kagi-ken-mcp: Instructions file for Codex

AGENTS.md

kagi-ken-mcp AGENTS.md is an instructions file for Codex, OpenCode from czottmann/kagi-ken-mcp. It costs 696 tokens per session, scanned A, original, MIT.

Repository instructions for a server that connects coding assistants to Kagi, a search and web-content summarisation service. The server exposes search and summarisation as separate tools through the Model Context Protocol.

In plain words
What is it for?
Use it when changing the Kagi MCP server, running it locally, inspecting its tools, or testing its search and summarisation functions.
Why use it?
It explains how to develop, test, debug, and understand the structure of this particular repository.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is czottmann/kagi-ken-mcp's own configuration. It tells Codex and OpenCode how to work on kagi-ken-mcp 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 kagi-ken-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to czottmann/kagi-ken-mcp. 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/czottmann/kagi-ken-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/czottmann/kagi-ken-mcp

Made for: Codex, OpenCode.

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 kagi-ken-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/czottmann/kagi-ken-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/czottmann/kagi-ken-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/czottmann/kagi-ken-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/czottmann/kagi-ken-mcp/agents-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 kagi-ken-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/czottmann/kagi-ken-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/czottmann/kagi-ken-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 696 This file is loaded in full into every session.
When invoked 696 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 $0.00696 $0.00696
Opus 5.5 $0.00278 $0.00278
Sonnet 5.5 $0.00139 $0.00139
Haiku 4.5 $0.00070 $0.00070

Measured 2mo ago against content hash ccd5ea29ec78, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kagi-ken-mcp AGENTS.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.

AGENTS.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to LLM agents when working with code in this repository.

Common Commands

Development

npm install          # Install dependencies
npm start           # Run the MCP server
npm run dev         # Run with Node.js inspector for debugging

Testing & Debugging

npx @modelcontextprotocol/inspector node src/index.js    # Launch MCP Inspector at localhost:5173

Architecture Overview

This is a Model Context Protocol (MCP) server that provides Kagi search and summarization tools to Claude Desktop/Code. The server acts as a bridge between Claude and the kagi-ken package for accessing Kagi's APIs.

Core Architecture Pattern

MCP Server Structure: The main server (src/index.js) uses the @modelcontextprotocol/sdk to create an MCP server that registers tools and handles communication via stdio transport.

Tool-Based Architecture: Each capability is implemented as a separate MCP tool:

  • kagi_search_fetch - Multi-query concurrent search
  • kagi_summarizer - URL/content summarization

Token Resolution System: Authentication follows the same pattern as kagi-ken-cli with priority-based token resolution:

  1. KAGI_SESSION_TOKEN environment variable
  2. ~/.kagi_session_token file

Key Components

src/index.js - Main server class that:

  • Creates McpServer instance
  • Registers tools with Zod schemas for input validation
  • Sets up stdio transport and error handling

src/tools/ - Tool implementations:

  • Each tool exports both the handler function and config object
  • Handlers return MCP-compliant response format with content array
  • Input validation uses direct Zod schema objects (not z.object())

src/utils/auth.js - Token resolution that mirrors kagi-ken-cli:

  • resolveToken() - Priority-based token resolution
  • readTokenFromFile() - File-based token reading
  • Comprehensive error messages for missing tokens

src/utils/formatting.js - Result formatting:

  • formatSearchResults() - Matches official Kagi MCP output format
  • getEnvironmentConfig() - Unified config with token resolution

Read the full file on GitHub · 84 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 · 84 lines · 696 tokens per session scan A ccd5ea29ec78

Subscribe to this mod's changes

kagi-ken-mcp AGENTS.md is an instructions file published in the GitHub repository czottmann/kagi-ken-mcp (42 stars, last pushed 8mo ago), licensed MIT. It adds 696 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 2026-08-30.

Related

kagi-ken-mcp AGENTS.md compared with instructions from other repositories

kagi-ken-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
kagi-ken-mcp AGENTS.mdczottmann/kagi-ken-mcpInstructions file428mo agoMITA696Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode