mcp-guide

A reference guide for choosing tools that connect an agent to documentation, websites, browsers, databases, and structured problem-solving. It covers Context7, Firecrawl, Playwright, Supabase, and Sequential Thinking.

In plain words
What is it for?
Use it when researching libraries, scraping technical sources, automating browser tests, inspecting Supabase data, or reasoning through complex bugs and refactors.
Why use it?
Developers may waste time choosing the wrong tool or using outdated library information. The guide maps common development and debugging tasks to the relevant tool.

Command

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 commands/kensaurus/cursor-kenji/mcp-guide
Clone the repo
git clone --depth 1 https://github.com/kensaurus/cursor-kenji
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 309 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 $0.00028 $0.00309
Opus 5 $0.00014 $0.00154
Sonnet 5 $0.00006 $0.00062
Haiku 4.5 $0.00003 $0.00031

Measured 3d ago against content hash 6545b2af3d30, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-guide 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 3d 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.

commands/mcp-guide.md · 40 lines

What it actually says

MCP-Powered Development

Named /mcp-guide (not /mcp) to avoid colliding with Claude Code's built-in /mcp command (the MCP server manager). This is a reference for which MCP toolset to reach for and when.

Tools

Context7 - Live Documentation

Fetches current, version-specific docs. Use before implementing unfamiliar libraries or when unsure about API syntax.

Firecrawl - Web Scraping

Scrapes documentation, Stack Overflow, tutorials, and GitHub repos. Use for deep research and gathering implementation patterns.

Playwright - Browser Automation

E2E testing, screenshots, form automation. Use for testing UI flows and visual regression.

Supabase - Backend Management

Direct database queries, auth management, storage, migrations. Use for data inspection and schema changes.

Sequential Thinking - Problem Solving

Step-by-step reasoning for complex bugs, architecture decisions, and multi-file refactors.


Workflow

New Feature:

  1. Context7 → Verify library docs
  2. Firecrawl → Research patterns
  3. Sequential Thinking → Plan approach
  4. Supabase → Prepare schema
  5. Playwright → Write tests

Debugging:

  1. Sequential Thinking → Analyze problem
  2. Firecrawl → Search similar issues
  3. Supabase → Inspect data state
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. 3d ago First seen · 40 lines · 28 tokens per session scan A 6545b2af3d30

Subscribe to this mod's changes

mcp-guide is a command published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 5d ago), licensed MIT. It adds 28 tokens to every session and 309 once invoked, about $0.0001 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.