// SCAN REPORT

Azure DevOps MCP Server

42 tools. 11 can modify or destroy data without limits.

11 write tools that can modify data. Rate limits recommended.

Last updated:

11 can modify or destroy data
31 read-only
42 tools total

Community server · catalogue entry verified 10/06/2026

How to control Azure DevOps MCP Server ↓

TOOL MAP

Read (31) Write / Execute (11) Destructive / Financial (0)

MOST DANGEROUS TOOLS

High Risk
Execute · High trigger_pipeline This tool triggers execution of a CI/CD pipeline, which runs code and automated workflows whose effects are determined by the pipeline's configuration and the arguments passed. Write · Low add_pull_request_comment This tool creates new data (a comment) on an existing pull request, which is a reversible write operation. Write · Medium create_branch Creating a branch is a reversible write operation that modifies repository state without deleting data or executing arbitrary code. Write · Medium create_pull_request Creating a pull request is a reversible write operation that adds new metadata/records to the system but does not execute code, destroy data, or move money.

11 of Azure DevOps MCP Server's 42 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

HOW TO CONTROL AZURE DEVOPS MCP SERVER

PolicyLayer is an MCP gateway — it sits between your AI agents and Azure DevOps MCP Server, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations
{
  "add_pull_request_comment": {
    "limits": [
      {
        "counter": "add_pull_request_comment_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "pipeline_timeline": {
    "limits": [
      {
        "counter": "pipeline_timeline_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register Azure DevOps MCP Server — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON AZURE DEVOPS →

Free to start. No card required.

ALL 42 AZURE DEVOPS MCP SERVER TOOLS

EXECUTE 1 tools
Execute trigger_pipeline Trigger a pipeline run
WRITE 10 tools
Write add_pull_request_comment Add a comment to a pull request (repositoryId optional; derived from pullRequestId when omitted) Write create_branch Create a new branch from an existing one Write create_pull_request Create a new pull request, including reviewers, linked work items, and optional tags Write create_wiki Create a new wiki in the project Write create_wiki_page Create a new page in a wiki. If the page already exists at the specified path, it will be updated. Write create_work_item Create a new work item Write manage_work_item_link Add or remove links between work items Write update_pull_request Update an existing pull request with new properties, manage reviewers and work items, and add or remove tags Write update_wiki_page Update content of a wiki page Write update_work_item Update an existing work item
READ 31 tools
Read pipeline_timeline Retrieve the timeline of stages and jobs for a pipeline run, to reduce the amount of data returned, you can fi Read download_pipeline_artifact Download a file from a pipeline run artifact and return its textual content Read get_all_repositories_tree Displays a hierarchical tree view of files and directories across multiple Azure DevOps repositories within a Read get_file_content Get content of a file or directory from a repository Read get_me Get details of the authenticated user (id, displayName, email) Read get_pipeline Get details of a specific pipeline Read get_pipeline_log Retrieve a specific pipeline log using the timeline log identifier Read get_pipeline_run Get details for a specific pipeline run Read get_project Get details of a specific project Read get_project_details Get comprehensive details of a project including process, work item types, and teams Read get_pull_request Get a pull request by ID (no repositoryId required; best for Azure DevOps Server where PR IDs are project-scop Read get_pull_request_changes Get the files changed in a pull request, their unified diffs, source/target branch names, and the status of po Read get_pull_request_comments Get comments from a specific pull request Read get_repository Get details of a specific repository Read get_repository_details Get detailed information about a repository including statistics and refs Read get_repository_tree Displays a hierarchical tree view of files and directories within a single repository starting from an optiona Read get_wiki_page Get the content of a wiki page Read get_wikis Get details of wikis in a project Read get_work_item Get details of a specific work item Read list_commits List recent commits on a branch including file-level diff content for each commit Read list_organizations List all Azure DevOps organizations accessible to the current authentication Read list_pipeline_runs List recent runs for a pipeline Read list_pipelines List pipelines in a project Read list_projects List all projects in an organization Read list_pull_requests List pull requests in a repository Read list_repositories List repositories in a project Read list_wiki_pages List pages within an Azure DevOps wiki Read list_work_items List work items in a project Read search_code Search for code across repositories in a project Read search_wiki Search for content across wiki pages in a project Read search_work_items Search for work items across projects in Azure DevOps

RELATED SERVERS

Other MCP servers with similar tools — same risk classification, starter policies for each.

BNB Chain MCP 1240 tools
automation
Binance MCP Server 734 tools
automation
Nodebench 724 tools
automation
GoHighLevel MCP Server 566 tools
automation
UnClick 451 tools
automation
NowAIKit — ServiceNow AI Toolkit 446 tools
automation
Mcp Windows 441 tools
automation
0nmcp 407 tools
automation

FAQ

How do I prevent bulk modifications through Azure DevOps MCP Server? +

The Azure DevOps MCP Server server has 10 write tools including add_pull_request_comment, create_branch, create_pull_request. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Azure DevOps MCP Server.

How many tools does the Azure DevOps MCP Server MCP server expose? +

42 tools across 3 categories: Execute, Read, Write. 31 are read-only. 11 can modify, create, or delete data.

How do I enforce a policy on Azure DevOps MCP Server? +

Register the Azure DevOps MCP Server MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Azure DevOps MCP Server tool call.

Deterministic rules across all 42 Azure DevOps MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON AZURE DEVOPS →

Free to start. No card required.

42 Azure DevOps MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.