Agent skill

Discover MCP

by rand in rand/cc-polymath

Automatically discover MCP (Model Context Protocol) skills when building MCP servers, designing tools, implementing resources/prompts, or testing MCP integrations.

MITAuto-check passedAgent Workflows

Install Discover MCP

skills CLI
$ npx skills add rand/cc-polymath --skill discover-mcp -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install rand/cc-polymath discover-mcp --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/rand/cc-polymath.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/discover-mcp .claude/skills/discover-mcp && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
discover-mcp
GitHub stars
181
Token cost
~938 tokens
SKILL.md length
374 words
Files
1
Skills in repo
26
Repo updated
First seen
Licence
MIT

At a glance

Automatically discover MCP (Model Context Protocol) skills when building MCP servers, designing tools, implementing resources/prompts, or testing MCP integrations.

  • Works in 3 steps: mcp-server-fundamentals - Architecture,… → mcp-tool-design - Tool naming, schemas,… → mcp-testing - Inspector, unit tests,…
  • Tasks that involve MCP servers
  • SKILL.md covers When This Skill Activates, Available Skills, Common Workflows and Integration with Other Skills, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Discover MCP is an agent skill from rand/cc-polymath. Automatically discover MCP (Model Context Protocol) skills when building MCP servers, designing tools, implementing resources/prompts, or testing MCP integrations. Activates for MCP server development tasks.

Its SKILL.md is about 940 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Designed for Claude Code. Compatible with any agent supporting the Agent Skills format.

It sits in Agent Workflows, covering MCP servers. It works with Model Context Protocol. The repository describes itself as: Claude Code skills and workflows, optimized for context-efficiency and skill quality. Skills ranging from cloud infrastructure to design to advanced maths. The licence is MIT.

When your agent uses it

  • Tasks that involve MCP servers

Example prompts

  • “/discover-mcp”

Requirements

  • Compatibility (from SKILL.md): Designed for Claude Code. Compatible with any agent supporting the Agent Skills format.

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. mcp-server-fundamentals - Architecture, transports, tools/resources/prompts primitives, SDK setup
  2. mcp-tool-design - Tool naming, schemas, error handling, annotations, progressive disclosure
  3. mcp-testing - Inspector, unit tests, integration tests, transport debugging, CI/CD

What it can do on your machine

Read from SKILL.md and the folder at commit baa2df1. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Designed for Claude Code. Compatible with any agent supporting the Agent Skills format.

    From compatibility in the SKILL.md frontmatter.

Context cost

Discover MCP loads about 938 tokens when it runs. Until then it costs about 55 tokens; SKILL.md has 374 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~55
When it runs · the whole SKILL.md, loaded when a task matches
~938

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from rand/cc-polymath at commit baa2df1, republished under its MIT licence (© rand). 374 words, ~938 tokens.

Download SKILL.mdSave it as .claude/skills/discover-mcp/SKILL.md (or your agent's skills folder).
name
discover-mcp
description
Automatically discover MCP (Model Context Protocol) skills when building MCP servers, designing tools, implementing resources/prompts, or testing MCP integrations. Activates for MCP server development tasks.
compatibility
Designed for Claude Code. Compatible with any agent supporting the Agent Skills format.
license
MIT
metadata.author
rand
metadata.version
4.0

MCP Skills Discovery

Provides automatic access to comprehensive MCP server development, tool design, and testing skills.

