Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Mcp Spec

ASecurity

Model Context Protocol (MCP) open spec. Use for writing an MCP server or client (any language; TypeScript @modelcontextprotocol/sdk, Python mcp), JSON-RPC framing, initialize handshake, capability negotiation, stdio/streamable HTTP/SSE transports, defining tools/resources/prompts, sampling, roots, completion. Skip: Anthropic's hosted MCP connector (use anthropic-platform-features), Claude Connectors directory (use claude-connectors), Claude Code's .mcp.json (use claude-code → SKILL-mcp).

17 stars
0 votes
0 copies
0 views
Added 9/30/2026
ai-agentstypescriptpythongogit

Works with

claude codeclimcp

Security Analysis

A100/100

Pro scans all 20 files and shows the line behind each finding

Scanned 9/30/2026

$npx -y skills add xiaolai/anthropic-docs --skill mcp-spec --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mcp Spec?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Mcp Spec
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/xiaolai-mcp-spec/badge)](https://www.skillsdirectory.com/skills/xiaolai-mcp-spec)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: mcp-spec
description: |
  Model Context Protocol (MCP) open spec. Use for writing an MCP server or
  client (any language; TypeScript @modelcontextprotocol/sdk, Python mcp),
  JSON-RPC framing, initialize handshake, capability negotiation,
  stdio/streamable HTTP/SSE transports, defining tools/resources/prompts,
  sampling, roots, completion. Skip: Anthropic's hosted MCP connector (use
  anthropic-platform-features), Claude Connectors directory (use
  claude-connectors), Claude Code's .mcp.json (use claude-code →
  SKILL-mcp).
user-invocable: true
---

# Model Context Protocol (MCP) — Router

| Field | Value |
|---|---|
| **Source docs** | [modelcontextprotocol.io](https://modelcontextprotocol.io) |
| **Spec repo** | [modelcontextprotocol/modelcontextprotocol](https://github.com/modelcontextprotocol/modelcontextprotocol) |
| **TypeScript SDK** | [`@modelcontextprotocol/sdk`](https://www.npmjs.com/package/@modelcontextprotocol/sdk) |
| **Python SDK** | [`mcp`](https://pypi.org/project/mcp/) |

> **This skill is auto-updated daily.** A pipeline reads the upstream
> docs and rewrites the per-surface files below. Section structure is
> stable; content drifts to track upstream.

## When to use

Router skill for the Model Context Protocol (MCP) open spec, covering
the protocol itself (JSON-RPC framing, capabilities, lifecycle), the
client and server roles, the transport layers (stdio / streamable
HTTP / SSE), and the core primitives (tools, resources, prompts,
sampling, roots, completion).

Use when the user asks about: writing an MCP server (in any language),
writing an MCP client, the JSON-RPC protocol framing, the
initialize handshake, capability negotiation, the stdio transport,
the streamable HTTP transport, the SSE transport, defining a tool /
resource / prompt, sampling, roots, or completion. Includes the
TypeScript SDK (`@modelcontextprotocol/sdk`) and Python SDK (`mcp`).

Skip: Anthropic's hosted MCP connector (use
anthropic-platform-features), the user-facing Claude Connectors
directory (use claude-connectors), Claude Code's `.mcp.json` config
(use claude-code → SKILL-mcp).

## Dispatch table

| Surface file | Read when the user asks about… |
|---|---|
| [`SKILL-protocol.md`](SKILL-protocol.md) | JSON-RPC framing, the `initialize` handshake, capability negotiation, lifecycle, error codes, versioning |
| [`SKILL-clients.md`](SKILL-clients.md) | implementing an MCP client, calling tools, reading resources, the client-side of sampling |
| [`SKILL-servers.md`](SKILL-servers.md) | implementing an MCP server in TypeScript or Python, server-side capability advertisement, server lifecycle |
| [`SKILL-transport.md`](SKILL-transport.md) | stdio transport, streamable HTTP transport, SSE transport (legacy), choosing a transport |
| [`SKILL-tools-resources-prompts.md`](SKILL-tools-resources-prompts.md) | defining tools (input schema, output schema), defining resources (URI templates, MIME types), defining prompts, sampling, roots, completion |

## Examples

<example>
Context: A developer is building an MCP server in Python.
user: "How do I expose a resource and notify clients when it changes?"
assistant: Uses mcp-spec and reads the resources surface for list, read and change notifications.
</example>

<example>
Context: A developer configures a server for Claude Code.
user: "Where do I add my server so Claude Code loads it?"
assistant: Routes to claude-code instead; .mcp.json is Claude Code configuration.
</example>

---

*This skill is auto-updated daily by a maintainer-run pipeline. File
issues at [xiaolai/anthropic-docs](https://github.com/xiaolai/anthropic-docs).*

Attribution

xiaolaixiaolai
View sourceSee grades on GitHubMore from xiaolai →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →