Make a generic Azure DevOps REST API call
AI agents invoke ado_api_call to trigger actions in MCP Server for Azure DevOps. 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.
A generic API call tool can invoke any Azure DevOps REST endpoint with any HTTP method (GET, POST, PUT, PATCH, DELETE), enabling arbitrary reads, writes, deletions, pipeline triggers, and more.
From the tool's definition "Make a generic Azure DevOps REST API call" — unrestricted REST API access with no specified scope
Attacks that exploit this kind of access
Make a generic Azure DevOps REST API call. It is categorised as a Execute tool in the MCP Server for Azure DevOps MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Server for Azure DevOps MCP server in PolicyLayer and add a rule for ado_api_call: 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 MCP Server for Azure DevOps. Nothing to install.
ado_api_call 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 ado_api_call 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 ado_api_call. 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.
ado_api_call is provided by the MCP Server for Azure DevOps MCP server (sepal7/mcp-ado). 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 →