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.
curl -O https://raw.githubusercontent.com/catoncat/notion-local-ops-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/catoncat/notion-local-ops-mcpWrote 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.
[](https://agentmods.dev/instructions/catoncat/notion-local-ops-mcp/agents-md)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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 |
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.
- 9d ago First seen · 91 lines · 1,228 tokens per session scan A 9bba2474d8d8
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.
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.
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.
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).
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).
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.
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.