How do I use ado-mcp?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@ado-mcp show my assigned work items" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

ado-mcp

by og-mcp

Overview Schema Source Related Servers Discussions Admin

TypeScript

Hybrid

Azure DevOps MCP Server

A production-grade Model Context Protocol server for Azure DevOps. Exposes Azure DevOps operations as MCP tools (plus, in later phases, resources and prompts) over stdio (local) and Streamable HTTP (hosted/multi-user).

TypeScript (ESM, Node 20+)
ADO access via the official azure-devops-node-api SDK, with an axios REST fallback for endpoints the SDK doesn't cover (search, analytics, etc.)
Three auth modes: PAT, Azure CLI (az login), On-Behalf-Of + Entra JWT (hosted)
Per-tool RBAC, destructive-op guard, secret redaction, structured logging, retry with backoff

Status: All 6 phases complete — 113 tools across 13 domains, plus 4 MCP resources and 4 MCP prompts:
core (7) · repos (15) · pullrequests (12) · workitems (16) · boards (10)
pipelines (13) · releases (8) · testplans (10) · wiki (7) · search (3) · artifacts (5)
security (5) · analytics (2)
Resources: ado://projects, ado://project/{project}/repos, ado://project/{project}/workitem/{id}, ado://project/{project}/repo/{repo}/pullrequest/{prId}
Prompts: pr-review, release-readiness, sprint-planning, bug-triage
Hardening: per-host circuit breaker, retry w/ backoff + Retry-After, secret redaction, per-tool RBAC + destructive guard, audit logging, ESLint, a Vitest suite (unit + live MCP-protocol test), and an Azure Pipelines CI (azure-pipelines.yml).

1. Prerequisites

Node.js ≥ 20 and npm
An Azure DevOps organization you can access
One of:
- a Personal Access Token (PAT), or
- the Azure CLI installed and az login completed, or
- (hosted) an Entra app registration with the ADO delegated permission, for OBO

Related MCP server: Azure DevOps MCP Server (Python)

2. Install

cd "E:\MCP Servers\ado-mcp-server"
npm install

3. Configure

cp .env.example .env      # PowerShell: Copy-Item .env.example .env

Edit .env. Minimum for a quick local start with the Azure CLI:

ADO_ORG=YourOrgName
ADO_DEFAULT_PROJECT=YourProject
AUTH_MODE=azcli

Auth modes

`AUTH_MODE`	Needs	Notes
`azcli`	`az login` done locally	Easiest for dev. No secrets stored.
`pat`	`ADO_PAT`	PAT scopes must cover the tools you call (e.g. Work Items: Read & Write, Code: Read & Write).
`obo`	`AZURE_TENANT_ID`, `AZURE_CLIENT_ID`, `AZURE_CLIENT_SECRET`	HTTP transport only. Validates the caller's Entra JWT, then exchanges it for an ADO token preserving the user's identity.

A PAT is created in Azure DevOps → User settings → Personal access tokens.

4. Build & run

npm run build      # compile to dist/
npm start          # stdio transport (default)

Development with auto-reload:

npm run dev        # stdio
npm run dev:http   # Streamable HTTP on PORT (default 3000)

Force a transport regardless of TRANSPORT:

node dist/index.js --transport http
node dist/index.js --transport stdio

5. Connect a client

Claude Desktop / VS Code / Claude Code (stdio)

Add to your MCP client config (e.g. Claude Desktop claude_desktop_config.json).

Published package via npx (recommended distribution — no clone, no build):

{
  "mcpServers": {
    "azure-devops": {
      "command": "npx",
      "args": ["-y", "ado-mcp-server"],
      "env": {
        "ADO_ORG": "YourOrgName",
        "ADO_DEFAULT_PROJECT": "YourProject",
        "AUTH_MODE": "pat",
        "ADO_PAT": "<your-pat>"
      }
    }
  }
}

Local build via node (for development on a clone):

{
  "mcpServers": {
    "azure-devops": {
      "command": "node",
      "args": ["E:\\MCP Servers\\ado-mcp-server\\dist\\index.js"],
      "env": {
        "ADO_ORG": "YourOrgName",
        "ADO_DEFAULT_PROJECT": "YourProject",
        "AUTH_MODE": "azcli"
      }
    }
  }
}

The org is never hardcoded — it comes from ADO_ORG in the client's env block, so the same published package serves any org.

