mcp-docs

Instructions for using current MCP protocol and TypeScript SDK version 2 documentation. MCP is a standard for connecting AI systems to tools and data.

In plain words
What is it for?
Tasks involving MCP protocol behavior or TypeScript SDK version 2 APIs.
Why use it?
It helps prevent relying on outdated documentation or APIs from an earlier SDK version.

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/neschadin/askell-mcp/mcp-docs
Clone the repo
git clone --depth 1 https://github.com/Neschadin/askell-mcp

Made for: Cursor.

Per session 216 This file is loaded in full into every session.
When invoked 216 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 $0.00216 $0.00216
Opus 5 $0.00108 $0.00108
Sonnet 5 $0.00043 $0.00043
Haiku 4.5 $0.00022 $0.00022

Measured yesterday against content hash 2df12da88aa5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-docs 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.

.cursor/rules/mcp-docs.mdc · 16 lines

What it actually says

Live MCP docs

This repo is @modelcontextprotocol/server v2 (Bun + stdio). Training data will hallucinate v1 @modelcontextprotocol/sdk.

When the task touches protocol or SDK APIs, load the mcp-docs skill and read live docs:

  1. Protocol / Inspector / spec — MCP server mcp-protocol-docs (search_model_context_protocol). Index: https://modelcontextprotocol.io/llms.txt (prefer 2026-07-28).
  2. TypeScript SDK v2https://ts.sdk.modelcontextprotocol.io/v2/llms.txt then the page's .md URL. Or Context7 library /websites/ts_sdk_modelcontextprotocol_io_v2.

Do not scaffold a new MCP project. Do not copy v1 APIs (.tool(), McpError, extra, SSE).

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 · 16 lines · 216 tokens per session scan A 2df12da88aa5

Subscribe to this mod's changes

mcp-docs is a cursor rule published in the GitHub repository Neschadin/askell-mcp (0 stars, last pushed 4d ago), licensed MIT. It adds 216 tokens to every session, about $0.0011 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.