notion-local-ops-mcp: Instructions file for Codex

AGENTS.md

notion-local-ops-mcp AGENTS.md is an instructions file for Codex, OpenCode from catoncat/notion-local-ops-mcp. It costs 1,228 tokens per session, scanned A, original, MIT.

A set of instructions for a local server that lets Notion AI agents work with files, search, shell commands, and delegated coding tasks on your computer.

In plain words
What is it for?
Use it when developing, configuring, or extending the notion-local-ops-mcp server, including its file tools, search, command execution, and task delegation.
Why use it?
It explains the server's purpose, structure, and available tools so an agent can use it consistently. It also documents how the Python service is arranged and configured.

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 catoncat/notion-local-ops-mcp's own configuration. It tells Codex and OpenCode how to work on notion-local-ops-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-local-ops-mcp configures →

Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/catoncat/notion-local-ops-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/catoncat/notion-local-ops-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,228 This file is loaded in full into every session.
When invoked 1,228 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 $0.01228 $0.01228
Opus 5 $0.00614 $0.00614
Sonnet 5 $0.00246 $0.00246
Haiku 4.5 $0.00123 $0.00123

Measured 9d ago against content hash 9bba2474d8d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

notion-local-ops-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 9d 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 · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — notion-local-ops-mcp

What is this?

A local MCP (Model Context Protocol) server that gives Notion AI agents the ability to operate on your local filesystem and shell. Built with Python 3.11+ and FastMCP, served over SSE on http://127.0.0.1:8766/mcp.

Architecture

Notion Agent ──SSE──▶ FastMCP Server (uvicorn)
                          │
          ┌───────────────┼───────────────┐
          ▼               ▼               ▼
    Direct Tools     Shell Tool     Delegate Tasks
   (files/search)   (run_command)  (codex/claude-code)

Source layout

src/notion_local_ops_mcp/
├── server.py      # FastMCP app, tool registration, uvicorn entrypoint / fd-aware child
├── config.py      # All env-var driven settings (host, port, paths, timeouts…)
├── pathing.py     # Path resolution: relative → absolute under WORKSPACE_ROOT
├── files.py       # list_files, read_text, write_file, internal replace helpers
├── search.py      # search implementations (glob/regex/text)
├── shell.py       # run_command — subprocess with timeout
├── tasks.py       # TaskStore — persistent task metadata & logs on disk
├── executors.py   # ExecutorRegistry — async delegate_task via codex / claude-code
└── supervisor.py  # Rolling-reload supervisor for dev-tunnel / local hot restarts

Tools exposed

Tool Purpose
server_info Inspect runtime config and available MCP tools
set_default_cwd / get_default_cwd Manage session default working directory
list_files List directory contents (flat or recursive)
search Canonical unified query tool (glob/regex/text); hides hidden and .gitignored paths by default and supports regex/text against a single file
read_text Canonical single/batch text reader with line pagination and optional line numbers
write_file Create or overwrite a file (dry_run supported)
apply_patch Default edit tool for existing files; rejects pure-context hunks, requires unique matches, and supports validation/dry-run
git_status / git_diff / git_commit / git_log / git_show / git_blame Structured git workflows (when cwd is actually inside a git repo)
run_command Execute a shell command (sync or background)
run_command_stream Start long shell command and poll via task id
delegate_task Submit long-running task to codex/claude-code with optional structured output parsing
get_task / wait_task Poll or block on delegated/background task completion
cancel_task Cancel a running delegated task
purge_tasks GC old task logs under STATE_DIR/tasks

Read the full file on GitHub · 91 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. 9d ago First seen · 91 lines · 1,228 tokens per session scan A 9bba2474d8d8

Subscribe to this mod's changes

notion-local-ops-mcp AGENTS.md is an instructions file published in the GitHub repository catoncat/notion-local-ops-mcp (109 stars, last pushed 1mo ago), licensed MIT. It adds 1,228 tokens to every session, about $0.0061 per session on Opus 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

Other instructions, from other repositories

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 · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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 · 6,785 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 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 · 4,469 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 · 3,735 tokens