New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

MCP Registry Discovery

by codewhale-hq in codewhale-hq/Codewhale

Finds and starts a local MCP server from the public registry when a session lacks a capability that no existing tool, script or local code can cover.

MITAuto-check passedAgent Workflows

Install MCP Registry Discovery

skills CLI
$ npx skills add codewhale-hq/Codewhale --skill mcp-discovery -a claude-code

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

GitHub CLI
$ gh skill install codewhale-hq/Codewhale mcp-discovery --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/codewhale-hq/Codewhale.git skills-src && mkdir -p .claude/skills && cp -r skills-src/crates/tui/assets/skills/mcp-discovery .claude/skills/mcp-discovery && 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
mcp-discovery
GitHub stars
41k
Token cost
~805 tokens
SKILL.md length
455 words
Files
2
Skills in repo
63
Repo updated
First seen
Licence
MIT

At a glance

Finds and starts a local MCP server from the public registry when a session lacks a capability that no existing tool, script or local code can cover.

  • Works in 5 steps: Name the gap. State the capability you… → Load and query. registry_sync and… → Judge the matches. Take a server when it… → …
  • A task needs a database or service client that the session has no tool for
  • SKILL.md covers When to use, When not to use, Workflow and If a server fails to start, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

This skill is a fallback for when a task needs a capability the session does not have, such as an external service, a database or a protocol client, and no available tool, project script or few lines of code can do it. It points to the public MCP Registry, which offers hundreds of ready-made stdio servers, and warns that discovery costs a tool search, a query, an approval and an install, so it should never be a first step.

The workflow is to name the missing capability, load the deferred registry_sync and start_registry_mcp_server tools, query the registry for at most eight scored matches, judge whether one covers the gap (refining the query once if not), and start the chosen server by its exact name with only the required arguments. Packages that declare environment variables, including API keys, are excluded, nothing is installed through the shell, and starting a server needs approval. Once connected, the server's tools are available in the same turn.

When your agent uses it

  • A task needs a database or service client that the session has no tool for
  • Avoiding a hand-written converter or client when a ready-made MCP server exists
  • Deciding whether a capability gap justifies searching the MCP Registry

Example prompts

  • “I need to query a SQLite database but no tool here can do it, so look for an MCP server that can.”
  • “Find a zero-environment MCP server that can turn these audio files into text.”
  • “Check the MCP Registry for a server that can read PDF files, since none of our tools can.”

Requirements

  • A session with the registry_sync and start_registry_mcp_server tools
  • Approval to start a server

Workflow steps

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

  1. Name the gap. State the capability you lack before searching. If you
  2. Load and query. registry_sync and start_registry_mcp_server are
  3. Judge the matches. Take a server when it covers the gap you named. If
  4. Install + run transactionally. Call
  5. Solve the task with the new tools. Their complete schemas are added to

What it can do on your machine

Read from SKILL.md and the folder at commit 0ea319a. 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.

Context cost

MCP Registry Discovery loads about 805 tokens when it runs. Until then it costs about 44 tokens; SKILL.md has 455 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~44
When it runs · the whole SKILL.md, loaded when a task matches
~805

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 codewhale-hq/Codewhale at commit 0ea319a, republished under its MIT licence (© codewhale-hq). 455 words, ~805 tokens.

Download SKILL.mdSave it as .claude/skills/mcp-discovery/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
mcp-discovery
description
Find and start a zero-environment local MCP server when the session lacks a capability that no available tool, project script, or ordinary local code can cover.

mcp-discovery

The public MCP Registry ships hundreds of ready-made stdio servers (filesystems, databases, browsers, media processing, developer utilities, cloud APIs, SaaS integrations, …). This skill is how you reach one when the session is genuinely missing a capability.

It is a fallback, not a first step. Discovery costs a tool_search to load the deferred tools, a query, an approval, and an install — spend that only when it buys a capability you do not have.

When to use

  • An available tool, a project script or test, or a few lines of local code cannot do the job.
  • The task needs an external service, database, or protocol client that this session has no access to.
  • You would otherwise install a package or reimplement a well-known converter or client by hand.

When not to use

  • Ordinary work: writing and editing files, reading fixtures, running repo commands, and checking your own output. Do those directly.
  • A capability an already-loaded tool covers, even partially — try it first.
  • A near-miss row in a result list. A scored match is a suggestion; the missing capability is what decides.

Workflow

  1. Name the gap. State the capability you lack before searching. If you cannot name one, you do not need the Registry.
  2. Load and query. registry_sync and start_registry_mcp_server are deferred: load one with tool_search and use the returned schema. If a call only loads the schema without executing, retry once with that schema. Then call registry_sync {query: "<the missing capability>"}. It scores a host-side snapshot and returns at most eight matches; the full index never enters the conversation. Packages declaring any environment variable (including API keys/tokens) are excluded and never written to the cache.
  3. Judge the matches. Take a server when it covers the gap you named. If nothing does, refine the query once, then continue with local tools.
  4. Install + run transactionally. Call start_registry_mcp_server {registry_name: "<exact name>", arguments: {...}}. Supply only values listed in required_args; omit arguments when none are required. Never install or launch the package through the shell. Starting a server requires approval.
  5. Solve the task with the new tools. Their complete schemas are added to the current turn immediately after a successful connection; call the exact names returned by the start result.
Show full SKILL.md (86 more words)Show less

If a server fails to start

start_registry_mcp_server reports when a package exits before the handshake (often CLI help output = incomplete launch args). Verify the exact required arguments, retry once with the corrected structured values, and if it still fails move on to the next candidate or to a local approach. Failed starts are rolled back, so retrying the same Registry name is safe.

