v1.11: Unified phase submission. The ONLY tool for advancing through phases.
AI agents invoke submit_phase to trigger actions in Code Intelligence 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 advances the system through workflow phases, which likely triggers downstream operations (analysis, code modification, writes) depending on which phase is being submitted. Since the server is designed for 'high-confidence code modifications,' phase submission can lead to code writes or structural changes.
From the tool's definition 'Unified phase submission. The ONLY tool for advancing through phases.' - triggers phase transitions in a structured workflow
Attacks that exploit this kind of access
v1.11: Unified phase submission. The ONLY tool for advancing through phases. It is categorised as a Execute tool in the Code Intelligence MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Code Intelligence MCP Server MCP server in PolicyLayer and add a rule for submit_phase: 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 Code Intelligence MCP Server. Nothing to install.
submit_phase 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 submit_phase 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 submit_phase. 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.
submit_phase is provided by the Code Intelligence MCP Server MCP server (tech-spoke/llm-helper). 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 →