mcp-docs

mcp-docs is a skill for Claude Code, Codex, Cursor from Neschadin/askell-mcp. It costs 113 tokens per session (958 once invoked), scanned A, original, MIT.

A documentation helper for the Model Context Protocol and its TypeScript SDK version 2. MCP is a protocol for connecting AI agents to tools, resources, and other server features.

In plain words
What is it for?
Use it to look up current MCP features and TypeScript SDK patterns, including tools, resources, prompts, transports, authorization, and capability negotiation.
Why use it?
MCP documentation changes over time, so it directs work to the current specification and SDK documentation instead of relying on outdated knowledge.

Skill for Claude CodeCodexCursor

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 skills/neschadin/askell-mcp/mcp-docs
Any agent
npx skills add Neschadin/askell-mcp --skill mcp-docs
Clone the repo
git clone --depth 1 https://github.com/Neschadin/askell-mcp

Made for: Claude Code, Codex, Cursor.

Wrote 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.

agentmods badge for mcp-docs

README.md
[![agentmods](https://agentmods.dev/badge/skills/neschadin/askell-mcp/mcp-docs.svg)](https://agentmods.dev/skills/neschadin/askell-mcp/mcp-docs)
Your own site
<a href="https://agentmods.dev/skills/neschadin/askell-mcp/mcp-docs"><img src="https://agentmods.dev/badge/skills/neschadin/askell-mcp/mcp-docs.svg" alt="Measured on agentmods" height="20"></a>
Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 958 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 5.1 $0.00113 $0.00958
Opus 5 $0.00056 $0.00479
Sonnet 5 $0.00023 $0.00192
Haiku 4.5 $0.00011 $0.00096

Measured yesterday against content hash 21185f090ff2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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/skills/mcp-docs/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP live docs (protocol + TS SDK v2)

Spec and SDK move faster than training data. Live docs beat memory. This project is already an MCP v2 stdio server (@modelcontextprotocol/server, serveStdio, registerTool). Do not scaffold a new server (that is typescript-mcp-server-generator). Do not re-design the tool catalog (that is mcp-tool-design).

Sources

What Index How to read
Protocol, Inspector, security https://modelcontextprotocol.io/llms.txt MCP tools first, then fetch page .md URLs
TypeScript SDK v2 (2026-07-28) https://ts.sdk.modelcontextprotocol.io/v2/llms.txt Fetch index, then the page's .md URL

Every SDK page is also plain markdown at the same path with .md (e.g. tools). Full dump: https://ts.sdk.modelcontextprotocol.io/v2/llms-full.txt — only if you need many pages at once.

Prefer 2026-07-28 (and docs/2026-07-28/…). Ignore older spec eras in the protocol llms.txt unless the user names one.

Fetch strategy

Protocol — MCP tools first

If search_model_context_protocol is connected:

  1. search_model_context_protocol({ query })
  2. Read the page with query_docs_filesystem_model_context_protocol (head/cat the .mdx path). Do not treat that tool as a real shell.

Fallback if those tools are missing:

  1. Fetch https://modelcontextprotocol.io/llms.txt
  2. Pick the 2026-07-28 (or specification/2026-07-28) URL
  3. Fetch that .md URL

TypeScript SDK v2

  1. If Context7 is available: resolve-library-id then query-docs with library /websites/ts_sdk_modelcontextprotocol_io_v2 (or /modelcontextprotocol/typescript-sdk).
  2. Else fetch https://ts.sdk.modelcontextprotocol.io/v2/llms.txt, pick the page, fetch its .md URL.

Quick map (SDK v2):

  • Tools / registerToolservers/tools.md
  • Resources → servers/resources.md
  • Prompts → servers/prompts.md
  • Completion → servers/completion.md
  • Logging, progress, cancel → servers/logging-progress-cancellation.md
  • Elicitation → servers/elicitation.md
  • input_required (not sunset sampling) → servers/input-required.md
  • Errors → servers/errors.md
  • stdio / serveStdioserving/stdio.md
  • Testing → testing.md
  • v1 → v2 → migration/upgrade-to-v2.md
  • 2026-07-28 protocol on v2 packages → migration/support-2026-07-28.md

Read the full file on GitHub · 75 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. yesterday Changed · +7 tokens per session 21185f090ff2
  2. 4d ago First seen · 75 lines · 106 tokens per session scan A f8c2febced73

Subscribe to this mod's changes

mcp-docs is a skill published in the GitHub repository Neschadin/askell-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 113 tokens to every session and 958 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens