03-mcp-configuration

A project file that documents the Model Context Protocol servers configured for an environment. MCP is a standard way for an AI assistant to use connected tools such as file, memory, or web services.

In plain words
What is it for?
Use it to record MCP server names, purposes, commands, access scopes, authentication details, rate limits, and error-handling guidance from the project's mcp.json file.
Why use it?
It tells the assistant which external tools exist, what they are for, how to call them, and what access or authentication limits apply.

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/thesethrose/devrules/03-mcp-configuration
Clone the repo
git clone --depth 1 https://github.com/TheSethRose/DevRules

Made for: Cursor.

Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 359 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00031 $0.00359
Opus 5 $0.00015 $0.00179
Sonnet 5 $0.00006 $0.00072
Haiku 4.5 $0.00003 $0.00036

Measured yesterday against content hash a09443bb0e30, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

03-mcp-configuration 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 yesterday.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.cursor/rules/03-mcp-configuration.mdc · 52 lines

What it actually says

MCP Server Configuration

This file documents the Model Context Protocol (MCP) servers available in your environment. It helps the AI understand which tools it can use for tasks involving memory, filesystem operations, web interaction, etc.

How to Provide Your MCP Configuration

  1. Open Cursor Settings (Cmd+, or Ctrl+,)
  2. Go to the 'MCP' section
  3. Click 'Add new global MCP server' (opens mcp.json)
  4. With mcp.json open, return to chat and provide context using @

Available MCP Servers

Example Server Format

### MCP Server Name
Purpose: Provides file system access for reading/writing files
When to Use: For file operations (read, write, check existence)
Key Commands: `read_file`, `write_file`, `file_exists`, `list_directory`
Usage Instructions: Always use absolute file paths

Server Template

### MCP Server
Purpose: 
When to Use: 
Key Commands: 
Usage Instructions: 
Access Scope: 
Authentication: 
Rate Limits: 
Error Handling: 

Important Notes

  • Always use absolute paths for filesystem operations
  • Tool descriptions are derived from available tool descriptions in your configuration

NOTE TO AI:

  • Populate this file based on user's .cursor/mcp.json
  • For each server, list name and brief description of purpose/commands
  • Include relevant configuration details (paths, environment variables, etc.)
  • Remove example section when populating with actual MCP servers

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. yesterday First seen · 52 lines · 31 tokens per session scan A a09443bb0e30

Subscribe to this mod's changes

03-mcp-configuration is a cursor rule published in the GitHub repository TheSethRose/DevRules (25 stars, last pushed 1y ago), licensed MIT. It adds 31 tokens to every session and 359 once invoked, about $0.0002 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.