Generate exactly 10 requirement/optimization directions from test evidence (CLI + browser logs/summaries).
AI agents call propose_requirements to retrieve information from AutoDev MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads existing test evidence (CLI and browser logs/summaries) and generates requirement/optimization suggestions. It produces output based on existing data without creating, modifying, executing, or deleting anything. The generation is analytical/read-only in nature.
From the tool's definition Generate exactly 10 requirement/optimization directions from test evidence (CLI + browser logs/summaries)
Attacks that exploit this kind of access
Generate exactly 10 requirement/optimization directions from test evidence (CLI + browser logs/summaries). It is categorised as a Read tool in the AutoDev MCP MCP Server, which means it retrieves data without modifying state.
Register the AutoDev MCP server in PolicyLayer and add a rule for propose_requirements: 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 AutoDev MCP. Nothing to install.
propose_requirements is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the propose_requirements 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 propose_requirements. 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.
propose_requirements is provided by the AutoDev MCP server (rookiejefren/autocoding-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 →