Azure Devops

97 tools. 40 can modify or destroy data without limits.

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

Last updated:

40 can modify or destroy data
57 read-only
97 tools total

Community server · catalogue entry verified 11/06/2026

How to control Azure Devops ↓

Read (57) Write / Execute (39) Destructive / Financial (1)
Critical Risk

40 of Azure Devops's 97 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

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

Deny destructive operations
{
  "deletePackageVersion": {
    "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
{
  "integrateSarifResults": {
    "limits": [
      {
        "counter": "integratesarifresults_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "predictBuildFailures": {
    "limits": [
      {
        "counter": "predictbuildfailures_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 — 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.

WRITE 30 tools
Write integrateSarifResults Import and process SARIF format security results Write recordExploratoryTestResults Record findings during exploratory testing Write addWorkItemComment Add a comment to a work item Write approvePullRequest Approve a pull request Write assignWorkItem Assign a work item to a user Write bulkCreateWorkItems Create or update multiple work items in a single operation Write configureTestAgents Configure and manage test agents Write convertFindingsToWorkItems Convert exploratory test findings to work items Write createArea Create a new area in a project Write createComplianceReport Create compliance reports for auditing Write createExploratorySessions Create new exploratory testing sessions Write createIntelligentAlerts Set up intelligent alerts based on patterns Write createIteration Create a new iteration in a project Write createLink Create a link between work items Write createPackageDownloadReport Create reports on package downloads Write createProject Create a new project Write createPullRequest Create a new pull request Write createRepository Create a new repository Write createWorkItem Create a new work item Write manageContainerPolicies Manage policies for container repositories Write manageSecurityPolicies Manage security policies Write manageTestEnvironments Manage test environments for different test types Write manageUniversalPackages Manage universal packages Write mergePullRequest Merge a pull request Write moveCardOnBoard Move a card on a board Write promotePackage Promote a package version between views Write publishPackage Publish a package to a feed Write trackSecurityVulnerabilities Track and manage security vulnerabilities Write updateWorkItem Update an existing work item Write updateWorkItemState Update the state of a work item
READ 57 tools
Read predictBuildFailures Predict potential build failures before they occur Read auditSecretUsage Audit usage of secrets across services Read browseRepository Browse the contents of a repository Read checkPackageDependencies Check package dependencies and vulnerabilities Read getAICodeReview Get AI-based code review suggestions Read getAreas Get areas for a project Read getBoardColumns Get columns for a specific board Read getBoardItems Get items on a specific board Read getBoards Get all boards for a team Read getCodeQualityTrends Track code quality trends over time Read getCommitHistory Get commit history for a repository Read getComplianceStatus Get current compliance status Read getContainerImageTags Get tags for a container image Read getCurrentSprint Get the current sprint Read getDeveloperProductivity Measure developer productivity metrics Read getExploratoryTestStatistics Get statistics on exploratory testing activities Read getFileContent Get the content of a file Read getIterations Get iterations for a project Read getMyWorkItems Get work items assigned to you Read getPackageVersions Get versions of a package in a feed Read getPredictiveBugAnalysis Predict potential bugs in code changes Read getPredictiveEffortEstimation AI-based effort estimation for work items Read getProcesses Get all processes Read getProjectDetails Get details of a specific project Read getPullRequest Get details of a specific pull request Read getPullRequestChangedFiles Get changed files in a pull request Read getPullRequestComments Get comments on a pull request Read getRecentlyUpdatedWorkItems Get recently updated work items Read getRepository Get details of a specific repository Read getSecurityScanResults Get results from security scans Read getSprintCapacity Get capacity for a specific sprint Read getSprints Get all sprints for a team Read getSprintWorkItems Get work items in a specific sprint Read getTeamMembers Get members of a team Read getTestAutomationStatus Check status of automated test execution Read getTestFlakiness Analyze and report on test flakiness Read getTestGapAnalysis Identify gaps in test coverage Read getTestHealthDashboard View overall test health metrics Read getWorkItemById Get a specific work item by ID Read getWorkItemTypeFields Get fields for a work item type Read getWorkItemTypes Get work item types for a process Read identifyCodeSmells Identify potential code smells and anti-patterns Read listArtifactFeeds List artifact feeds in the organization Read listBranches List branches in a repository Read listContainerImages List container images in a repository Read listProjects List all projects Read listPullRequests List pull requests Read listRepositories List all repositories Read listWorkItems List work items based on a WIQL query Read scanContainerImage Scan a container image for vulnerabilities and compliance issues Read searchCode Search for code in repositories Read searchWorkItems Search for work items by text Read suggestAutomationOpportunities Identify opportunities for automation Read suggestCodeOptimization Suggest code optimizations using AI Read suggestWorkItemRefinements Get AI suggestions for work item refinements Read trackSecurityAwareness Track security awareness and training Read generateSecurityCompliance Generate security compliance reports

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

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

Yes. The Azure Devops server exposes 1 destructive tools including deletePackageVersion. 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? +

The Azure Devops server has 30 write tools including integrateSarifResults, recordExploratoryTestResults, addWorkItemComment. 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.

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

97 tools across 4 categories: Destructive, Execute, Read, Write. 57 are read-only. 40 can modify, create, or delete data.

How do I enforce a policy on Azure Devops? +

Register the Azure Devops 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 tool call.

Deterministic rules across all 97 Azure Devops tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

97 Azure Devops 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.