Remote / hosted (Streamable HTTP)

node dist/index.js --transport http

Endpoint: POST http://localhost:3000/mcp · health: GET /health. In obo mode every request must carry Authorization: Bearer <Entra access token>.

6. Verify it works

# Health (HTTP mode)
curl http://localhost:3000/health

# From an MCP client, call the connectivity probe tool:
#   ado_get_me      → confirms auth + org connection
#   ado_list_projects

A scripted stdio smoke test (lists tools without calling ADO):

printf '%s\n' \
 '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"smoke","version":"1.0"}}}' \
 '{"jsonrpc":"2.0","method":"notifications/initialized"}' \
 '{"jsonrpc":"2.0","id":2,"method":"tools/list","params":{}}' \
 | ADO_ORG=x AUTH_MODE=pat ADO_PAT=dummy node dist/index.js

7. Publishing (npx distribution)

This server is distributed as an npm package so anyone can run it with npx ado-mcp-server — no clone or build on their side.

npm run build          # compile (also runs automatically via prepublishOnly)
npm version patch      # bump version
npm publish            # publishes; only dist/, README.md, .env.example ship (see "files")

After publishing, the npx client config in §5 works as-is. To test the package contents before publishing:

npm pack --dry-run     # lists exactly what will be uploaded
npm pack               # builds the .tgz locally; install it to smoke-test

Auth for distributed use: prefer AUTH_MODE=pat — each user supplies their own ADO_PAT (and ADO_ORG) in their MCP client's env. azcli only works where the user has the Azure CLI installed and az login completed.

8. Scripts

Script	Purpose
`npm run build`	Compile TypeScript → `dist/`
`npm start`	Run compiled server (stdio)
`npm run start:http`	Run compiled server (HTTP)
`npm run dev` / `dev:http`	Watch-mode dev (tsx)
`npm run typecheck`	`tsc --noEmit`
`npm run lint`	ESLint
`npm test`	Vitest

9. Configuration reference

See .env.example. Key vars: ADO_ORG, ADO_DEFAULT_PROJECT, ADO_API_VERSION, AUTH_MODE, ADO_PAT, AZURE_TENANT_ID/CLIENT_ID/CLIENT_SECRET, TRANSPORT, PORT, LOCAL_ROLE, LOG_LEVEL, ALLOW_DESTRUCTIVE.

ALLOW_DESTRUCTIVE — destructive tools (delete_*, complete PR, deploy release, …) are blocked unless this is true.
LOCAL_ROLE — effective RBAC role in pat/azcli modes (admin/editor/viewer). In obo mode roles come from Entra App Roles on the caller's token.

10. Architecture (short)

transport (stdio | http)
  → server (McpServer + registry)
    → dispatch (RBAC · destructive guard · audit · error envelope)
      → domain tools (Zod schemas)
        → domain services
          → AdoClient (azure-devops-node-api SDK | REST fallback + retry)
            → auth (PAT | AzCli | OBO credential)

Each ADO area is a self-contained module under src/domains/<area>/ exporting a DomainModule. To add an area, create the module and append it to domains in src/server.ts — nothing else changes.

Full walkthrough: see docs/END_TO_END_FLOW.md for how a request travels through every layer (startup, a tool call step by step, auth flows, resources/prompts, reliability, and a worked example).

Available Tools

113 tools

ado_abandon_pull_requestA

Destructive

Abandon (close without merging) a pull request. Destructive.

Inputs: prId (required), repoId (required), project.

ado_add_pr_reviewersB

Add reviewers (by identity ID) to a pull request.

Inputs: prId (required), repoId (required), reviewerIds (required), project.

ado_add_test_casesC

Add existing test case work items to a suite.

Inputs: planId (required), suiteId (required), workItemIds (required), project.

ado_add_work_item_attachmentC

Upload a text attachment and link it to a work item.

Inputs: id (required), content (required), fileName (required), comment, +1 more.

ado_add_work_item_commentB

Add a comment to a work item.

Inputs: id (required), text (required), project.

ado_approve_releaseA

Destructive

Approve or reject a pending release approval. Destructive — gates a deployment.

Inputs: decision (required), approvalId (required), project, comments.

ado_bulk_create_work_itemsB

Create multiple work items in one call.

Inputs: items (required), project.

ado_bulk_export_work_itemsA

Read-only

Export work items selected by a WIQL query (batched for large result sets).

Inputs: query (required), fields, project.

ado_cancel_buildB

Cancel an in-progress build.