When This Skill Activates

This skill auto-activates when you're working with:

  • Building MCP servers (TypeScript or Python)
  • Designing MCP tools, resources, or prompts
  • Choosing MCP transports (stdio, SSE, Streamable HTTP)
  • Implementing JSON-RPC 2.0 over MCP
  • Testing MCP servers with Inspector or automated tests
  • Debugging MCP protocol or transport issues
  • Publishing or deploying MCP servers

Available Skills

Quick Reference

The MCP category contains 3 specialized skills:

  1. mcp-server-fundamentals - Architecture, transports, tools/resources/prompts primitives, SDK setup
  2. mcp-tool-design - Tool naming, schemas, error handling, annotations, progressive disclosure
  3. mcp-testing - Inspector, unit tests, integration tests, transport debugging, CI/CD
Load Full Category Details

For complete descriptions and workflows:

Read ../mcp/INDEX.md

This loads the full MCP category index with:

  • Detailed skill descriptions
  • Usage triggers for each skill
  • Common workflow combinations
  • Cross-references to related skills
Load Specific Skills

Load individual skills as needed:

Server architecture and setup

Read ../mcp/mcp-server-fundamentals.md

Tool design and best practices

Read ../mcp/mcp-tool-design.md

Testing and debugging

Read ../mcp/mcp-testing.md

Common Workflows

New MCP Server

Sequence: Fundamentals -> Tool Design -> Testing

Read ../mcp/mcp-server-fundamentals.md # Architecture, transport, SDK Read ../mcp/mcp-tool-design.md # Design tool interfaces Read ../mcp/mcp-testing.md # Test with Inspector, CI

Adding Tools to Existing Server

Sequence: Tool Design -> Testing

Read ../mcp/mcp-tool-design.md # Naming, schemas, errors Read ../mcp/mcp-testing.md # Test new tools

Debugging MCP Issues

Sequence: Testing -> Fundamentals

Read ../mcp/mcp-testing.md # Inspector, transport debugging Read ../mcp/mcp-server-fundamentals.md # Lifecycle, capabilities

Show full SKILL.md (145 more words)Show less

Integration with Other Skills

MCP skills commonly combine with:

API skills (discover-api):

  • MCP servers wrapping REST or GraphQL APIs
  • Authentication for MCP tool backends

Testing skills (discover-testing):

  • Comprehensive test strategies
  • Contract testing patterns

Infrastructure skills (discover-infra, discover-cloud):

  • Deploying MCP servers
  • Scaling HTTP transports

Progressive Loading

This gateway skill (~170 lines, ~1.5K tokens) enables progressive loading:

  • Level 1: Gateway loads automatically (you're here now)
  • Level 2: Load category INDEX.md (~2.5K tokens) for full overview
  • Level 3: Load specific skills (~2-3K tokens each) as needed

Total context: 1.5K + 2.5K + skill(s) = 4-8K tokens vs 12K+ for everything.

Quick Start Examples

"Build an MCP server": Read ../mcp/mcp-server-fundamentals.md

"Design MCP tools for my API": Read ../mcp/mcp-tool-design.md

"Test my MCP server": Read ../mcp/mcp-testing.md

"Debug why my MCP tool isn't showing up": Read ../mcp/mcp-testing.md

Next Steps: Run Read ../mcp/INDEX.md to see full category details, or load specific skills using the commands above.

© rand, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/discover-mcp of rand/cc-polymath.

Open the folder on GitHubat commit baa2df1

Compare with similar skills

Discover MCP next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Discover MCP compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Discover MCP this skillrand/cc-polymath181—~938Automated safety check: PassMIT
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k4 repos~1.2kAutomated safety check: PassMIT
MCP Integration for Pluginsanthropics/claude-plugins-official38k11 repos~3.1kAutomated safety check: PassApache-2.0
Crush Configurationcharmbracelet/crush29k—~3.7kAutomated safety check: PassCustom licence
Context Mode Output Sandboxmksglu/context-mode26k—~4.1kAutomated safety check: PassCustom licence

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 4 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    38k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed
  • Crush Configuration

    charmbracelet/crush

    Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.

    29k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Context Mode Output Sandbox

    mksglu/context-mode

    Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.

    26k GitHub stars~4.1k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Migrates the compatible subset of settings and global file-based MCP servers from the Warp desktop app into Warp Agent CLI without exposing credentials or state.

