.cursorrules

Project instructions for an MCP server that connects AI clients such as Claude Desktop or Cursor to HeyReach, a LinkedIn outreach platform.

In plain words
What is it for?
Use them when developing or maintaining features for HeyReach campaigns, leads, and LinkedIn outreach automation.
Why use it?
They give the project consistent rules for implementing tools, validating requests, and handling its protocol behavior.

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/bcharleson/heyreach-mcp/cursorrules
Clone the repo
git clone --depth 1 https://github.com/bcharleson/heyreach-mcp

Made for: Cursor.

Per session 2,299 This file is loaded in full into every session.
When invoked 2,299 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.02299 $0.02299
Opus 5 $0.01149 $0.01149
Sonnet 5 $0.00460 $0.00460
Haiku 4.5 $0.00230 $0.00230

Measured 2d ago against content hash 407ddf99010b, 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 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

this.client = axios.create({
.cursor/.rules/.cursorrules.mdc · 354 lines

How it starts

The opening of the file, as written. The whole thing — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HeyReach MCP Server - Cursor Rules

Project Overview

This is a production-ready Model Context Protocol (MCP) server for HeyReach LinkedIn automation platform. It enables Claude Desktop and other MCP clients to manage campaigns, add leads, and automate LinkedIn outreach with comprehensive validation and error handling.

MCP Protocol Compliance

Current Protocol Version

  • Protocol Version: 2025-03-26 (current)
  • Revision: Current (ready for use)
  • SDK: @modelcontextprotocol/sdk (TypeScript)

Supported MCP Features

  • Tools: Full implementation with 12 production-ready tools
  • Resources: Not implemented (not needed for this use case)
  • Prompts: Not implemented (not needed for this use case)
  • Sampling: Not implemented
  • Logging: Should be implemented for production debugging
  • Pagination: Should be implemented for large result sets

MCP Client Compatibility

Primary targets (verified working):

  • Claude Desktop App: Full support (tools, prompts, resources)
  • Cursor: Tools support
  • Windsurf Editor: Tools support with AI Flow
  • Continue: Tools, prompts, and resources support

Code Style & Architecture

TypeScript Standards

  • Use strict TypeScript with proper type definitions
  • Prefer explicit types over any
  • Use Zod for runtime validation and schema definition
  • Follow functional programming patterns where appropriate
  • Use async/await for all asynchronous operations

MCP Server Architecture

// Proper MCP server structure
export class HeyReachMcpServer {
  private server: McpServer;
  private heyReachClient: HeyReachClient;
  
  constructor(config: HeyReachConfig) {
    this.server = new McpServer({
      name: 'heyreach-mcp-server',
      version: '1.1.7'
    });
    this.heyReachClient = new HeyReachClient(config);
    this.setupTools();
  }
}

Tool Definition Best Practices

// Correct tool definition pattern
this.server.tool(
  'tool-name',
  {
    // Zod schema - NO description field here
    param1: z.string().describe('Parameter description'),
    param2: z.number().optional().default(0).describe('Optional parameter')
  },
  async ({ param1, param2 }) => {
    try {
      // Implementation
      return createSuccessResponse(data, message);
    } catch (error) {
      return createErrorResponse(error.message);
    }
  }
);

Read the full file on GitHub · 354 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 · 354 lines · 2,299 tokens per session scan A 407ddf99010b

Subscribe to this mod's changes

.cursorrules is a cursor rule published in the GitHub repository bcharleson/heyreach-mcp (5 stars, last pushed 11mo ago), licensed MIT. It adds 2,299 tokens to every session, about $0.0115 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.