atlas_analyze

Analyze code structure and dependencies across modules. Alias: code_atlas (deprecated)

Part of the Lex MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

// WHEN AI AGENTS USE THIS TOOL

AI agents call atlas_analyze to retrieve information from Lex 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 ATLAS_ANALYZE

Even though atlas_analyze 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.

lex.yaml

tools:
  atlas_analyze:
    rules:
      - action: allow

See the full Lex policy for all 14 tools.

// DETAILS

Tool Name atlas_analyze

Category Read

MCP Server Lex MCP Server

Risk Level Low

// MORE LEX TOOLS

Write frame_create Read contradictions_scan Read db_stats Read frame_get Read frame_list Read frame_search Read frame_validate Read help

View all 14 tools →

// RELATED READING

// FAQ

What does the atlas_analyze tool do? +

Analyze code structure and dependencies across modules. Alias: code_atlas (deprecated). It is categorised as a Read tool in the Lex MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on atlas_analyze? +

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

What risk level is atlas_analyze? +

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

Can I rate-limit atlas_analyze? +

Yes. Add a rate_limit block to the atlas_analyze 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 atlas_analyze completely? +

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

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

atlas_analyze

Enforce policies on Lex