Don't

  • Don't attempt to pass env vars or secrets; this flow has no env channel.
  • Don't reconstruct or edit the Registry-provided package command.

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

Files

SKILL.md and 1 other file in crates/tui/assets/skills/mcp-discovery of codewhale-hq/Codewhale.

  • SKILL.md
  • SKILL.generation-10.md

Open the folder on GitHubat commit 0ea319a

Compare with similar skills

MCP Registry Discovery 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.

MCP Registry Discovery compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
MCP Registry Discovery this skillcodewhale-hq/Codewhale41k—~805Automated 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

  • Warp GUI to Agent CLI Migration

    warpdotdev/warp

    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 codewhale-hq/Codewhale

All 63 skills in this repo

  • Codewhale Dogfood Install

    codewhale-hq/Codewhale

    Proves a Codewhale change in the real product: a stamped release build, an atomic local install, fresh-shell verification and manual QA that automated gates cannot cover.

    41k GitHub stars~1.3k tokensUpdated today
    Auto-check passed

  • Codewhale Session Handoff

    codewhale-hq/Codewhale

    Writes a paste-ready handoff for the next agent session, opening with a state-check command block and separating done, suspected and blocked work.

    41k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Codewhale Landing Workflow

    codewhale-hq/Codewhale

    Decides how verified work should reach main, directly, in a worktree or on an integration branch, while keeping contributor credit and respecting merge gates.

    41k GitHub stars~1.6k tokensUpdated today
    Auto-check passed

  • Sub-Agent Delegation

    codewhale-hq/Codewhale

    Guides when and how to split multi-step coding, research or verification work into focused sub-agent runs while the parent keeps integration and final checks.

    41k GitHub stars~790 tokensUpdated today
    Auto-check passed

  • Codewhale Fleet Manager

    codewhale-hq/Codewhale

    Triages and manages Codewhale fleet runs and workers with typed commands, classifying failures and choosing a safe restart, resume or escalation.

    41k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • GitHub Issue Bulk Assigner

    codewhale-hq/Codewhale

    Moves a list of GitHub issues into a milestone or assigns them to owners with the gh CLI, checking each one before and after the change.

    41k GitHub stars~953 tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about MCP Registry Discovery

What does MCP Registry Discovery do?

Finds and starts a local MCP server from the public registry when a session lacks a capability that no existing tool, script or local code can cover. This skill is a fallback for when a task needs a capability the session does not have, such as an external service, a database or a protocol client, and no available tool, project script or few lines of code can do it. It points to the public MCP Registry, which offers hundreds of ready-made stdio servers, and warns that discovery costs a tool search, a query, an approval and an install, so it should never be a first step.

When should I use MCP Registry Discovery?

MCP Registry Discovery fits situations like: A task needs a database or service client that the session has no tool for; avoiding a hand-written converter or client when a ready-made MCP server exists; deciding whether a capability gap justifies searching the MCP Registry.

How do I install MCP Registry Discovery in Claude Code?

Run `npx skills add codewhale-hq/Codewhale --skill mcp-discovery -a claude-code`. Or copy the skill folder (crates/tui/assets/skills/mcp-discovery in codewhale-hq/Codewhale) into .claude/skills/mcp-discovery in your project. Claude Code loads it when a task matches its description.

How do I install MCP Registry Discovery in Codex?

Run `npx skills add codewhale-hq/Codewhale --skill mcp-discovery -a codex`. Or copy the skill folder (crates/tui/assets/skills/mcp-discovery in codewhale-hq/Codewhale) into .agents/skills/mcp-discovery in your project. Codex loads it when a task matches its description.

Can I use MCP Registry Discovery 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 codewhale-hq/Codewhale --skill mcp-discovery -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mcp-discovery, .gemini/skills/mcp-discovery, .github/skills/mcp-discovery and .opencode/skills/mcp-discovery in your project.

What does MCP Registry Discovery need to run?

SKILL.md names no scripts, command-line tools or credentials: MCP Registry Discovery is instructions for the agent only. Our summary lists: A session with the registry_sync and start_registry_mcp_server tools; Approval to start a server.

Does MCP Registry Discovery 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 MCP Registry Discovery 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 MCP Registry Discovery use?

MCP Registry Discovery is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does MCP Registry Discovery use?

About 805 tokens (SKILL.md is roughly 3.2k 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 MCP Registry Discovery?

Skills that share tags, products or a category with MCP Registry Discovery: 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 MCP Registry Discovery?

codewhale-hq (a GitHub organization) maintains it in codewhale-hq/Codewhale, which has 41,082 GitHub stars. The repository holds 63 skills in this directory. The repository was last updated on October 11, 2026.

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