get_code_context
AI agents call get_code_context to retrieve information from Portable MCP Toolkit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the empty description, the naming convention and context within the sibling tools suggest this retrieves or queries code context without modifying data. The 'get_' prefix is a strong indicator of a read operation. Even in worst-case scenarios (retrieval of sensitive code), no data is modified, deleted, or executed, keeping this in the Read category with low severity.
From the tool's definition Tool name 'get_code_context' combined with sibling tools like 'read_file_full', 'search_code_semantic', 'get_context', and 'analyze_code_patterns' indicates this is a read-only operation that retrieves code context and information.
Attacks that exploit this kind of access
get_code_context. It is categorised as a Read tool in the Portable MCP Toolkit MCP Server, which means it retrieves data without modifying state.
Register the Portable MCP Toolkit MCP server in PolicyLayer and add a rule for get_code_context: 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 Portable MCP Toolkit. Nothing to install.
get_code_context 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 get_code_context 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 get_code_context. 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.
get_code_context is provided by the Portable MCP Toolkit MCP server (mjdevaccount/aistack-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 →