Does Code Explainer MCP use an LLM?
No. All analysis is done with regex and pattern matching inside the Worker, with no LLM calls and no external runtime dependencies.
@BillDuke13
Basic information
A Cloudflare Worker that serves as an MCP (Model Context Protocol) server for code explanation. It analyzes and explains code with a comprehensive breakdown of structure and functionality.
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Code Explainer MCP is a Cloudflare Worker that analyzes source code snippets and returns a Markdown report containing an ASCII architecture diagram, a core-functionality summary, and a breakdown of main classes and functions. It uses only regex and pattern matching—no LLM calls or external dependencies—and supports JavaScript, TypeScript, Python, Java, and C# with a generic fallback.
Deploy the Worker to Cloudflare, set the SHARED_SECRET secret, then send a POST request to the Worker URL with a JSON body containing "method": "explainCode" and "params": [code, language]. Include the bearer token in the Authorization: Bearer <SHARED_SECRET> header. For local development, run npm run dev after setting the secret in .dev.vars.
No. All analysis is done with regex and pattern matching inside the Worker, with no LLM calls and no external runtime dependencies.
The code string (`params[0]`) must not exceed 100,000 characters; longer input is rejected with a `413` status.
No. Despite its name, the current version serves a plain HTTP JSON endpoint with a custom `{ method, params }` body. It does not use `workers-mcp` at runtime or implement JSON-RPC.
The POST endpoint is protected by a bearer token (`SHARED_SECRET`) sent in the `Authorization` header. The Worker fails closed—returning `503` if the secret is unset or still the placeholder—and compares digests in constant time.
Node.js 22 or higher, Wrangler (included in devDependencies), and a Cloudflare account. The Worker is deployed to Cloudflare Workers and tested with Vitest and `@cloudflare/vitest-pool-workers`.

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.

Form backend for static sites. Create form endpoints, get paste-ready markup for HTML, React, Vue, Svelte and Astro, and read submission stats — straight from your agent. Submissions are spam-filtered, stored, and routed
Comments