// SCAN REPORT

Azure DevOps MCP Server

41 tools. 12 can modify or destroy data without limits.

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

Last updated: 29 Jun 2026

12 can modify or destroy data

29 read-only

41 tools total

Community server · catalogue entry verified 29/06/2026

How to control Azure DevOps MCP Server ↓

TOOL MAP

What Azure DevOps MCP Server exposes to your agents

Read (29) Write / Execute (9) Destructive / Financial (3)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Azure DevOps MCP Server tools

Destructive · High delete_wiki This tool permanently removes a wiki, which is an irreversible action that destroys data and cannot be undone. Destructive · High delete_wiki_page Deleting a wiki page is an irreversible operation that permanently removes documentation content. Destructive · High remove_work_item_relation Removing a relationship is destructive because it irreversibly deletes metadata (the link itself) that connects two work items. Write · Low add_comment This tool creates new data (a comment) but does not delete, execute arbitrary code, or move money.

12 of Azure DevOps MCP Server's 41 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

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:

Deny destructive operations

{
  "delete_wiki": {
    "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_field_exists": {
    "limits": [
      {
        "counter": "check_field_exists_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 Azure DevOps MCP Server — 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 AZURE DEVOPS →

Instant setup, no code required.

FULL CATALOGUE

All 41 Azure DevOps MCP Server tools

DESTRUCTIVE 3 tools

Destructive delete_wiki Delete a wiki Destructive delete_wiki_page Delete a wiki page Destructive remove_work_item_relation Remove a relationship between work items

WRITE 9 tools

Write add_comment Add a comment to a work item Write add_work_item_relation Add a relationship between work items Write create_wiki Create a new wiki. Use type Write create_wiki_page Create a new wiki page Write create_work_item Create a new work item Write move_to_iteration Move a work item to a different iteration/sprint Write set_organization Switch to a different Azure DevOps organization for subsequent commands Write update_wiki_page Update an existing wiki page. Requires the page version (ETag) which can be obtained from get_wiki_page. Write update_work_item Update an existing work item

READ 29 tools

Read check_field_exists Check if a specific field exists in Azure DevOps Read discover_fields Discover available fields in Azure DevOps (compact output with filtering) Read discover_relationships Discover relationship types and link types available Read discover_states Discover valid states and transitions for work item types Read discover_work_item_types List all work item types with compact field summaries Read get_current_iteration Get the current active sprint/iteration Read get_default_project Get the currently configured default project and organization Read get_iteration_details Get detailed information about an iteration including work items grouped by type and state Read get_iteration_work_items Get all work items in a specific iteration Read get_organization Get the currently active Azure DevOps organization Read get_project Get detailed information about a specific project Read get_project_stats Get statistics about work items in a project Read get_wiki Get details of a specific wiki Read get_wiki_page Get the content of a wiki page Read get_work_item Get detailed information about a specific work item Read get_work_item_relations Show all relationships for a work item Read healthcheck Check Azure DevOps connection and configuration status Read inspect_work_item Get RAW complete work item data to see all fields and values Read list_iterations List all iterations/sprints in a project Read list_my_work List work items assigned to me, organized by state Read list_organizations List all Azure DevOps organizations accessible to the current user. Discovers orgs from Azure CLI account and Read list_project_pipelines List all pipelines in a project Read list_project_repos List all repositories in a project Read list_project_teams List all teams in a project Read list_projects List all projects in the Azure DevOps organization Read list_relation_types List all available work item relation types Read list_wikis List all wikis in a project or organization Read query_work_items Query work items using WIQL or predefined queries Read test_query Test a WIQL query and show raw results to understand data structure

EXPLORE

Related servers

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

FAQ

Questions about Azure DevOps MCP Server

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

Yes. The Azure DevOps MCP Server server exposes 3 destructive tools including delete_wiki, delete_wiki_page, remove_work_item_relation. 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 DevOps MCP Server? +

The Azure DevOps MCP Server server has 9 write tools including add_comment, add_work_item_relation, create_wiki. 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? +

41 tools across 3 categories: Destructive, Read, Write. 29 are read-only. 12 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 41 Azure DevOps MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON AZURE DEVOPS →

Instant setup, no code required.

41 Azure DevOps MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.