mcp-discovery

mcp-discovery is a skill for Claude Code from opensesh/DESIGN-OPS. It costs 0 tokens per session (3,446 once invoked), scanned A, original, Apache-2.0.

A runtime process for finding ways to connect external tools through MCP, a standard that lets an agent use tools and services. It checks npm, GitHub, and vendor documentation instead of relying only on a fixed list.

In plain words
What is it for?
Use it during setup when someone selects a tool such as Monday.com. It compares possible connection methods and returns a recommendation with a confidence level.
Why use it?
Fixed tool lists can become outdated as new MCP packages and documentation appear. This helps determine whether an official connection, a community package, or a direct API integration is available.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

Part of the design-ops plugin — 5 skills, 13 commands shipped together

Good fit Use it during setup when someone selects a tool such as Monday.com. It compares possible connection methods and returns a recommendation with a confidence level.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/opensesh/design-ops/mcp-discovery
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.

Any agent
npx skills add opensesh/DESIGN-OPS --skill mcp-discovery
Clone the repo
git clone --depth 1 https://github.com/opensesh/DESIGN-OPS

Made for: Claude Code.

Or install design-ops, the plugin that ships this one along with the rest of its 5 skills, 13 commands.

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-discovery

README.md
[![agentmods](https://agentmods.dev/badge/skills/opensesh/design-ops/mcp-discovery/github.svg)](https://agentmods.dev/skills/opensesh/design-ops/mcp-discovery)
Your own site
<a href="https://agentmods.dev/skills/opensesh/design-ops/mcp-discovery"><img src="https://agentmods.dev/badge/skills/opensesh/design-ops/mcp-discovery/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mcp-discovery

Your own site · 80×15
<a href="https://agentmods.dev/skills/opensesh/design-ops/mcp-discovery"><img src="https://agentmods.dev/badge/skills/opensesh/design-ops/mcp-discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,446 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00000 $0.03446
Opus 5 $0.00000 $0.01723
Sonnet 5 $0.00000 $0.00689
Haiku 4.5 $0.00000 $0.00345

Measured 11d ago against content hash a7cd7b9565dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mcp-discovery 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 11d ago.

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.

skills/mcp-discovery/SKILL.md · 485 lines

How it starts

The opening of the file, as written. The whole thing — 485 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Discovery Skill

Dynamic MCP package discovery at runtime. Instead of relying on a static registry, this skill verifies MCP availability by querying npm, GitHub, and vendor documentation.

Purpose

When a user selects a tool during /design-ops:setup, this skill discovers the best connection method:

  1. Check for official/vendor MCPs
  2. Evaluate community packages (with quality metrics)
  3. Find API documentation for direct integration
  4. Return a recommendation with confidence level

Why Dynamic Discovery?

  • 100+ potential tools across operations/design/analytics
  • Static registries become stale immediately
  • New MCPs are published constantly
  • Tool-agnostic design requires runtime discovery

Trigger

Invoked by tool-evaluator skill during setup flow:

skill: mcp-discovery
input:
  tool: "monday"
  pillar: "operations"

Discovery Flow

User selects tool (e.g., "Monday.com")
           │
           ▼
┌─────────────────────────────────────────────────────────────┐
│  Step 1: Check Known Tools (fast path)                      │
│  - Look up in known_tools.yaml for common tools             │
│  - If found with high confidence, return immediately        │
└─────────────────────────────────────────────────────────────┘
           │ not found
           ▼
┌─────────────────────────────────────────────────────────────┐
│  Step 2: Search npm for Official MCP                        │
│  - npm view @modelcontextprotocol/server-{tool}             │
│  - npm view @{vendor}/mcp-server                            │
│  - Check for vendor-published packages                      │
└─────────────────────────────────────────────────────────────┘
           │
           ▼
┌─────────────────────────────────────────────────────────────┐
│  Step 3: Search npm for Community MCPs                      │
│  - npm search {tool} mcp --json                             │
│  - Filter by: downloads > 1000, updated < 6 months          │
│  - Rank by quality metrics                                  │
└─────────────────────────────────────────────────────────────┘
           │
           ▼
┌─────────────────────────────────────────────────────────────┐
│  Step 4: Check Anthropic MCP Servers Repo                   │
│  - GitHub API: repos/anthropics/mcp-servers/contents        │
│  - Look for tool-specific server                            │
└─────────────────────────────────────────────────────────────┘
           │
           ▼
┌─────────────────────────────────────────────────────────────┐
│  Step 5: Discover API Documentation                         │
│  - Web search: "{tool} API documentation"                   │
│  - Check common patterns: api.{tool}.com, developers.{tool} │
│  - Scrape for authentication requirements                   │
└─────────────────────────────────────────────────────────────┘
           │
           ▼
┌─────────────────────────────────────────────────────────────┐
│  Step 6: Return Discovery Result                            │
│  - Recommendation: mcp | api | both | unavailable           │
│  - Confidence level based on source quality                 │
│  - Warning if community package                             │
└─────────────────────────────────────────────────────────────┘

Read the full file on GitHub · 485 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 485 lines · 0 tokens per session scan A a7cd7b9565dc

Subscribe to this mod's changes

mcp-discovery is a skill published in the GitHub repository opensesh/DESIGN-OPS (23 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,446 tokens. 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 2026-08-30.

Related

Other skills, from other repositories

system-pitch

Write a design system investment pitch with a business case and ROI framing. Trigger when someone says: pitch the design system, make the case for the system, sell this to leadership, justify the investment, business case for design systems, why should we invest in a design system, or anything about building an…

murphytrueman/design-system-ops · 72 tokens

token-audit

Audit a design system's token definitions for naming violations, missing semantic tiers, and structural debt. This audits how tokens are defined and organised, NOT how they are consumed in code. Trigger when someone says: audit my tokens, token naming review, are my tokens consistent, token health check, review my…

murphytrueman/design-system-ops · 93 tokens

ai-component-description

Generate AI-optimised text descriptions for components, formatted for Figma's MCP server and LLM consumption. This produces prose descriptions in a six-section format (purpose, props, anti-patterns, composition, accessibility, examples), NOT JSON schemas or structured data files. Trigger when someone says: write…

murphytrueman/design-system-ops · 132 tokens

stakeholder-brief

Write a one-page stakeholder brief translating design system health or status into business language. Trigger when someone says: stakeholder update, exec brief, leadership summary, status report for leadership, system status for non-designers, write a brief for the business, or anything about communicating design…

murphytrueman/design-system-ops · 73 tokens

accessibility-per-component

Run an accessibility audit on a specific design system component. Trigger when someone says: accessibility check, a11y audit, WCAG compliance, is this accessible, check accessibility, does this meet WCAG, screen reader support, keyboard navigation check, or anything about auditing the accessibility of a specific…

murphytrueman/design-system-ops · 65 tokens

codemod-generator

Generate codemods (automated code transformation scripts) for design system migrations — token renames, component API changes, prop deprecations, and import path updates. Produces ready-to-run jscodeshift or custom AST transform scripts that safely apply changes across consuming codebases. Trigger when someone says…

murphytrueman/design-system-ops · 162 tokens