Inputs: buildId (required), project.

ado_code_searchA

Read-only

Full-text search across code in the organization (or a project). Requires the Code Search extension.

Inputs: searchText (required), top, skip, project.

ado_complete_pull_requestA

Destructive

Complete (merge) a pull request. Destructive — merges code and optionally deletes the source branch.

Inputs: prId (required), repoId (required), project, bypassPolicy, +3 more.

ado_create_branchA

Create a new branch from the tip of an existing source branch.

Inputs: repoId (required), newBranch (required), sourceBranch (required), project.

ado_create_classification_nodeA

Create an area or iteration path node (admin). For iterations, pass start/finish dates in attributes.

Inputs: name (required), structureGroup (required), project, attributes, +1 more.

ado_create_projectA

Create a new project (async operation; returns an OperationReference). Resolves the process template by name when an explicit ID is not given.

Inputs: name (required), visibility, description, sourceControl, +2 more.

ado_create_pr_threadA

Start a new comment thread on a pull request (optionally anchored to a file).

Inputs: prId (required), repoId (required), content (required), project, +1 more.

ado_create_pull_requestB

Create a pull request from a source branch into a target branch.

Inputs: title (required), repoId (required), sourceBranch (required), targetBranch (required), +4 more.

ado_create_pushB

Commit and push one or more file add/edit/delete changes to a branch in a single push.

Inputs: branch (required), repoId (required), changes (required), comment (required), +1 more.

ado_create_releaseC

Create a release from a release definition.

Inputs: definitionId (required), isDraft, project, artifacts, +1 more.

ado_create_repoB

Create a new Git repository in a project.

Inputs: name (required), project.

ado_create_tagB

Create an annotated tag pointing at a commit.

Inputs: name (required), repoId (required), message (required), objectId (required), +1 more.

ado_create_test_planC

Create a test plan.

Inputs: name (required), project, areaPath, iteration, +1 more.

ado_create_test_runB

Create a test run for a plan (optionally over specific test points).

Inputs: name (required), planId (required), project, pointIds, +1 more.

ado_create_test_suiteA

Create a test suite under a parent suite in a plan (static/requirement/query).

Inputs: name (required), planId (required), parentSuiteId (required), project, +3 more.

ado_create_wikiB

Create a project wiki.

Inputs: name (required), project.

ado_create_wiki_pageB

Create a wiki page at a path with markdown content.

Inputs: path (required), wikiId (required), content (required), project.

ado_create_work_itemB

Create a work item (Bug, Task, User Story, Epic, …). Pass fields as a map; optionally set a parent.

Inputs: type (required), fields (required), project, parentId.

ado_delete_repoA

Destructive

Permanently delete a Git repository. Destructive.

Inputs: repoId (required), project.

ado_delete_wiki_pageB

Destructive

Delete a wiki page by path. Destructive.

Inputs: path (required), wikiId (required), project.

ado_delete_work_itemA

Destructive

Delete a work item (recycle bin by default; destroy=true is permanent). Destructive.

Inputs: id (required), destroy, project.

ado_deploy_releaseB

Destructive

Trigger deployment of a release to an environment/stage. Destructive — initiates a deployment.

Inputs: releaseId (required), environmentId (required), comment, project.

ado_get_aclsA

Read-only

Get access control lists for a security namespace, optionally scoped to a token.

Inputs: namespaceId (required), token, includeExtendedInfo.

ado_get_analytics_metadataA

Read-only

Fetch the Analytics OData $metadata (the entity model / available fields) as XML.

Inputs: project.

ado_get_backlog_work_itemsC

Read-only

Get the work items at a given backlog level for a team.

Inputs: backlogId (required), team, project.

ado_get_board_columnsB

Read-only

Get the columns configured on a board.

Inputs: board (required), team, project.

ado_get_branchA

Read-only

Get details (tip commit, stats) of a branch.

Inputs: name (required), repoId (required), project.

ado_get_buildA

Read-only

Get a single build by ID (status, result, timing).

Inputs: buildId (required), project.

ado_get_build_changesC

Read-only

List the source changes (commits/work items) associated with a build.

Inputs: buildId (required), top, project.

ado_get_build_logA

Read-only

Get the content (lines) of a specific build log.

Inputs: logId (required), buildId (required), project.

ado_get_build_logsA

Read-only

List the available logs for a build.

Inputs: buildId (required), project.

ado_get_commitA

Read-only

Get a single commit by SHA.

