识别代码中的Bug、逻辑错误或潜在问题，提供详细的问题分析和修复建议。支持调试运行时错误和逻辑错误。
AI agents call code_debug to retrieve information from Unified MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool analyzes code to identify bugs and suggest fixes — it reads/inspects code and produces a report. It does not execute code, modify files, or cause side effects. It is a diagnostic/read tool similar to code_review or code_explain siblings on the server.
From the tool's definition 识别代码中的Bug、逻辑错误或潜在问题，提供详细的问题分析和修复建议 (Identifies bugs, logic errors or potential issues, provides detailed problem analysis and fix suggestions)
Attacks that exploit this kind of access
识别代码中的Bug、逻辑错误或潜在问题，提供详细的问题分析和修复建议。支持调试运行时错误和逻辑错误。. It is categorised as a Read tool in the Unified MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Unified MCP Server MCP server in PolicyLayer and add a rule for code_debug: 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 Unified MCP Server. Nothing to install.
code_debug 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 code_debug 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 code_debug. 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.
code_debug is provided by the Unified MCP Server MCP server (qingyunyupan/ollama-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 →