extract_code_blocks

What extract_code_blocks does on MCP Framework Personal

AI agents call extract_code_blocks to retrieve information from MCP Framework Personal without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why extract_code_blocks is rated Low

This tool appears to extract or retrieve code blocks from a document or file—a read-only operation with no side effects. It does not execute code, modify data, or delete anything. The low severity reflects that misuse (e.g., extracting code maliciously) does not directly cause harm; the tool simply surfaces existing content. Confidence is slightly reduced due to the absent description, but the context is clear.

From the tool's definition Tool name 'extract_code_blocks' indicates retrieval/parsing of code from documents. The sibling tools on this server are all non-destructive read operations (extract_headings, extract_links, get_file_summary, filter_rows, etc.).

The rule that runs extract_code_blocks safely

PolicyLayer is an MCP gateway: it sits between your AI agents and MCP Framework Personal, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For extract_code_blocks, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "extract_code_blocks": {}
  }
}

Questions about extract_code_blocks