Inputs: repoId (required), commitId (required), project.

ado_get_diffsA

Read-only

Get the diff (changed files/commits) between two branches.

Inputs: repoId (required), baseBranch (required), targetBranch (required), top, +2 more.

ado_get_feedA

Read-only

Get a single feed by ID or name.

Inputs: feedId (required), project.

ado_get_fileA

Read-only

Read a file's content and metadata from a repository at an optional branch.

Inputs: path (required), repoId (required), branch, project.

ado_get_group_membersA

Read-only

List the members of a group by its subject descriptor.

Inputs: groupDescriptor (required).

ado_get_meA

Read-only

Return the authenticated identity and Azure DevOps organization connection data. Use this to verify connectivity and auth before other calls.

Inputs: no named parameters.

ado_get_packageB

Read-only

Get a package in a feed by ID.

Inputs: feedId (required), packageId (required), project.

ado_get_pipelineB

Read-only

Get a single pipeline by ID.

Inputs: pipelineId (required), project.

ado_get_pipeline_runB

Read-only

Get the status/result of a specific pipeline run.

Inputs: runId (required), pipelineId (required), project.

ado_get_projectA

Read-only

Get details for a single project, including process and version-control capabilities.

Inputs: project (required), includeCapabilities.

ado_get_pull_requestA

Read-only

Get a single pull request by ID.

Inputs: prId (required), repoId (required), project.

ado_get_queryA

Read-only

Get a saved query by GUID or folder path (includes its WIQL).

Inputs: queryIdOrPath (required), project.

ado_get_releaseA

Read-only

Get a single release (environments, status, artifacts).

Inputs: releaseId (required), project.

ado_get_release_definitionA

Read-only

Get a single release definition (stages, artifacts, triggers).

Inputs: definitionId (required), project.

ado_get_repoB

Read-only

Get a single Git repository by name or ID.

Inputs: repoId (required), project.

ado_get_sprint_work_itemsA

Read-only

Get the work items assigned to a sprint (iteration).

Inputs: iterationId (required), team, project.

ado_get_team_capacityB

Read-only

Get a team's capacity for a sprint (iteration).

Inputs: iterationId (required), team, project.

ado_get_test_planB

Read-only

Get a single test plan by ID.

Inputs: planId (required), project.

ado_get_test_resultsB

Read-only

Get the results of a test run.

Inputs: runId (required), project.

ado_get_test_runA

Read-only

Get a test run by ID (status, totals).

Inputs: runId (required), project.

ado_get_wikiA

Read-only

Get a single wiki by ID or name.

Inputs: wikiId (required), project.

ado_get_wiki_pageA

Read-only

Read a wiki page's content (and ETag) by path.

Inputs: path (required), wikiId (required), project.

ado_get_work_itemA

Read-only

Get a single work item by ID (org-wide lookup; project optional). Optionally expand relations.

Inputs: id (required), fields, project, expandRelations.

ado_get_work_item_commentsA

Read-only

List the comments on a work item.

Inputs: id (required), project.

ado_get_work_itemsA

Read-only

Get multiple work items by their IDs.

Inputs: ids (required), fields, project.

ado_get_work_item_type_fieldsA

Read-only

List the fields defined for a given work item type.

Inputs: type (required), project.

ado_get_work_item_typesA

Read-only

List the work item types available in a project.

Inputs: project.

ado_link_work_itemsB

Link two work items (parent/child/related/duplicate/successor/predecessor or a raw link ref).

Inputs: id (required), linkType (required), targetId (required), comment, +1 more.

ado_list_area_pathsA

Read-only

List the area path classification tree for a project.

Inputs: depth, project.

ado_list_backlogsA

Read-only

List backlog levels (Epics, Features, Stories) for a team.

Inputs: team, project.

ado_list_boardsA

Read-only

List the boards available to a team.

Inputs: team, project.

ado_list_branchesC

Read-only

List branches (refs) in a repository.

Inputs: repoId (required), filter, project.

ado_list_build_definitionsA

Read-only

List build/pipeline definitions in a project.

Inputs: top, name, project.

ado_list_buildsB

Read-only

List builds, optionally filtered by definition and branch.

Inputs: top, branch, project, definitionIds.

ado_list_commitsC

Read-only

List commits in a repository, optionally filtered by branch.

Inputs: repoId (required), top, skip, branch, +1 more.

ado_list_feedsB

Read-only

List artifact feeds (org- or project-scoped).

Inputs: project.

ado_list_groupsA

Read-only

List groups in the organization (Graph API).

