Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@skillsindex-mcp Search for MCP servers for databases"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server for SkillsIndex — the scored directory of 11,000+ AI agent tools (MCP servers, Claude skills, GPT actions, IDE plugins).
Give your AI agents the ability to search, score, review, and submit tools from the largest independent AI tool directory.
Tool | Description |
| Search by keyword, ecosystem, or category — returns ranked results with scores |
| Full details for a tool: security score, GitHub stats, scoring breakdown |
| Top-rated tools, optionally filtered by ecosystem or category |
| Security score (0-5) + audit notes for any indexed tool |
| Submit a new tool for indexing — auto-adds to the review queue |
| Subscribe an email to The Weekly Index (Thursday newsletter) |
Related MCP server: agent101-mcp
npx skillsindex-mcpOr install globally:
npm install -g skillsindex-mcpAdd to your claude_desktop_config.json:
{
"mcpServers": {
"skillsindex": {
"command": "npx",
"args": ["skillsindex-mcp"]
}
}
}Config file locations:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Add to your MCP settings:
{
"skillsindex": {
"command": "npx",
"args": ["skillsindex-mcp"]
}
}Once connected, you can ask Claude things like:
"Search for MCP servers that connect to databases"
"What's the security score for the filesystem-mcp-server?"
"Show me the top 10 Claude skills"
"Submit this GitHub repo to SkillsIndex: https://github.com/..."
"Subscribe me to the SkillsIndex weekly newsletter"
search_toolsquery: Search keyword or use case (required)
ecosystem: mcp_server | claude_skill | gpt_action | openclaw_skill | plugin
category: databases-storage | browser-automation | code-execution | ...
limit: 1-20 (default: 5)get_toolslug: Tool slug, e.g. "filesystem-mcp-server" (from the URL: skillsindex.dev/tools/[slug]/)get_top_ratedecosystem: optional filter
category: optional filter
limit: 1-20 (default: 10)check_securityslug: Tool slug (preferred)
name: Tool name (fuzzy match fallback)submit_toolname: Tool name (required)
github_url: GitHub repo or homepage URL (required)
description: What the tool does (required, min 10 chars)
ecosystem: mcp_server | claude_skill | gpt_action | ... (default: mcp_server)
category: databases-storage | browser-automation | ... (default: other)Submissions land in a review queue. Tools are scored on security, utility, maintenance, and uniqueness before publishing.
subscribeemail: Email address to subscribe (required)11,393+ tools across 5 ecosystems
Scoring: security (30%) + utility (30%) + maintenance (25%) + uniqueness (15%)
Updated weekly via GitHub API
Security scores based on static analysis of source code
Directory: skillsindex.dev
Browse: skillsindex.dev/browse/
Submit a tool: skillsindex.dev/submit/
Scoring methodology: skillsindex.dev/methodology/
Newsletter: The Weekly Index — every Thursday
MIT
Get the security score and audit notes for a specific tool. Returns the tool's security score (0-5), risk flags, and audit summary from SkillsIndex's static analysis.
Inputs: name, slug.
Compare 2 to 5 tools side by side by their slugs: overall + security/utility/maintenance scores, GitHub stars, pricing, maintenance status. Use this to help a user choose between alternatives.
Inputs: slugs (required).
List the top AI agent tools that work on a specific platform (Claude, ChatGPT, Cursor, Windsurf, Cline, VS Code, JetBrains, OpenClaw, opencode, Ollama, LM Studio, local/open-source). Use this when the user runs a specific agent or editor.
Inputs: platform (required), limit.
Get full details for a specific tool by its slug (e.g. "filesystem-mcp-server"). Includes security score, GitHub stats, install instructions, and scoring breakdown.
Inputs: slug (required).
Get the top-rated AI agent tools from SkillsIndex, sorted by overall score (0-100). Optionally filter by ecosystem or category.
Inputs: limit, category, ecosystem.
Search the SkillsIndex directory for AI agent tools (MCP servers, Claude skills, GPT actions, IDE plugins). Returns ranked results with scores.
Inputs: query (required), limit, category, ecosystem.
Submit a new AI agent tool to SkillsIndex for indexing and scoring. The tool will be reviewed for security, utility, maintenance, and uniqueness before being published. Use this when you discover a useful tool that isn't in the directory yet.
Inputs: name (required), github_url (required), description (required), category, +1 more.
Subscribe a user email to The Weekly Index newsletter from SkillsIndex — weekly digest of new AI agent tools, security alerts, and honest picks.
Inputs: email (required).
Get the most recently added AI agent tools on SkillsIndex (newest first). Use this to discover fresh MCP servers, skills, and tools the directory just indexed.
Inputs: limit, ecosystem.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 9 tools
Most tools have clearly distinct purposes, but check_security largely duplicates the security information already included in get_tool, and get_by_platform overlaps with get_top_rated as both return ranked lists with different filters. This creates minor selection ambiguity.
The majority of tools follow the verb_noun pattern (search_tools, get_tool, submit_tool, compare_tools), but whats_new deviates from this pattern and get_by_platform is a slightly awkward phrase. Overall style is consistent snake_case.
Nine tools appropriately cover a directory service's functionality without bloat. Each tool serves a specific user need from discovery to evaluation to contribution.
The surface covers core directory operations: search, detail, compare, security, top lists, recent additions, submission, and newsletter subscription. No critical gaps exist for the typical user workflow.
Find AI agent skills: public previews and source links. Read-only discovery; no account required.
One place to build, share, and govern the skills and tools your AI agents use at work.
Find, read and install 50,000+ Agent Skills for Claude Code and other agents, with trust scores.
Search 1,700+ agent skills for Claude, Codex and Cursor, each safety-scanned, with proofs.
