mcp-research
Discover, profile, and evaluate MCP servers for a given domain or purpose. Use when searching for MCP servers to add to a project, comparing server capabilities, enriching the local registry cache, or evaluating whether a server suite covers a stated need. Covers cache-first discovery, remote registry scanning, deep server profiling, and gap analysis.
npx skills add majiayu000/claude-skill-registry --skill mcp-research-arustydev-ai --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# MCP Server Research Guide for discovering, profiling, and evaluating MCP servers using the local SQLite+FTS5 registry cache and three specialized agents. ## When to Use This Skill - Finding MCP servers for a specific domain (e.g., "code analysis", "database management") - Profiling an MCP server to understand its tools, install method, and quality - Comparing multiple servers to recommend the best fit - Seeding or enriching the local registry cache - Running the `/find-mcp-servers` slash command ## Architecture ``` ┌─────────────────────┐ │ /find-mcp-servers │ ← Slash command (entry point) └────────┬────────────┘ │ ▼ ┌─────────────────────┐ ┌──────────────────────┐ │ plugin-mcp-researcher│────▶│ SQLite+FTS5 Cache │ │ (orchestrator) │ │ .data/mcp/registry- │ └────────┬────────────┘ │ cache.db │ │ └──────────────────────┘ ┌────┴────┐ ▼ ▼ ┌────────┐ ┌─────────────┐ │Scanner │ │ Profiler │ │(haiku) │ │ (sonnet) │ └────────┘ └─────────────┘ ``` ### Components | Component | Type | Model | Purpose | |-----------|------|-------|---------| | `plugin-mcp-researcher` | agent | haiku | Cache-first orchestrator — queries FTS, dispatches scanner/profiler | | `mcp-registry-scanner` | agent | ha
- When to Use This Skill
- Architecture
- Components
- Storage Layer
- Workflow: Discovering Servers
- Step 1: Query Local Cache
- Step 2: Evaluate Coverage
- Step 3: Remote Discovery (if needed)
- Step 4: Deep Profiling (if needed)
- Step 5: Rank and Present
- Workflow: Profiling a Single Server
- Workflow: Seeding from YAML Config
- Registry Reference
- Tier 1 (always search)
just mcp-stats # Show server/registry counts just mcp-search "query" # Search servers by name/description just mcp-list # List top servers by stars just mcp-show <slug> # Show server details just mcp-tools <slug> # Show server's tools just kg-dump # Dump entire knowledge graph sqlite3 -json .data/mcp/knowledge-graph.db " SELECT e.id, e.name, e.slug, e.content as description, FROM entities e JOIN entities_fts f ON e.id = f.rowid
What does the mcp-research skill do?
Discover, profile, and evaluate MCP servers for a given domain or purpose. Use when searching for MCP servers to add to a project, comparing server capabilities, enriching the local registry cache, or evaluating whether a server suite covers a stated need. Covers cache-first discovery, remote registry scanning, deep server profiling, and gap analysis.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill mcp-research-arustydev-ai --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.