects stale approvals that the raw API buries.

Args: pr_id: Pull request ID. working_directory: Optional path for context resolution.

analyze_pending_reviewsA

Discover PRs needing review attention across a repository.

Lists active PRs, filters by age and creator, and enriches each with staleness detection data.

Args: max_days_old: Exclude PRs older than this many days. Default 30. creator_filter: Optional substring match on PR creator. working_directory: Optional path for context resolution.

list_repo_itemsA

List files and folders at a path on any branch, commit, or tag.

Returns a list of dicts, each with keys: path, is_folder, git_object_type, object_id, commit_id, url.

Context (repository, project, org) is resolved from the cached RepositoryContext unless explicit params are provided.

Args: path: Directory path to list. Defaults to "/". ref: Branch name, commit SHA, or tag. None = default branch. recursion: "none", "oneLevel" (default), or "full". repository: Repository name (overrides context). project: Project name (overrides context). working_directory: Optional path for context resolution.

get_repo_file_contentA

Fetch a single file's content from any branch, commit, or tag.

Returns a dict with keys: path, content, encoding, size_bytes.

Context (repository, project, org) is resolved from the cached RepositoryContext unless explicit params are provided.

Args: path: File path within the repository. ref: Branch name, commit SHA, or tag. None = default branch. repository: Repository name (overrides context). project: Project name (overrides context). working_directory: Optional path for context resolution.

repository_discoveryA

Discover Azure DevOps repositories from local git remotes.

Scans the working directory (or cwd) for git repos, extracts ADO remote metadata, and selects the best match.

Args: working_directory: Path to scan. Defaults to the current working directory when omitted.

discover_all_repositoriesA

List every Azure DevOps repository discovered under the working directory.

Walks the working directory (or cwd) for git repositories with Azure DevOps remotes. Use this tool when another tool surfaces a multi-repo ambiguity error to enumerate the candidate repos so an end user can disambiguate.

Args: working_directory: Path to scan. Defaults to the current working directory when omitted.

set_repository_contextA

Cache repository context for the session.

Sets the working directory and caches discovery results so subsequent tool calls skip redundant git CLI lookups.

Args: working_directory: Path to the git repository root.

get_repository_context_statusA

Inspect current cached context state.

Returns cache state, timestamps, and working directory details. Useful for agents debugging context issues or verifying setup.

clear_repository_contextA

Reset cached context.

Clears cached discovery results, forcing fresh discovery on the next tool call. Idempotent — safe to call even when no context is set.

establish_work_item_contextA

Resolve a work-item URL or numeric ID into a structured context.

Parses a full Azure DevOps work-item URL or resolves a bare numeric work-item ID using the cached repository context. The returned AzureDevOpsWorkItemContext carries the organisation, project, work-item ID, and computed org_url for downstream tools.

Caveat — work board ≠ code repo: when resolving a bare numeric ID against a workspace whose work board lives in a different organisation than any of the discovered code repos, the resolved org_url will land on the code-repo organisation, not the work board's. Prefer passing a full work-item URL whenever one is available.

Args: work_item_url_or_id: A full Azure DevOps work-item URL or a numeric work-item ID. working_directory: Optional path for repository-context resolution when using a numeric ID.

get_work_itemA

Fetch a single work item by URL or numeric ID.

Returns WorkItemDetail with all fields, area path, parent ID, and a full fields dict for type-specific access.

Caveat — work board ≠ code repo: passing a bare numeric ID resolves the org/project from the cached repository context, which can land on the wrong organization when the work board lives in a different tenant than any of the discovered code repos. Prefer passing a full work-item URL whenever one is available.

Args: work_item_url_or_id: A full Azure DevOps work-item URL or a numeric work-item ID. working_directory: Optional path for repository-context resolution when using a numeric ID.

get_work_itemsA

Batch-fetch multiple work items by ID with full field data.

Args: project: Azure DevOps project name. work_item_ids: List of numeric work item IDs. working_directory: Optional path for ADO context resolution.

update_work_itemA

Update fields on an existing work item, addressed by URL or ID.

Accepts a dict of field reference names to values (e.g. {"System.State": "Closed", "System.IterationPath": "..."}).

Caveat — work board ≠ code repo: passing a bare numeric ID resolves the org/project from the cached repository context, which can land on the wrong organization when the work board lives in a different tenant than any of the discovered code repos. Prefer passing a full work-item URL whenever one is available — mutations in the wrong tenant are unrecoverable without manual intervention.

Args: work_item_url_or_id: A full Azure DevOps work-item URL or a numeric work-item ID. fields: Dict mapping field reference names to new values. working_directory: Optional path for repository-context resolution when using a numeric ID.

create_work_itemA

Create a new work item of any type.

Args: project: Azure DevOps project name. work_item_type: Work item type (e.g. "Task", "Bug", "Product Backlog Item"). fields: Dict mapping field reference names to values. parent_id: Optional parent work item ID for hierarchy linking. working_directory: Optional path for ADO context resolution.

move_work_items_to_sprintA

Move work items to a target sprint by updating their iteration path.

Does not auto-include children — callers decide which IDs to move.

Args: project: Azure DevOps project name. work_item_ids: List of work item IDs to move. iteration_path: Target iteration path (e.g. "One\FY26\Q4\2Wk\2Wk22"). working_directory: Optional path for ADO context resolution.

clone_work_itemA

Clone a work item into a new item of the same type, addressed by URL or ID.

Copies all fields from the source, applies optional overrides, and preserves the parent link. Does not close the source.

Caveat — work board ≠ code repo: passing a bare numeric ID resolves the org/project from the cached repository context, which can land on the wrong organization when the work board lives in a different tenant than any of the discovered code repos. Prefer passing a full work-item URL — clones created in the wrong tenant are unrecoverable without manual cleanup.

Args: source_work_item_url_or_id: A full Azure DevOps work-item URL or a numeric work-item ID for the source. field_overrides: Optional dict of fields to override in the clone. working_directory: Optional path for repository-context resolution when using a numeric ID.

get_work_item_type_fieldsA

Discover available fields for a work item type in a project.

Returns field metadata including name, reference name, type, and whether the field is required.

Args: project: Azure DevOps project name. work_item_type: Work item type (e.g. "Task", "Bug"). working_directory: Optional path for ADO context resolution.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/grimlor/ado-workflows-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server