agentmods.dev

google-knowledge-graph-mcp: Instructions file for Codex

AGENTS.md

google-knowledge-graph-mcp AGENTS.md is an instructions file for Codex, OpenCode from houtini-ai/google-knowledge-graph-mcp. It costs 876 tokens per session, scanned A, original, MIT.

Repository instructions for AI coding agents working on an MCP server that searches Google's public Knowledge Graph API. MCP is a standard way for an AI assistant to call external tools.

In plain words
What is it for?
Use it when changing, building, checking, or manually testing this TypeScript MCP server.
Why use it?
It tells an agent how the project is organised, which commands to run, and which limits to respect, reducing incorrect changes and unsupported claims about testing.

Instructions file for CodexOpenCode

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

This is houtini-ai/google-knowledge-graph-mcp's own configuration. It tells Codex and OpenCode how to work on google-knowledge-graph-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 google-knowledge-graph-mcp configures →

not rated 12repo today A scan 876 tokens original MIT
View source ↗ houtini-ai/google-knowledge-graph-mcp houtini.com
Reuse

Borrowing it

Nothing to install: this file belongs to houtini-ai/google-knowledge-graph-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/houtini-ai/google-knowledge-graph-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/houtini-ai/google-knowledge-graph-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 google-knowledge-graph-mcp AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/houtini-ai/google-knowledge-graph-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/houtini-ai/google-knowledge-graph-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 876 This file is loaded in full into every session.
When invoked 876 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 $0.00876 $0.00876
Opus 5.5 $0.00350 $0.00350
Sonnet 5.5 $0.00175 $0.00175
Haiku 4.5 $0.00088 $0.00088

Measured 22d ago against content hash 9ad02a7b5cb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

google-knowledge-graph-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 22d 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 · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Instructions for AI coding agents (OpenCode, Codex, Cursor, Claude Code and others) working in this repo. Human-facing docs live in README.md and CONTRIBUTING.md.

What this is

An MCP server (stdio) for Google's free public Knowledge Graph Search API. Two tools: search_knowledge_graph (query search) and lookup_knowledge_graph_entities (lookup by MID). Published to npm as @houtini/google-knowledge-graph-mcp and to the MCP Registry as io.github.houtini-ai/google-knowledge-graph.

Scope: the free public API only, never the Enterprise API. Keep it small: two runtime dependencies, no new ones without a reason.

Commands

  • Install: npm install
  • Build: npm run build (tsc to dist/)
  • Type-check only: npm run type-check
  • Run: node dist/index.js (needs GOOGLE_KNOWLEDGE_GRAPH_API_KEY in the environment)

There is no automated test suite yet. Do not claim tests pass. Verify a change with npm run type-check, then npm run build, then a real call through an MCP client (see "Trying a change" below).

Layout

  • src/index.ts - MCP server: tool definitions (JSON schema) and the request handlers that shape the output.
  • src/client.ts - Knowledge Graph HTTP client, API-key check, and explainApiError (turns Google's error JSON into an actionable message).
  • src/version.ts - reads the version from package.json at runtime. Never hardcode a version string in source.
  • server.json - MCP Registry manifest.

Rules that bite

  • stdout is the protocol. It carries MCP JSON-RPC. Never console.log; diagnostics go to stderr (console.error, process.stderr.write).
  • CommonJS output. tsconfig.json compiles to module: commonjs; version.ts relies on __dirname. Keep relative imports with the .js suffix (./client.js), as the existing code does.
  • The API key travels in the URL query (Google's requirement). Never log a request URL, a key, or the environment. Error messages may include Google's response body, never the URL.
  • Key kinds: a Google Cloud key (AIza..., 39 chars) works; a Google AI Studio key (AQ.) never does. Keep explainApiError and the boot-time warning in step with that.
  • Env vars: GOOGLE_KNOWLEDGE_GRAPH_API_KEY, or GOOGLE_CLOUD_API_KEY as the fallback. Never read or write .env; .env.example is the documented shape.
  • Tool contract: tool names and input schemas are public API for every client that has this server installed. Renaming or removing a field is a breaking change: call it out, don't slip it in.

Read the full file on GitHub · 51 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. 22d ago First seen · 51 lines · 876 tokens per session scan A 9ad02a7b5cb0

Subscribe to this mod's changes

google-knowledge-graph-mcp AGENTS.md is an instructions file published in the GitHub repository houtini-ai/google-knowledge-graph-mcp (12 stars, last pushed today), licensed MIT. It adds 876 tokens to every session, about $0.0035 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 2026-10-03.

Building agentsapi-cliententitiesentity-recognitionknowledge-graphmcpmodel-context-protocol
Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,581 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens