cursorrules

A set of Cursor editor rules for a Python agent built with LangGraph and MCP. They describe coding style, file organisation, agent structure, and deployment-related practices.

In plain words
What is it for?
Use them to guide naming, formatting, type hints, docstrings, file size, state management, authentication, authorisation, and separation between agent logic and MCP transport.
Why use it?
They give the coding agent project-specific conventions to follow, reducing inconsistent code and architectural decisions.

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/vishnu2kmohan/mcp-server-langgraph/cursorrules
Clone the repo
git clone --depth 1 https://github.com/vishnu2kmohan/mcp-server-langgraph

Made for: Cursor.

Per session 2,038 This file is loaded in full into every session.
When invoked 2,038 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 $0.02038 $0.02038
Opus 5 $0.01019 $0.01019
Sonnet 5 $0.00408 $0.00408
Haiku 4.5 $0.00204 $0.00204

Measured 2d ago against content hash fe8fa8d4d510, 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 · 358 lines

How it starts

The opening of the file, as written. The whole thing — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cursor AI Rules for LangGraph MCP Agent

Project Overview

This is a production-ready LangGraph agent with Model Context Protocol (MCP) implementation, featuring:

  • Multi-LLM support via LiteLLM (100+ providers)
  • Fine-grained authorization with OpenFGA
  • Secrets management with Infisical
  • OpenTelemetry observability
  • Kubernetes-ready deployment

Code Style Guidelines

Python

  • Line length: 127 characters (enforced by black)
  • Formatter: black with --line-length=127
  • Import sorting: isort with --profile=black
  • Type hints: Always use type hints for function signatures
  • Docstrings: Use Google-style docstrings
  • Naming conventions:
    • Classes: PascalCase
    • Functions/methods: snake_case
    • Constants: UPPER_SNAKE_CASE
    • Private methods: _leading_underscore

File Organization

  • Keep files focused and under 500 lines when possible
  • Group related functionality together
  • Use clear, descriptive file names

Architecture Patterns

Agent Design

  • Use LangGraph's functional API for stateless operations
  • Implement proper state management with checkpointing
  • Keep agent logic separate from transport layer (MCP)

Authentication & Authorization

  • Always validate JWT tokens before processing requests
  • Use OpenFGA for fine-grained authorization checks
  • Never hardcode credentials or secrets
  • Use Infisical or environment variables for secrets

Error Handling

  • Use specific exception types
  • Log errors with trace context
  • Return user-friendly error messages
  • Never expose internal stack traces to clients

Observability

  • Add OpenTelemetry spans for all major operations
  • Use structured logging with context
  • Track metrics for performance-critical paths
  • Include trace IDs in all logs

Testing Guidelines

Test Structure

  • Unit tests: Mark with @pytest.mark.unit
  • Integration tests: Mark with @pytest.mark.integration
  • E2E tests: Mark with @pytest.mark.e2e
  • Benchmarks: Mark with @pytest.mark.benchmark

Read the full file on GitHub · 358 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 · 358 lines · 2,038 tokens per session scan A fe8fa8d4d510

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository vishnu2kmohan/mcp-server-langgraph (4 stars, last pushed 9d ago), licensed MIT. It adds 2,038 tokens to every session, about $0.0102 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.