Interact with specific Azure services. SERVICES: storage, cosmos, search, kusto, monitor, appconfig, keyvault, postgres STORAGE actions: list, listContainers, listBlobs, getContainer, listTables, queryTable COSMOS actions: list, listDatabases, listContainers, query, getContainer SEARCH actions: l...
AI agents invoke azure_service to trigger actions in Azure Omni-Tool MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool spans multiple categories. While many actions are read-only (list, get, listBlobs), it includes Execute-level operations such as running arbitrary queries against Cosmos DB, Kusto, Monitor, and Search; and Write-level operations like setKeyValue, lock, and unlock in AppConfig. The most severe applicable category is Execute due to arbitrary query execution across multiple services.
From the tool's definition Interact with specific Azure services across storage, cosmos, search, kusto, monitor, appconfig, keyvault, postgres — includes 'query' actions (arbitrary query execution), 'setKeyValue' (write to app config), 'lock'/'unlock' (state-changing operations on…
Attacks that exploit this kind of access
Interact with specific Azure services. SERVICES: storage, cosmos, search, kusto, monitor, appconfig, keyvault, postgres STORAGE actions: list, listContainers, listBlobs, getContainer, listTables, queryTable COSMOS actions: list, listDatabases, listContainers, query, getContainer SEARCH actions: list, listIndexes, getIndex, query, getService KUSTO actions: list, listDatabases, listTables, getSchema, sample, query MONITOR actions: list, getWorkspace, listTables, query, listMetrics, getMetrics APPCONFIG actions: list, getStore, listKeyValues, getKeyValue, setKeyValue, lock, unlock KEYVAULT actions: list, getVault, listKeys, getKey, createKey, listSecrets, getSecret, listCertificates POSTGRES actions: list, getServer, listDatabases, listParameters, getParameter, listTables, getTableSchema, query Pass required params for each action (e.g., accountName, resourceGroup, query). It is categorised as a Execute tool in the Azure Omni-Tool MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Azure Omni-Tool MCP Server MCP server in PolicyLayer and add a rule for azure_service: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Azure Omni-Tool MCP Server. Nothing to install.
azure_service is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the azure_service rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for azure_service. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
azure_service is provided by the Azure Omni-Tool MCP Server MCP server (vedantparmar12/azure-_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →