CodeXRay

16 tools. 0 can modify or destroy data without limits.

Read-only server. Low risk, but rate limits prevent runaway API costs.

Last updated:

0 can modify or destroy data
16 read-only
16 tools total

Community server · catalogue entry verified 12/06/2026

How to control CodeXRay ↓

What CodeXRay exposes to your agents

Read (16) Write / Execute (0) Destructive / Financial (0)

What can go wrong

Even read-only tools carry cost. An agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up bills.

How to control CodeXRay

PolicyLayer is an MCP gateway — it sits between your AI agents and CodeXRay, and nothing reaches the server without passing your rules. These are the rules we recommend:

Cap read operations
{
  "codexray_context": {
    "limits": [
      {
        "counter": "codexray_context_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register CodeXRay — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON CODEXRAY →

Free to start. No card required.

All 16 CodeXRay tools

READ 16 tools
Read codexray_context Build comprehensive task-relevant context for a coding task. Analyzes your query, finds relevant symbols, incl Read codexray_callees Find all functions/methods that the specified symbol CALLS. Use to understand what a function depends on. Read codexray_callers Find all functions/methods that CALL the specified symbol. Essential for understanding usage patterns and impa Read codexray_circular Detect circular dependencies in the codebase. Finds import/call cycles that can cause issues. Use for refactor Read codexray_complexity Find the most complex functions/methods in the codebase by cyclomatic complexity score. High complexity = hard Read codexray_deadcode Find potentially unused/dead code — symbols that are never called or referenced by other symbols. Useful for c Read codexray_deps Get the full dependency tree of a symbol — everything it imports, extends, implements, or uses. Use to underst Read codexray_files Get the indexed file tree with symbol counts per file. Use to understand project structure and find where code Read codexray_hotspots Find the most connected/critical symbols in the codebase — those with the highest number of callers and depend Read codexray_impact Analyze the blast radius of changing a symbol. Traces all callers/dependents recursively to show everything th Read codexray_node Get detailed info about a specific symbol including its full source code, signature, docstring, complexity, an Read codexray_overview Get a high-level project overview including file count, languages, symbol distribution, key hotspot symbols, a Read codexray_path Find the shortest connection path between two symbols in the dependency graph. Useful for understanding how tw Read codexray_search Search for code symbols (functions, classes, methods, types, etc.) by name or keyword. Returns matching symbol Read codexray_semantic Find code by MEANING, not just name. Search Read codexray_status Check the health and statistics of the CodeXRay index — total symbols, edges, files, languages, and index fres

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

Questions about CodeXRay

Is the CodeXRay MCP server safe to use without restrictions? +

The CodeXRay server is primarily read-only with 16 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the CodeXRay MCP server expose? +

16 tools across 2 categories: Execute, Read. 16 are read-only. 0 can modify, create, or delete data.

How do I enforce a policy on CodeXRay? +

Register the CodeXRay MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every CodeXRay tool call.

Deterministic rules across all 16 CodeXRay tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

16 CodeXRay tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.