6 skills built for Model Context Protocol
Claude Code skills for Model Context Protocol
MCP skills for building, testing and securing Model Context Protocol servers, wiring them into Claude Code, and keeping their tool output from flooding the context window.
Start with these
- MCP Server Builder Connect Claude to your systems with tools it picks right Builds Model Context Protocol servers that Claude can actually use well. Instead of mirroring every REST endpoint, Claude designs a few task-level tools with bounded schemas, compact outputs and fixable error messages, wires stdio or Streamable HTTP with the official SDKs, tests each tool in the Inspector and a scripted client, and registers the server for you or your team without leaking secrets.
- MCP Troubleshooting From 'Failed to connect' to a named cause in six rungs Claude stops restarting servers at random and works a fixed ladder: claude mcp list and get, running the server command by hand with an initialize probe, the MCP Inspector, then filtered debug logs. It checks whole-entry scope precedence, env expansion, auth state and timeouts, and only calls it fixed after one real tool call succeeds in a fresh session.
- Agent SDK Builder Ship a custom agent on Claude Code's own loop Builds agents on the Claude Agent SDK that are safe to run inside a product. Claude starts with a read-only loop that logs every message type, adds domain tools as in-process MCP servers, gates risky calls with canUseTool or hooks, chooses the system prompt preset and settingSources on purpose so CLAUDE.md and skills load only when intended, and bounds every run by turns, time and logged cost.
3 more Model Context Protocol skills
Each card opens the full playbook, example prompts and install commands.
Context Window Hygiene
Keep long sessions sharp instead of slowly forgetful
Treats the context window as working memory that degrades when stuffed with dead ends and raw logs. Claude checks /context, trims fixed costs like unused MCP servers, scopes every read and command output, keeps the plan and key facts in a file, and picks the right reset: clear for a new task, compact with keep and drop instructions, rewind after a wrong turn, or a fresh session when corrections stop sticking.
Permissions Policy
Fewer prompts for safe work, hard stops for the rest
Designs a layered permission setup instead of clicking yes all day. Claude classifies the actions your repo really performs, allows the routine read-only and workspace work, asks for anything that leaves the machine, denies secrets and irreversible commands, and commits the shared baseline. It also covers what rules cannot stop, such as reading .env through Bash, and adds hooks or the sandbox there.
Plugin Marketplace Publisher
Ship your skills, agents and hooks as one install
Packages a scattered set of skills, subagents, hooks and MCP servers into one versioned plugin and publishes it through a git-hosted marketplace. Claude fixes the layout mistakes that stop components loading, rewrites paths for the plugin cache, validates manifests with a bundled checker, proves the install works in a clean session, and commits the settings that prompt teammates to install it.
General skills with Model Context Protocol guidance
Not built around Model Context Protocol, but they include Model Context Protocol-specific tools or steps. Not part of the install-all command.
Install
Every Model Context Protocol skill in one command
Installs these 6 skills into ~/.claude/skills/. Add --project after -- to install into the current repository instead.
The installer is a 101-line POSIX shell script. It downloads each skill you name from claudeskills.page and unpacks it into your skills folder, nothing else: no sudo, no telemetry. Every skill page shows the full SKILL.md, so you can read what you install first. Read install.sh
- mcp-server-builder
- mcp-troubleshooting
- agent-sdk-builder
- context-window-hygiene
- permissions-policy
- plugin-marketplace-publisher
curl -fsSL https://claudeskills.page/install.sh | sh -s -- …6 names Model Context Protocol skills FAQ
Answers drawn from the skills themselves, including what they don't cover.
Do the skills cover building MCP servers or only using them?
Both. MCP Server Builder writes servers with the official TypeScript SDK, with a Python FastMCP reference, designs task-level tools with tight Zod schemas plus resources and prompts, tests them in the MCP Inspector and a scripted client smoke test, then registers them with claude mcp add or a shared .mcp.json. Agent SDK Builder adds in-process MCP tools for custom agents.
Should my MCP server use stdio or Streamable HTTP?
MCP Server Builder defaults to stdio for a local, single-user tool and Streamable HTTP for shared or remote servers with many clients. It treats SSE as legacy and says not to start new servers on it. For HTTP it requires a bearer token or OAuth before handling requests, Origin header validation, binding to 127.0.0.1 unless the server must be reachable, and TLS in front.
What do the skills do when a server shows Failed to connect or its tools are missing?
MCP Troubleshooting works a fixed ladder: claude mcp list, claude mcp get, running the server command by hand with the same env, the MCP Inspector, then claude --debug=mcp. It maps common causes to fixes, such as stdout logging corrupting JSON-RPC, binaries missing from the PATH Claude Code inherits, unset ${VAR} expansion, and output over the 25,000-token MAX_MCP_OUTPUT_TOKENS default.
How do I install all 6 Model Context Protocol skills at once?
Pass every name to the installer in one command: curl -fsSL https://claudeskills.page/install.sh | sh -s -- mcp-server-builder mcp-troubleshooting agent-sdk-builder context-window-hygiene permissions-policy plugin-marketplace-publisher. Add --project after -- to install them into the current repository's .claude/skills/ folder so your team gets them too.