Test DevContainer functionality
AI agents invoke test_devcontainer to trigger actions in DevContainer 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.
Testing a DevContainer requires building and running a container environment, which constitutes executing external operations. If misused, an AI agent could spin up unintended container environments, consume resources, or trigger unintended side effects within the container.
From the tool's definition 'Test DevContainer functionality' — testing a DevContainer involves running the container and executing operations within it
Attacks that exploit this kind of access
Test DevContainer functionality. It is categorised as a Execute tool in the DevContainer MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the DevContainer MCP Server MCP server in PolicyLayer and add a rule for test_devcontainer: 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 DevContainer MCP Server. Nothing to install.
test_devcontainer 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 test_devcontainer 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 test_devcontainer. 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.
test_devcontainer is provided by the DevContainer MCP Server MCP server (siddhant-k-code/mcp-devcontainer). 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 →