Suggest how to split large bounded contexts based on cohesion analysis
AI agents call suggest_context_splits to retrieve information from MCP Code Analysis Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs semantic analysis of code structure and provides recommendations for refactoring (splitting bounded contexts). It retrieves and analyzes existing code organization but does not execute changes, delete anything, or modify the codebase. The output is advisory guidance based on code analysis, making it a Read category tool with low blast radius if misused by an AI agent.
From the tool's definition Tool name and description: 'suggest_context_splits' provides suggestions based on 'cohesion analysis'. The verb 'suggest' indicates analysis and recommendation output with no modification or deletion of code or repositories. No side effects mentioned.
Documented attack patterns abuse exactly the kind of access suggest_context_splits gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Code Analysis Server, and nothing reaches the server without passing your rules. This is the rule we recommend for suggest_context_splits:
{
"version": "1",
"default": "deny",
"tools": {
"suggest_context_splits": {}
}
}suggest_context_splits is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Suggest how to split large bounded contexts based on cohesion analysis. It is categorised as a Read tool in the MCP Code Analysis Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Code Analysis Server MCP server in PolicyLayer and add a rule for suggest_context_splits: 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 Code Analysis Server. Nothing to install.
suggest_context_splits 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 suggest_context_splits 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 suggest_context_splits. 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.
suggest_context_splits is provided by the MCP Code Analysis Server MCP server (johannhartmann/mcpcodeanalysis). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Code Analysis Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
44 MCP Code Analysis Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.