cursorrules

Project rules for a FastMCP server and web app that connect Claude Desktop and Cursor with OpenClaw and Moltbook. OpenClaw provides an AI-agent gateway and related services; Moltbook is a social network for AI agents.

In plain words
What is it for?
Developing or running the Python server, React web app, desktop package, and integrations with OpenClaw and Moltbook.
Why use it?
It clarifies which platforms the project connects to, how its tools and services are organized, and which ports and commands developers should use.

Cursor rule for Cursor

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/sandraschi/openclaw-molt-mcp/cursorrules
Clone the repo
git clone --depth 1 https://github.com/sandraschi/openclaw-molt-mcp

Made for: Cursor.

Per session 682 This file is loaded in full into every session.
When invoked 682 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00682 $0.00682
Opus 5 $0.00341 $0.00341
Sonnet 5 $0.00136 $0.00136
Haiku 4.5 $0.00068 $0.00068

Measured 2d ago against content hash 8d1c20f0e947, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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 2d 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.

.cursorrules · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

openclaw-molt-mcp — Agent Instructions

Repo-local rules. Fleet-wide standards live in D:\Dev\repos\mcp-central-docs\standards\.

What this repo is

FastMCP server + webapp that bridges Claude Desktop / Cursor to OpenClaw (agent Gateway, channels, routing, sessions, skills, security) and Moltbook (AI-agent social network). It uses those platforms; it does not implement or replace them.

Architecture

  • MCP toolssrc/openclaw_molt_mcp/tools/ (11 portmanteau tools: clawd_agent, clawd_bastion, clawd_channels, clawd_gateway, clawd_moltbook, clawd_openclaw_disconnect, clawd_routing, clawd_security, clawd_sessions, clawd_skills, clawd_voice). Each tool has one @mcp.tool() entrypoint with an operation enum param.
  • Webapp APIwebapp_api/main.py (FastAPI, port 10745), serves the React SPA.
  • Webapp UIwebapp/ (React + Vite + TS, port 10744).
  • Desktopnative/ (Tauri 2 + PyInstaller sidecar → NSIS installer).

Ports

Port Service
10744 Vite frontend
10745 FastAPI backend + static SPA
18789 OpenClaw Gateway (external daemon port)

Conventions

  • Run Python with uv run --directory <repo> --extra dev — never naked python.
  • Run JS with bun (bun.lock is the lockfile). Never npm.
  • Lint: uv run ruff check . + uv run ruff format --check .. Format with uv run ruff format.
  • Type check: uv run pyright src. Tests: uv run pytest.
  • Webapp: bun run lint, bun run type-check, bun run build (in webapp/).
  • Do NOT hardcode secrets or ports in source. Config lives in .env (gitignored); document keys in .env.example.
  • Do NOT commit node_modules/, .venv/, .bak*, _llm_test_scripts/, dist/, target/.

Key files

  • src/openclaw_molt_mcp/config.py — pydantic-settings, OPENCLAW_ prefix.
  • src/openclaw_molt_mcp/gateway_client.py — OpenClaw Gateway HTTP client.
  • src/openclaw_molt_mcp/moltbook_client.py — Moltbook API client.
  • fleet-start.config.ps1 — ports + backend target for start.ps1.

Read the full file on GitHub · 53 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. 2d ago First seen · 53 lines · 682 tokens per session scan A 8d1c20f0e947

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository sandraschi/openclaw-molt-mcp (3 stars, last pushed 13d ago), licensed MIT. It adds 682 tokens to every session, about $0.0034 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 2026-08-31.