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.
npx agentmods add rules/swonvip/mcp-server-talk/mcp-server-presentation-plangit clone --depth 1 https://github.com/SwonVIP/mcp-server-talkWrote 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/rules/swonvip/mcp-server-talk/mcp-server-presentation-plan)<a href="https://agentmods.dev/rules/swonvip/mcp-server-talk/mcp-server-presentation-plan"><img src="https://agentmods.dev/badge/rules/swonvip/mcp-server-talk/mcp-server-presentation-plan.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01122 |
| Opus 5 | $0.00000 | $0.00561 |
| Sonnet 5 | $0.00000 | $0.00224 |
| Haiku 4.5 | $0.00000 | $0.00112 |
Grade A, and why
mcp-server-presentation-plan 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 4d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Server Presentation Plan
Slide 1: Introduction
- Title: "Agentic Coding’s Secret Weapon"
- Subtitle: "A Guide and Demo of Model Context Protocol (MCP) Servers"
Slide 2: The Toolbox Analogy
- Just as craftspeople need tools to accomplish tasks:
- [IMAGE PLACEHOLDER: Title slide with toolbox visual]
- Screwdrivers for connecting/fastening
- Measuring tools for gathering information
- Power tools for complex operations
- LLMs need MCP servers to interact with the digital world
- MCP servers are specialized tools that extend LLM capabilities
- Each server solves specific problems (file access, API connections, etc.)
- [IMAGE PLACEHOLDER: Comparison between physical toolbox and digital toolbox for LLMs]
Slide 3: The Computer Interface Evolution
- Historical computer interface problems:
- Early days: Proprietary connectors for each component (GPUs, HDDs, printers)
- Each manufacturer had different standards
- Connecting N devices to M computers: M×N problem
- Evolution to standardized interfaces:
- IDE/SATA for storage
- USB for peripherals
- PCIe for expansion cards
- [IMAGE PLACEHOLDER: Timeline showing evolution of computer interfaces]
Slide 4: MCP as the "USB-C for AI Applications"
- Before MCP: Each AI integration required custom code
- M applications × N systems = M×N integrations
- After MCP: Standardized protocol transforms problem
- M applications + N systems = M+N implementations
- Just as USB-C standardized physical connections, MCP standardizes AI connections
- [IMAGE PLACEHOLDER: Diagram showing M×N problem vs M+N solution with MCP]
Slide 5: Core MCP Architecture
- Client-Server Architecture
- MCP Hosts: User-facing applications (Claude Desktop, IDEs like Cursor)
- MCP Clients: Components maintaining 1:1 connections with servers
- MCP Servers: Programs providing capabilities to AI models
- Transport Layer: stdio for local connections, HTTP/SSE for remote
- [IMAGE PLACEHOLDER: MCP architecture diagram showing components]
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.
- 4d ago First seen · 134 lines · 0 tokens per session scan A 367f665bcacb
mcp-server-presentation-plan is a cursor rule published in the GitHub repository SwonVIP/mcp-server-talk (0 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,122 tokens. 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.
Other cursor rules, from other repositories
logseq-youtube-notes
Logseq-Flavored Markdown (LFM) YouTube transcript headings.
006_Program_of_Thought_Tutorial
DSPY 3 Program of Thought Tutorial - Production code reasoning system from official DSPy 3.0.1 tutorial.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.