Inputs: no named parameters.

ado_list_itemsB

Read-only

List files and folders at a path in a repository.

Inputs: repoId (required), branch, project, recursive, +1 more.

ado_list_iteration_pathsB

Read-only

List the iteration path classification tree for a project.

Inputs: depth, project.

ado_list_packagesB

Read-only

List packages in a feed.

Inputs: feedId (required), top, query, project.

ado_list_package_versionsA

Read-only

List the versions of a package in a feed.

Inputs: feedId (required), packageId (required), project.

ado_list_pipeline_runsC

Read-only

List recent runs of a pipeline.

Inputs: pipelineId (required), project.

ado_list_pipelinesA

Read-only

List YAML pipelines in a project.

Inputs: top, project.

ado_list_pr_commitsA

Read-only

List the commits included in a pull request.

Inputs: prId (required), repoId (required), project.

ado_list_projectsA

Read-only

List all projects in the Azure DevOps organization, with optional state filter and paging.

Inputs: top, skip, stateFilter.

ado_list_pr_threadsB

Read-only

List comment threads on a pull request.

Inputs: prId (required), repoId (required), project.

ado_list_pull_requestsA

Read-only

List pull requests in a repository, filterable by status and source/target branch.

Inputs: repoId (required), top, skip, status, +3 more.

ado_list_queriesA

Read-only

List saved/shared queries in a project.

Inputs: depth, project.

ado_list_release_approvalsB

Read-only

List pending release approvals in a project.

Inputs: top, project.

ado_list_release_definitionsA

Read-only

List classic release definitions in a project.

Inputs: top, project, searchText.

ado_list_releasesC

Read-only

List releases, optionally filtered by definition.

Inputs: top, project, definitionId.

ado_list_reposB

Read-only

List Git repositories in a project.

Inputs: project.

ado_list_security_namespacesA

Read-only

List security namespaces (permission catalogs) in the organization.

Inputs: no named parameters.

ado_list_sprintsA

Read-only

List a team's sprints (iterations), optionally only the current one.

Inputs: team, project, timeframe.

ado_list_tagsB

Read-only

List tags in a repository.

Inputs: repoId (required), project.

ado_list_team_membersB

Read-only

List the members of a team within a project.

Inputs: team (required), project (required), top, skip.

ado_list_teamsB

Read-only

List teams in a project.

Inputs: project (required), top, mine, skip.

ado_list_test_casesB

Read-only

List the test cases in a suite.

Inputs: planId (required), suiteId (required), project.

ado_list_test_plansB

Read-only

List test plans in a project.

Inputs: project.

ado_list_test_suitesB

Read-only

List the test suites in a test plan.

Inputs: planId (required), project.

ado_list_usersA

Read-only

List users in the organization (Graph API).

Inputs: subjectTypes.

ado_list_wikisA

Read-only

List wikis in a project.

Inputs: project.

ado_query_analyticsA

Read-only

Query the Analytics OData feed for reporting. Common entity sets: WorkItems, WorkItemSnapshot, PipelineRuns, Builds. Supports $filter/$select/$orderby/$top/$apply (aggregation).

Inputs: entitySet (required), top, apply, filter, +3 more.

ado_query_work_itemsA

Read-only

Run a WIQL query and return matching work item references.

Inputs: query (required), project.

ado_queue_buildB

Queue a build from a build definition, optionally on a source branch.

Inputs: definitionId (required), branch, project.

ado_reply_pr_threadB

Reply to an existing comment thread on a pull request.

Inputs: prId (required), repoId (required), content (required), threadId (required), +1 more.

ado_run_pipelineA

Queue a run of a YAML pipeline, optionally on a branch and with variables/template parameters.

Inputs: pipelineId (required), branch, project, variables, +1 more.

ado_set_pr_voteB

Cast a vote on a pull request (approve, approve-with-suggestions, reset, wait-for-author, reject). Defaults to the caller.

Inputs: prId (required), vote (required), repoId (required), project, +1 more.

ado_update_projectA

Update a project's name, description, or visibility (async operation; returns an OperationReference).

Inputs: project (required), name, visibility, description.

ado_update_pull_requestA

Update a pull request: title, description, target branch, or draft state.

Inputs: prId (required), repoId (required), title, isDraft, +3 more.

ado_update_wiki_pageA

Update an existing wiki page's content (handles the required ETag automatically).

