Skillsindex

io.github.thomasblcPublished by GitHub account thomasblcv0.2.1Updated Oct 24, 2026

Search and score 11,000+ AI agent tools: MCP servers, Claude skills, GPT actions, IDE plugins.

VerifiedSTDIODesktop onlyKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

A local MCP server that lets an assistant search, compare, review and submit entries in SkillsIndex, a scored directory of over 11,000 AI agent tools.

What you can do
Search indexed tools by keyword, ecosystem or category, with ranked results and scores. Retrieve full details for one tool, including its security score, GitHub stats and scoring breakdown. List top-rated tools, optionally filtered by ecosystem or category. Check a tool's security score and audit notes. Submit a new tool to the review queue and subscribe an email address to the weekly newsletter.
When to use it
Useful when you are choosing between MCP servers, Claude skills, GPT actions or IDE plugins and want scored, comparable information inside the assistant, or when you want to submit your own tool to the directory without leaving the chat.
Requirements
A local runtime with Node.js, since it runs via npx or a global npm install and is configured as a stdio command in the client's MCP settings. No API keys or environment variables are declared. Network access is needed to reach the directory service.
Before you install
The submit tool sends a tool name, URL and description to the directory, and submissions enter a public review queue. The subscribe tool sends an email address to a third-party newsletter. Both write data outside your machine, so confirm details before asking the assistant to run them.

Installation

In SourceWeft

  1. Open Skillsindex in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

skillsindex-mcp

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.

Tools

ToolDescription
search_toolsSearch by keyword, ecosystem, or category — returns ranked results with scores
get_toolFull details for a tool: security score, GitHub stats, scoring breakdown
get_top_ratedTop-rated tools, optionally filtered by ecosystem or category
check_securitySecurity score (0-5) + audit notes for any indexed tool
submit_toolSubmit a new tool for indexing — auto-adds to the review queue
subscribeSubscribe an email to The Weekly Index (Thursday newsletter)

Install

bash
npx skillsindex-mcp

Or install globally:

bash
npm install -g skillsindex-mcp

Claude Desktop

Add to your claude_desktop_config.json:

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

Cursor / Windsurf / Cline

Add to your MCP settings:

json
{  "skillsindex": {    "command": "npx",    "args": ["skillsindex-mcp"]  }}

Usage Examples

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"

Tool Details

search_tools

query:      Search keyword or use case (required)ecosystem:  mcp_server | claude_skill | gpt_action | openclaw_skill | plugincategory:   databases-storage | browser-automation | code-execution | ...limit:      1-20 (default: 5)

get_tool

slug:  Tool slug, e.g. "filesystem-mcp-server" (from the URL: skillsindex.dev/tools/[slug]/)

get_top_rated

ecosystem:  optional filtercategory:   optional filterlimit:      1-20 (default: 10)

check_security

slug:  Tool slug (preferred)name:  Tool name (fuzzy match fallback)

submit_tool

name:        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.

subscribe

email:  Email address to subscribe (required)

Data

  • 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

Links

License

MIT

Source: README.md at commit c021bc2

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.2.1LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.