notion-mcp: Instructions file for Codex

AGENTS.md

notion-mcp AGENTS.md is an instructions file for Codex, OpenCode from Glebsky/notion-mcp. It costs 3,682 tokens per session, scanned A, original, MIT.

A set of agent instructions for a Notion terminal MCP server, which lets AI agents communicate with a server that provides file-system access. MCP is a standard connection method for AI tools.

In plain words
What is it for?
It is for guiding agents that use the server over HTTP to read or change files safely and interpret its audit logs and access settings.
Why use it?
It explains how the server works, how it authenticates requests, and what limits and sandbox rules agents must follow.

Instructions file for CodexOpenCode

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

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

Reuse

Borrowing it

Nothing to install: this file belongs to Glebsky/notion-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/Glebsky/notion-mcp/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Glebsky/notion-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 notion-mcp AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/glebsky/notion-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/glebsky/notion-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,682 This file is loaded in full into every session.
When invoked 3,682 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 $0.03682 $0.03682
Opus 5.5 $0.01473 $0.01473
Sonnet 5.5 $0.00736 $0.00736
Haiku 4.5 $0.00368 $0.00368

Measured 1mo ago against content hash 030fa5439625, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

notion-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 1mo 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 · 390 lines

How it starts

The opening of the file, as written. The whole thing — 390 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Specification: Notion Terminal MCP

Technical specification and operational guide for AI Agents (Notion Custom Agents, Claude, Cursor, Antigravity, and autonomous LLM agents) interacting with this MCP server.


1. System Overview

  • Server Identifier: notion-terminal-files
  • Protocol: Model Context Protocol (MCP)
  • Transports: Streamable HTTP (/mcp) & Standard SSE (/sse + /messages)
  • Health Check: GET /health
  • Server Info: GET /
  • Authentication: HTTP Authorization header (Authorization: Bearer <API_KEY>) or x-api-key: <API_KEY>
┌────────────────────────────────────────┐
│        AI Agent (e.g. Notion)          │
└───────────────────┬────────────────────┘
                    │  Streamable HTTP (JSON-RPC / MCP)
                    ▼
┌────────────────────────────────────────┐
│     Ngrok / Cloudflare Public Tunnel   │
└───────────────────┬────────────────────┘
                    │
┌───────────────────▼────────────────────┐
│      Notion Terminal MCP Server        │
│  - Timing-Safe Authentication          │
│  - Host Header Validation              │
│  - Sandboxed / Full Access FS          │
│  - UTF-8 Windows Console Integration   │
│  - Structured Audit Logging            │
└────────────────────────────────────────┘

2. Security & Execution Model

2.1 Sandboxing (FULL_ACCESS)

  • When FULL_ACCESS=false (Default Sandbox):
    • All file and directory paths are strictly jailed within FILES_ROOT (e.g., ./workspace or custom configured path).
    • Path traversal attempts (../, symlink escapes, absolute paths pointing outside FILES_ROOT) are immediately rejected with an error.
    • Working directories (cwd) for terminal_execute default to FILES_ROOT.
  • When FULL_ACCESS=true (Unrestricted Mode):
    • The agent has full access to the host filesystem with permissions of the host user running the server.

2.2 Limits and Buffers

  • MAX_OUTPUT_BYTES (default: 1 MB): Terminal output exceeding this limit is capped with truncated: true.
  • MAX_FILE_BYTES (default: 10 MB): File read/write operations exceeding this limit require offset pagination or are rejected.
  • COMMAND_TIMEOUT_MS (default: 120,000 ms, max: 900,000 ms): Long running processes are automatically killed with their full process tree.

Read the full file on GitHub · 390 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. 1mo ago Changed · +1 lines · +23 tokens per session 030fa5439625
  2. 2mo ago Changed · +144 lines · +1,423 tokens per session d8ffc8425917
  3. 2mo ago First seen · 245 lines · 2,236 tokens per session scan A 179618b256b1

Subscribe to this mod's changes

notion-mcp AGENTS.md is an instructions file published in the GitHub repository Glebsky/notion-mcp (0 stars, last pushed 17d ago), licensed MIT. It adds 3,682 tokens to every session, about $0.0147 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

notion-mcp AGENTS.md compared with instructions from other repositories

notion-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
notion-mcp AGENTS.mdGlebsky/notion-mcpInstructions file017d agoMITA3,682Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, 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