Skip to main content
Glama

skvil_catalog

Browse certified AI agent skills with metadata to discover safe options for installation from the Skvil network's security catalog.

Instructions

Browse the full catalog of Skvil-certified AI agent skills with detailed metadata: author, version, description, provider, agent platform, file count, and install URL. Returns up to 100 skills. Use this to discover safe skills available for installation.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • The skvil_catalog tool registration and handler - defines the tool metadata, empty schema, and the async handler that calls api.catalog() and formats the results for display with skill details including name, level, reputation score, author, version, description, provider, agent, file count, certification date, install URL, and composite hash.
    // ── skvil_catalog ──────────────────────────────────────────────────────────
    server.tool(
      'skvil_catalog',
      'Browse the full catalog of Skvil-certified AI agent skills with detailed ' +
        'metadata: author, version, description, provider, agent platform, file ' +
        'count, and install URL. Returns up to 100 skills. Use this to discover ' +
        'safe skills available for installation.',
      {},
      async () => {
        try {
          const result = await api.catalog();
    
          if (result.length === 0) {
            return {
              content: [
                {
                  type: 'text',
                  text: 'The skill catalog is empty. No certified skills available yet.',
                },
              ],
            };
          }
    
          const lines = [`**Skvil skill catalog** (${result.length} certified skills)\n`];
    
          for (const skill of result) {
            const parts = [`- **${skill.name}**`];
            parts.push(`  Level: ${skill.level} | Score: ${formatScore(skill.reputation_score)} | ${skill.total_scans} scans`);
            if (skill.author) parts.push(`  Author: ${skill.author}`);
            if (skill.version) parts.push(`  Version: ${skill.version}`);
            if (skill.description) parts.push(`  ${skill.description}`);
            if (skill.provider) parts.push(`  Provider: ${skill.provider}`);
            if (skill.agent) parts.push(`  Agent: ${skill.agent}`);
            parts.push(`  Files: ${skill.file_count} | Certified: ${skill.certified_at}`);
            if (skill.skill_url) parts.push(`  Install: ${skill.skill_url}`);
            parts.push(`  Hash: \`${skill.composite_hash}\``);
            lines.push(parts.join('\n'));
          }
    
          return { content: [{ type: 'text', text: lines.join('\n\n') }] };
        } catch (error) {
          return {
            content: [{ type: 'text', text: formatError('catalog', error) }],
            isError: true,
          };
        }
      },
    );
  • src/tools.ts:197-204 (registration)
    Tool registration call - registers 'skvil_catalog' with MCP server using server.tool(), providing name, description, empty schema object, and handler function.
    server.tool(
      'skvil_catalog',
      'Browse the full catalog of Skvil-certified AI agent skills with detailed ' +
        'metadata: author, version, description, provider, agent platform, file ' +
        'count, and install URL. Returns up to 100 skills. Use this to discover ' +
        'safe skills available for installation.',
      {},
      async () => {
  • API function that implements the catalog endpoint - makes a GET request to '/catalog' and returns array of CatalogSkill objects with full metadata.
    export async function catalog(): Promise<CatalogSkill[]> {
      return request<CatalogSkill[]>('GET', '/catalog');
    }
  • Type definition for CatalogSkill - defines the structure of catalog data including name, composite_hash, level, reputation_score, certified_at, total_scans, skill_url, provider, agent, file_count, author, version, and description fields.
    export interface CatalogSkill {
      name: string;
      composite_hash: string;
      level: 'V1' | 'V2' | 'V3' | 'Gold';
      reputation_score: number;
      certified_at: string;
      total_scans: number;
      skill_url?: string | null;
      provider?: string | null;
      agent?: string | null;
      file_count: number;
      author?: string | null;
      version?: string | null;
      description?: string | null;
    }
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses key behavioral traits: it returns up to 100 skills (a limit), includes metadata fields, and that skills are 'safe' and 'available for installation'. However, it doesn't mention potential rate limits, authentication needs, or error conditions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with zero waste: the first states purpose and scope, the second provides usage guidance. It's front-loaded with the core functionality and efficiently structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter tool with no annotations and no output schema, the description is reasonably complete: it explains what the tool does, what it returns, and when to use it. However, without an output schema, it could benefit from more detail on return format or pagination, though the 'up to 100 skills' limit is helpful.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 0 parameters with 100% coverage, so no parameter documentation is needed. The description appropriately adds no parameter information, maintaining focus on the tool's purpose and behavior. A baseline of 4 is applied for zero-parameter tools.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'browse' and the resource 'full catalog of Skvil-certified AI agent skills', specifying it includes detailed metadata fields. It distinguishes from siblings by focusing on browsing/discovery rather than certification, registration, reporting, scanning, statistics, or verification.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states 'Use this to discover safe skills available for installation', providing clear when-to-use guidance. It implies this is for discovery purposes, distinguishing it from tools that might perform actions like registration or verification.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Skvil-IA/skvil-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server