    65k GitHub starsUsed in 1 repo~2.1k tokens
    Agent WorkflowsAuto-check passed

More from rand/cc-polymath

All 26 skills in this repo
  • Anti Slop

    rand/cc-polymath

    Comprehensive toolkit for detecting and eliminating "AI slop" - generic, low-quality AI-generated patterns in natural language, code, and design.

    181 GitHub stars~2.9k tokensUpdated 7 mo ago
    Auto-check passed
  • Typed Holes Refactor

    rand/cc-polymath

    Refactor codebases using Design by Typed Holes methodology - iterative, test-driven refactoring with formal hole resolution, constraint propagation, and continuous validation.

    181 GitHub stars~5.6k tokensUpdated 7 mo ago
    Auto-check passed
  • Elegant Design

    rand/cc-polymath

    Create world-class, accessible, responsive interfaces with sophisticated interactive elements including chat, terminals, code display, and streaming content.

    181 GitHub stars~2.7k tokensUpdated 7 mo ago
    Auto-check passed
  • Discover Agentic

    rand/cc-polymath

    Automatically discover agentic workflow skills when building AI agents, implementing tool use patterns, managing context windows, decomposing complex tasks, or designing multi-step autonomous…

    181 GitHub stars~1.4k tokensUpdated 7 mo ago
    Auto-check passed
  • Discover API

    rand/cc-polymath

    Automatically discover API design skills when working with REST APIs, GraphQL schemas, API authentication, OAuth, JWT, rate limiting, API versioning, error handling, or endpoint design.

    181 GitHub stars~1.5k tokensUpdated 7 mo ago
    Auto-check passed
  • Discover Database

    rand/cc-polymath

    Automatically discover database skills when working with SQL, PostgreSQL, MongoDB, Redis, database schema design, query optimization, migrations, connection pooling, ORMs, or database selection.

    181 GitHub stars~2k tokensUpdated 7 mo ago
    Auto-check passed

Categories

Questions about Discover MCP

What does Discover MCP do?

Automatically discover MCP (Model Context Protocol) skills when building MCP servers, designing tools, implementing resources/prompts, or testing MCP integrations. Discover MCP is an agent skill from rand/cc-polymath. Automatically discover MCP (Model Context Protocol) skills when building MCP servers, designing tools, implementing resources/prompts, or testing MCP integrations.

When should I use Discover MCP?

Discover MCP fits situations like: tasks that involve MCP servers.

How do I install Discover MCP in Claude Code?

Run `npx skills add rand/cc-polymath --skill discover-mcp -a claude-code`. Or copy the skill folder (skills/discover-mcp in rand/cc-polymath) into .claude/skills/discover-mcp in your project. Claude Code loads it when a task matches its description.

How do I install Discover MCP in Codex?

Run `npx skills add rand/cc-polymath --skill discover-mcp -a codex`. Or copy the skill folder (skills/discover-mcp in rand/cc-polymath) into .agents/skills/discover-mcp in your project. Codex loads it when a task matches its description.

Can I use Discover MCP in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add rand/cc-polymath --skill discover-mcp -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/discover-mcp, .gemini/skills/discover-mcp, .github/skills/discover-mcp and .opencode/skills/discover-mcp in your project.

What does Discover MCP need to run?

SKILL.md names no scripts, command-line tools or credentials: Discover MCP is instructions for the agent only. Compatibility (from SKILL.md): Designed for Claude Code. Compatible with any agent supporting the Agent Skills format..

Does Discover MCP access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Discover MCP safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Discover MCP use?

Discover MCP is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Discover MCP use?

About 938 tokens (SKILL.md is roughly 3.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Discover MCP?

Skills that share tags, products or a category with Discover MCP: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and Crush Configuration (charmbracelet/crush, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Discover MCP?

rand (a GitHub user) maintains it in rand/cc-polymath, which has 181 GitHub stars. The repository holds 26 skills in this directory. The repository was last updated on February 28, 2026.

Source: rand/cc-polymath on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.