Inputs: path (required), wikiId (required), content (required), project.

ado_update_work_itemC

Update a work item's fields.

Inputs: id (required), fields (required), project.

ado_wiki_searchB

Read-only

Full-text search across wiki pages.

Inputs: searchText (required), top, skip, project.

ado_work_item_searchA

Read-only

Full-text search across work items.

Inputs: searchText (required), top, skip, project.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.3/5.0

Scored 2026-07-30 12:40 across 113 tools

Disambiguation4/5

Most tools have clearly distinct purposes, especially with well-defined descriptions for different resource types. However, a few pairs like 'ado_list_pipelines' vs 'ado_list_build_definitions' (YAML vs classic builds) could cause minor confusion without careful reading.

Naming Consistency5/5

All tool names follow a strict 'ado_verb_noun' pattern in snake_case. Verbs are consistently imperative (list, get, create, update, delete) and nouns are descriptive (repo, branch, pr, work_item, pipeline, etc.). No naming convention deviations are present.

Tool Count2/5

With 113 tools, the server is extremely comprehensive but far exceeds the typical well-scoped range (3-15). The high number makes it difficult for agents to efficiently navigate and choose the correct tool, and it would benefit from being split into multiple focused servers per Azure DevOps domain.

Completeness5/5

The tool surface covers an impressively broad range of Azure DevOps features: source control, pull requests, work items (with queries, comments, attachments, links), boards, sprints, backlogs, pipelines (YAML and classic), releases, test management, wikis, search, feeds, security, and analytics. Only niche areas like service connections or variable groups are missing, but the core workflows are fully supported.

Maintenance

ActivityInactive

ResponsivenessNo recent community issues

Resources

Related MCP Connectors

hithereiamaliff-mcp-nextcloud
ai.smithery
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Cloud Storage File Systems Workplace & Productivity
239
https://server.smithery.ai/@hithereiamaliff/mcp-nextcloud/mcp
backlog-forge
com.arcanum-plus
Crie épicos, features, histórias e tasks no Azure DevOps a partir de uma conversa.
Project Management Developer Tools
2
https://backlog-forge.arcanum-plus.com/mcp
mcp
com.vibgrate
Query your team's drift, vulnerability, and upgrade data from any AI assistant. OAuth 2.1, 51 tools.
Security Monitoring
2
https://mcp.vibgrate.com
Proofable MCPB
io.github.proofable
Context and control for any AI. Agent identity, scoped access, and proof across tools.
Security Agent Orchestration Autonomous Agents
351
https://mcp.proofable.me/mcp

Related MCP Servers

ado-workflows-mcp
Version Control CI/CD & DevOps Cloud Platforms
grimlor
A
license
A
quality
D
maintenance
Enables AI agents to discover Azure DevOps repositories, manage pull requests, and interact with PR comments and reviews via the Model Context Protocol.
Updated 6 months ago (2026-05-05 22:01 UTC)
45
165 PyPI
1
MIT
Azure DevOps MCP Server
Project Management Version Control Testing & QA Tools
trosinde
F
license
Not graded
quality
D
maintenance
Enables AI assistants to interact with Azure DevOps projects, including work items, test results, Git repositories, and dependency analysis via the Model Context Protocol.
Updated a year ago (2025-11-04 16:12 UTC)
-
Azure DevOps MCP Server
Developer Tools Project Management Version Control
sahilt20
A
license
Not graded
quality
D
maintenance
Enables AI assistants to interact with Azure DevOps for managing work items, repositories, wikis, and automating development workflows.
Updated 10 months ago (2026-01-24 22:07 UTC)
MIT
Azure DevOps MCP Server
CI/CD & DevOps Version Control Project Management
DevHaydon
A
license
Not graded
quality
B
maintenance
Enables AI agents to interact with Azure DevOps resources such as projects, builds, repositories, work items, test plans, and wikis through natural language using the Model Context Protocol.
Updated 2 months ago (2026-08-31 19:19 UTC)
132,683 npm
MIT

Azure DevOps MCP Server

1. Prerequisites

2. Install

3. Configure

Auth modes

4. Build & run

5. Connect a client

Claude Desktop / VS Code / Claude Code (stdio)

Remote / hosted (Streamable HTTP)

6. Verify it works

7. Publishing (npx distribution)

8. Scripts

9. Configuration reference

10. Architecture (short)

Available Tools

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

ado-workflows-mcp

Azure DevOps MCP Server

Azure DevOps MCP Server

Azure DevOps MCP Server