Azure DevOps

84 tools. 29 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated:

29 can modify or destroy data
55 read-only
84 tools total
Read (55) Write / Execute (28) Destructive / Financial (1)

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

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

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

One command. Full control.

Intercept sits between your agent and Azure DevOps. Every tool call checked against your policy before it executes — so your agent can do its job without breaking things.

npx -y @policylayer/intercept scan -- npx -y @@azure-devops/mcp
Scans every tool. Generates a policy. Starts enforcing.
Works with Claude Code · Cursor · Claude Desktop · Windsurf · any MCP client
Deny destructive operations
mcp_ado_wit_work_item_unlink:
  rules:
    - action: deny

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

Rate limit write operations
mcp_ado_pipelines_create_pipeline:
  rules:
    - rate_limit: 30/hour

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
mcp_ado_advsec_get_alert_details:
  rules:
    - rate_limit: 60/minute

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

READ 55 tools
Read mcp_ado_advsec_get_alert_details Read mcp_ado_advsec_get_alerts Read mcp_ado_core_get_identity_ids Read mcp_ado_core_list_project_teams Read mcp_ado_core_list_projects Read mcp_ado_pipelines_download_artifact Read mcp_ado_pipelines_get_build_changes Read mcp_ado_pipelines_get_build_definition_revisions Read mcp_ado_pipelines_get_build_definitions Read mcp_ado_pipelines_get_build_log Read mcp_ado_pipelines_get_build_log_by_id Read mcp_ado_pipelines_get_build_status Read mcp_ado_pipelines_get_builds Read mcp_ado_pipelines_get_run Read mcp_ado_pipelines_list_artifacts Read mcp_ado_pipelines_list_runs Read mcp_ado_repo_get_branch_by_name Read mcp_ado_repo_get_pull_request_by_id Read mcp_ado_repo_get_repo_by_name_or_id Read mcp_ado_repo_list_branches_by_repo Read mcp_ado_repo_list_directory Read mcp_ado_repo_list_my_branches_by_repo Read mcp_ado_repo_list_pull_request_thread_comments Read mcp_ado_repo_list_pull_request_threads Read mcp_ado_repo_list_pull_requests_by_commits Read mcp_ado_repo_list_pull_requests_by_repo_or_project Read mcp_ado_repo_list_repos_by_project Read mcp_ado_repo_search_commits Read mcp_ado_search_code Read mcp_ado_search_wiki Read mcp_ado_search_workitem Read mcp_ado_testplan_list_test_cases Read mcp_ado_testplan_list_test_plans Read mcp_ado_testplan_list_test_suites Read mcp_ado_testplan_show_test_results_from_build_id Read mcp_ado_wiki_get_page Read mcp_ado_wiki_get_page_content Read mcp_ado_wiki_get_wiki Read mcp_ado_wiki_list_pages Read mcp_ado_wiki_list_wikis Read mcp_ado_wit_get_query Read mcp_ado_wit_get_query_results_by_id Read mcp_ado_wit_get_work_item Read mcp_ado_wit_get_work_item_type Read mcp_ado_wit_get_work_items_batch_by_ids Read mcp_ado_wit_get_work_items_for_iteration Read mcp_ado_wit_list_backlog_work_items Read mcp_ado_wit_list_backlogs Read mcp_ado_wit_list_work_item_comments Read mcp_ado_wit_list_work_item_revisions Read mcp_ado_wit_my_work_items Read mcp_ado_work_get_iteration_capacities Read mcp_ado_work_get_team_capacity Read mcp_ado_work_list_iterations Read mcp_ado_work_list_team_iterations
Can an AI agent delete data through the Azure DevOps MCP server? +

Yes. The Azure DevOps server exposes 1 destructive tools including mcp_ado_wit_work_item_unlink. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Azure DevOps? +

The Azure DevOps server has 26 write tools including mcp_ado_pipelines_create_pipeline, mcp_ado_repo_create_branch, mcp_ado_repo_create_pull_request. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.

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

84 tools across 4 categories: Destructive, Execute, Read, Write. 55 are read-only. 29 can modify, create, or delete data.

How do I add Intercept to my Azure DevOps setup? +

One line change. Instead of running the Azure DevOps server directly, prefix it with Intercept: intercept -c azure-devops.yaml -- npx -y @@@azure-devops/mcp. Download a pre-built policy from policylayer.com/policies/azure-devops and adjust the limits to match your use case.

Other MCP servers with similar tools.

Starter policies available for each. Same risk classification, same one-command setup.

policylayer/intercept

Control every MCP tool call
your agent makes.

Set budgets, approvals, and hard limits across MCP servers.

npx -y @policylayer/intercept init
Protect your agent in 30 seconds. Scans your MCP config and generates enforcement policies for every server.
// GET IN TOUCH

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

Message sent.

We'll get back to you soon.