get_diagnostics

// WHEN AI AGENTS USE THIS TOOL

AI agents call get_diagnostics to retrieve information from Vscode without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

// WHY ENFORCE A POLICY ON GET_DIAGNOSTICS

Even though get_diagnostics only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

// RECOMMENDED POLICY

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

vscode.yaml

tools:
  get_diagnostics:
    rules:
      - action: allow

See the full Vscode policy for all 8 tools.

// DETAILS

Tool Name get_diagnostics

Category Read

MCP Server Vscode MCP Server

Risk Level Low

// MORE VSCODE TOOLS

Destructive execute_command Write open_files Write rename_symbol Read get_references Read get_symbol_lsp_info Read health_check Read list_workspaces

// WHAT CAN GO WRONG

Agents calling read-class tools like get_diagnostics have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

// OTHER READ TOOLS ACROSS MCP SERVERS

Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.

Firecrawl Web Scraping Server firecrawl_check_crawl_status Firecrawl Web Scraping Server firecrawl_crawl Firecrawl Web Scraping Server firecrawl_deep_research Firecrawl Web Scraping Server firecrawl_extract Firecrawl Web Scraping Server firecrawl_map Firecrawl Web Scraping Server firecrawl_scrape

// RELATED READING

// FAQ

What does the get_diagnostics tool do? +

Get diagnostic information from vscode language servers. Ideal quality-check tool for AI coding agents, much faster than 'tsc --noEmit' and 'eslint .' **Parameter Examples:** - Check modified files: workspace_path: '/path/to/open-vscode-workspace', __NOT_RECOMMEND__filePaths: [] (auto-detects git changes, including submodules) - Check submodule files explicitly: keep workspace_path at the open VSCode workspace root and pass file paths relative to that root, for example ['submodule/path/src/file.ts'] - Filter ESLint errors only: sources: ['eslint'], severities: ['error'] - Include editor hints: severities: ['error', 'warning', 'info', 'hint'] **Return Format:** Structured diagnostic results with severity levels, positions, and detailed error messages. Severity levels: 0=ERROR, 1=WARNING, 2=INFO, 3=HINT (matches VSCode DiagnosticSeverity enum) **Note:** - workspace_path selects the VSCode instance/socket, not the repository whose files you want to inspect. Use list_workspaces if unsure, and do not pass a child project or submodule path unless VSCode is opened there. - In most cases, pass __NOT_RECOMMEND__filePaths: [] to auto-detect git modified files. If the open workspace contains git submodules, modified files inside those submodules are included. - The severities parameter defaults to ["error", "warning", "info"]. "hint" is excluded by default because it usually represents editor suggestions (e.g., unused-var fade-out) rather than real issues. Pass it explicitly when you need hints. . It is categorised as a Read tool in the Vscode MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_diagnostics? +

Add a rule in your Intercept YAML policy under the tools section for get_diagnostics. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Vscode MCP server.

What risk level is get_diagnostics? +

get_diagnostics is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_diagnostics? +

Yes. Add a rate_limit block to the get_diagnostics rule in your Intercept 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 get_diagnostics completely? +

Set action: deny in the Intercept policy for get_diagnostics. 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 get_diagnostics? +

get_diagnostics is provided by the Vscode MCP server (@vscode-mcp/vscode-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Let agents act without letting them run wild.