// SCAN REPORT

Azure Boards MCP

52 tools. 8 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated: 6 Jun 2026

8 can modify or destroy data

44 read-only

52 tools total

Free to start. No card required.

TOOL MAP

Read (44) Write / Execute (6) Destructive / Financial (2)

WHAT CAN GO WRONG

Destructive tools (cancel_build, delete_work_item) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.

Write operations (add_comment, create_release, create_work_item) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.

Execute tools (queue_build) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.

RECOMMENDED RULES

Deny destructive operations

{
  "cancel_build": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "add_comment": {
    "limits": [
      {
        "counter": "add_comment_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "check_permissions": {
    "limits": [
      {
        "counter": "check_permissions_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

ALL 52 AZURE BOARDS MCP TOOLS

DESTRUCTIVE 2 tools

Destructive cancel_build Destructive delete_work_item

EXECUTE 1 tools

Execute queue_build

WRITE 5 tools

Write add_comment Write create_release Write create_work_item Write link_work_items Write update_work_item

READ 44 tools

Read check_permissions Read get_backlog Read get_board Read get_build Read get_build_log_content Read get_build_logs Read get_build_timeline Read get_current_iteration Read get_my_profile Read get_project_info Read get_pull_request Read get_release Read get_release_definition Read get_repository Read get_team_members Read get_work_item Read get_work_item_children Read get_work_item_history Read get_work_item_type_fields Read get_work_item_type_states Read list_all_fields Read list_area_paths Read list_backlog_levels Read list_boards Read list_branches Read list_builds Read list_comments Read list_commits Read list_iteration_paths Read list_iterations Read list_pipelines Read list_projects Read list_pull_requests Read list_recent_work_items Read list_release_definitions Read list_releases Read list_repositories Read list_teams Read list_work_item_types Read query_by_state Read query_current_sprint Read query_my_work_items Read query_wiql Read search_work_items

FAQ

Can an AI agent delete data through the Azure Boards MCP server? +

Yes. The Azure Boards MCP server exposes 2 destructive tools including cancel_build, delete_work_item. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Azure Boards MCP? +

The Azure Boards MCP server has 5 write tools including add_comment, create_release, create_work_item. 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 Boards MCP.

How many tools does the Azure Boards MCP server expose? +

52 tools across 4 categories: Destructive, Execute, Read, Write. 44 are read-only. 8 can modify, create, or delete data.

How do I enforce a policy on Azure Boards MCP? +

Register the Azure Boards 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.

// RELATED SERVERS

Other MCP servers with similar tools.

Starter policies for each. Same risk classification, live on your fleet in minutes.

Enforce policy on every Azure Boards MCP tool call.

Deterministic rules across all 52 Azure Boards MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

SECURE AZURE BOARDS MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

Azure Boards MCP

// TOOL MAP

// WHAT CAN GO WRONG

// RECOMMENDED RULES

// ALL 52 AZURE BOARDS MCP TOOLS

// FAQ