// SCAN REPORT

Ado

59 tools. 14 can modify or destroy data without limits.

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

Last updated: 3 Jul 2026

14 can modify or destroy data

45 read-only

59 tools total

Community server · catalogue entry verified 03/07/2026

How to control Ado ↓

TOOL MAP

What Ado exposes to your agents

Read (45) Write / Execute (11) Destructive / Financial (3)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Ado tools

Destructive · High delete_pipeline Pipeline deletion cannot be undone and eliminates CI/CD infrastructure, build definitions, and associated history. Destructive · High delete_work_item The tool name 'delete_work_item' combined with context of Azure DevOps work item management indicates this performs irreversible deletion of work items. Destructive · High delete_work_items_batch Batch deletion is a destructive operation that irreversibly removes data and cannot be undone. Execute · High run_pipeline_and_get_outcome Running pipelines triggers external operations (builds, deployments, tests) whose effects depend on what the pipeline contains.

14 of Ado's 59 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Ado

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

Deny destructive operations

{
  "delete_pipeline": {
    "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_work_item_comment": {
    "limits": [
      {
        "counter": "add_work_item_comment_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "analyze_pipeline_input": {
    "limits": [
      {
        "counter": "analyze_pipeline_input_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

Create a free account and register Ado — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON ADO →

Instant setup, no code required.

FULL CATALOGUE

All 59 Ado tools

DESTRUCTIVE 3 tools

Destructive delete_pipeline delete_pipeline Destructive delete_work_item delete_work_item Destructive delete_work_items_batch delete_work_items_batch

EXECUTE 4 tools

Execute preview_pipeline preview_pipeline Execute run_pipeline_and_get_outcome run_pipeline_and_get_outcome Execute run_pipeline_by_name run_pipeline_by_name Execute watch_pipeline_by_name watch_pipeline_by_name

WRITE 7 tools

Write add_work_item_comment add_work_item_comment Write create_pipeline create_pipeline Write create_work_item create_work_item Write link_work_items link_work_items Write set_ado_organization Switches the active Azure DevOps organization for the MCP server. Write update_work_item update_work_item Write update_work_items_batch update_work_items_batch

READ 45 tools

Read analyze_pipeline_input analyze_pipeline_input Read check_ado_authentication Verifies that the connection and authentication to Azure DevOps are successful. Read extract_pipeline_run_data extract_pipeline_run_data Read extract_pipeline_run_data_by_name extract_pipeline_run_data_by_name Read find_pipeline_by_id_and_name find_pipeline_by_id_and_name Read find_pipeline_by_name find_pipeline_by_name Read find_project_by_id_or_name find_project_by_id_or_name Read get_build_by_id get_build_by_id Read get_failed_step_logs get_failed_step_logs Read get_log_content_by_id get_log_content_by_id Read get_my_work_items Get work items assigned to a specific user. Read get_pipeline get_pipeline Read get_pipeline_failure_summary_by_name get_pipeline_failure_summary_by_name Read get_pipeline_run get_pipeline_run Read get_pipeline_timeline get_pipeline_timeline Read get_process_details get_process_details Read get_project_process_id get_project_process_id Read get_project_process_info get_project_process_info Read get_project_suggestions get_project_suggestions Read get_recent_work_items Get work items created or modified recently. Read get_work_item get_work_item Read get_work_item_comments get_work_item_comments Read get_work_item_history get_work_item_history Read get_work_item_relations get_work_item_relations Read get_work_item_template get_work_item_template Read get_work_item_templates get_work_item_templates Read get_work_item_type get_work_item_type Read get_work_item_type_field get_work_item_type_field Read get_work_item_type_fields get_work_item_type_fields Read get_work_items_batch get_work_items_batch Read get_work_items_page Get a paginated list of work items with metadata about pagination. Read list_all_projects_with_metadata list_all_projects_with_metadata Read list_area_paths list_area_paths Read list_available_pipelines list_available_pipelines Read list_iteration_paths list_iteration_paths Read list_pipeline_logs list_pipeline_logs Read list_pipelines Lists all pipelines in a given Azure DevOps project. Read list_processes list_processes Read list_projects Lists all projects in the Azure DevOps organization. Read list_service_connections Lists service connections for a given Azure DevOps project. Read list_work_item_types list_work_item_types Read list_work_items List work items in a project using WIQL (Work Item Query Language). Read query_work_items Query work items using WIQL or simple filtering with pagination support. Read resolve_pipeline_from_url resolve_pipeline_from_url Read watch_pipeline watch_pipeline

EXPLORE

Related servers

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

FAQ

Questions about Ado

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

Yes. The Ado server exposes 3 destructive tools including delete_pipeline, delete_work_item, delete_work_items_batch. 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 Ado? +

The Ado server has 7 write tools including add_work_item_comment, create_pipeline, 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 Ado.

How many tools does the Ado MCP server expose? +

59 tools across 4 categories: Destructive, Execute, Read, Write. 45 are read-only. 14 can modify, create, or delete data.

How do I enforce a policy on Ado? +

Register the Ado 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 Ado tool call.

Deterministic rules across all 59 Ado tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON ADO →

Instant setup, no code required.

59 Ado tools catalogued and risk-classified — across an index of 43,000+ MCP servers.