code_parse · Agent Wiki MCP: Risk & Policy

WHAT IT DOES

What code_parse does on Agent Wiki

AI agents invoke code_parse to trigger actions in Agent Wiki. 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.

WHY IT NEEDS A POLICY

Why code_parse needs a policy

The tool runs a parsing/analysis operation on source files and persists output artifacts to disk. This is more than a read — it executes a transformation pipeline (AST generation, normalization, summarization) and writes resulting files to storage. It does not delete or overwrite existing data irreversibly, so it falls under Execute (triggers external processing with side effects of file creation).

From the tool's definition 'Parse a source file... into structured code knowledge (AST, normalized model, summary)... Persists artifacts under raw/parsed/cobol/'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

code_parse Rate-limited

code_parse stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "code_parse": {
      "limits": [
        {
          "counter": "code_parse_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Agent Wiki, so you can run agents against it safely.

FAQ

Questions about code_parse

What does the code_parse tool do? +

Parse a source file from raw/ into structured code knowledge (AST, normalized model, summary). Currently supports COBOL (.cbl, .cob, .cpy). Persists artifacts under raw/parsed/cobol/. Optionally traces all references to a variable. It is categorised as a Execute tool in the Agent Wiki MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on code_parse? +

Register the Agent Wiki MCP server in PolicyLayer and add a rule for code_parse: 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 Agent Wiki. Nothing to install.

What risk level is code_parse? +

code_parse is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit code_parse? +

Yes. Add a rate_limit block to the code_parse 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.

How do I block code_parse completely? +

Set action: deny in the PolicyLayer policy for code_parse. 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.

What MCP server provides code_parse? +

code_parse is provided by the Agent Wiki MCP server (xinhuagu/agent-wiki). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.