kula-mcp-server: Instructions file for Claude Code

CLAUDE.md

kula-mcp-server CLAUDE.md is an instructions file for Claude Code from kula-ai/kula-mcp-server. It costs 706 tokens per session, scanned A, original, MIT.

Project instructions for Kula’s MCP server, which connects coding agents to Kula’s recruiting API. An API is a controlled interface that lets software request data or actions from another service.

In plain words
What is it for?
Use them when building, testing, or extending recruiting-related tools, API requests, input validation, or the server’s TypeScript code.
Why use it?
They document the project’s commands, structure, validation rules, and tool-registration pattern so changes can be made consistently and safely.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is kula-ai/kula-mcp-server's own configuration. It tells Claude Code how to work on kula-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything kula-mcp-server configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import { KulaClient } from "../client.js";.

Reuse

Borrowing it

Nothing to install: this file belongs to kula-ai/kula-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kula-ai/kula-mcp-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/kula-ai/kula-mcp-server

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for kula-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kula-ai/kula-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/kula-ai/kula-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kula-ai/kula-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/kula-ai/kula-mcp-server/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for kula-mcp-server CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kula-ai/kula-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/kula-ai/kula-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 706 This file is loaded in full into every session.
When invoked 706 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00706 $0.00706
Opus 5.5 $0.00282 $0.00282
Sonnet 5.5 $0.00141 $0.00141
Haiku 4.5 $0.00071 $0.00071

Measured 2mo ago against content hash 9ad3ed6f5585, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kula-mcp-server CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kula MCP Server

MCP server wrapping the Kula recruiting API (https://api.kula.ai/v1).

Quick Reference

  • Language: TypeScript (ESM, strict mode)
  • Runtime: Node 22 LTS (see .nvmrc)
  • MCP SDK: @modelcontextprotocol/sdk with STDIO transport
  • Validation: Zod schemas for all tool inputs

Commands

  • nvm use — switch to project Node version
  • npm run build — compile TypeScript to build/
  • npm run dev — watch mode compilation
  • npm start — run the compiled server
  • npm test — run tests (vitest)
  • npx @modelcontextprotocol/inspector — test tools interactively

Architecture

src/index.ts        → Entry point. Creates McpServer, registers tools, starts StdioServerTransport.
src/client.ts       → KulaClient class. Thin fetch() wrapper with auth headers and error handling.
src/tools/*.ts      → Each file exports register(server, client). One file per API domain.
src/types.ts        → Shared Zod schemas reused across tool modules.

Tool Registration Pattern

Every tool file follows this pattern:

import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { z } from "zod";
import { KulaClient } from "../client.js";

export function register(server: McpServer, client: KulaClient) {
  server.tool("tool_name", "Description for LLM", { param: z.string() }, async ({ param }) => {
    const data = await client.get(`/v1/endpoint/${param}`);
    return { content: [{ type: "text", text: JSON.stringify(data, null, 2) }] };
  });
}

Key Conventions

  • NEVER use console.log — STDIO transport uses stdout for JSON-RPC. Use console.error for logging.
  • Tool names use snake_case (MCP convention).
  • All tool handlers return { content: [{ type: "text", text: string }] }.
  • API errors are caught and returned as { content: [...], isError: true }.
  • Auth via KULA_API_KEY env var — validated at startup.
  • Import paths must include .js extension (ESM requirement).

API Domains → Tool Files (28 tools)

Read the full file on GitHub · 67 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 67 lines · 706 tokens per session scan A 9ad3ed6f5585

Subscribe to this mod's changes

kula-mcp-server CLAUDE.md is an instructions file published in the GitHub repository kula-ai/kula-mcp-server (0 stars, last pushed 2mo ago), licensed MIT. It adds 706 tokens to every session, about $0.0028 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

kula-mcp-server CLAUDE.md compared with instructions from other repositories

kula-mcp-server CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
kula-mcp-server CLAUDE.mdkula-ai/kula-mcp-serverInstructions file02mo agoMITA706Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283ktodayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot