← Browse

@sundial-org/agnxi-search

B

The official search utility for Agnxi.com - The premier directory of AI Agent Tools, MCP Servers, and Skills.

skillclaude

Install

agr install @sundial-org/agnxi-search --target claude

Writes 3 files into .claude/skills/, pinned to git-6a844fca.

  • .claude/skills/agnxi-search/README.md
  • .claude/skills/agnxi-search/SKILL.md
  • .claude/skills/agnxi-search/search.py

Document


name: agnxi-search description: The official search utility for Agnxi.com - The premier directory of AI Agent Tools, MCP Servers, and Skills. author: Agnxi version: 1.1.0 tags: [search, tools, mcp, skills, directory, discovery]

Agnxi Search Skill

This skill provides direct access to the Agnxi.com database, allowing agents to autonomously discover and retrieve information about thousands of curated tools, MCP servers, and coding capabilities.

Capabilities

  • Skill Discovery: Find specific agent skills (e.g., "browser automation", "pdf parsing").
  • MCP Server Lookup: Locate Model Context Protocol servers to extend agent capabilities.
  • Tool Retrieval: Direct links to tool documentation and repositories.

Tools

search_agnxi

Performs a keyword search against the Agnxi sitemap index to find relevant resources.

Parameters:

  • query (string, required): The search keywords (e.g., "browser use", "postgres mcp", "text to speech").

Usage Implementation:

Note: This tool runs a local Python script to query the live sitemap, ensuring up-to-date results without API keys.

python3 search.py "{{query}}"

Best Practices for Agents

  1. Search Broadly: If specific terms yield no results, try broader categories (e.g., instead of "PyPDF2", search "PDF").
  2. Verify Links: The tool returns direct URLs. Always verify the content matches the user's need.
  3. Cross-Reference: Use this skill to find the name of a tool, then use your browser or github skills to fetch specific documentation if needed.

Trustgrade B

  • passBody integrity

    Whether the stored document is plausibly the kind of file the artifact declares, rather than something fetched by mistake.

  • passType matchnot applicable to this artifact type

    Whether the artifact is really the kind of thing its metadata claims it is.

  • passFreshness

    How long since the source repository was last pushed to.

  • passPrompt injection

    Scans the artifact's own text for instructions aimed at your agent rather than at you.

  • warnLicenseno SPDX license detected

    Whether the source repository declares an SPDX license permissive enough to redistribute.

How the grade is calculated

Each check contributes 0 points when it passes, 1 when it warns, and 2 when it fails. The total maps to a letter:

  • Aevery check passed
  • Bone warning
  • Ctwo warnings
  • Dprompt injection or body integrity failed, or three warnings
  • Fone of those failed, and something else is wrong

These are automated hygiene checks, not a security audit, and not a dependency or vulnerability scan. A grade of A means nothing was flagged — not that the artifact is safe.

Versions

  • git-6a844fca89c52026-07-31