Skip to main content
Glama

premium_agents_directory

Browse and filter an enriched AI agents catalog with live operational status, recent news, traffic data, pricing, and trending scores. Sort by trending, price, or news count. Costs 1 credit.

Instructions

Enriched AI agents catalog joined with live status, recent news, agent traffic, flagship pricing, and a 0-100 trending_score. Costs 1 credit.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
categoryNocoding, research, general, creative, frameworks
statusNo
open_sourceNo
sortNo
limitNo

Implementation Reference

  • The MCP server tool registration and handler for 'premium_agents_directory'. Defines the tool with Zod schema for inputs (category, status, open_source, sort, limit), builds query params, calls fetchJSON to GET /premium/agents/directory, and formats the response as text content.
    // ── Tool: premium_agents_directory (1 credit) ───────────────────────
    
    server.tool(
      'premium_agents_directory',
      'Enriched AI agents catalog joined with live status, recent news, agent traffic, flagship pricing, and a 0-100 trending_score. Costs 1 credit.',
      {
        category: z.string().optional().describe('coding, research, general, creative, frameworks'),
        status: z.enum(['operational', 'degraded', 'down', 'unknown']).optional(),
        open_source: z.boolean().optional(),
        sort: z.enum(['trending', 'alphabetical', 'status', 'price_low', 'price_high', 'news_count']).optional(),
        limit: z.number().min(1).max(100).optional(),
      },
      async ({ category, status, open_source, sort, limit }) => {
        const params = new URLSearchParams();
        if (category) params.set('category', category);
        if (status) params.set('status', status);
        if (typeof open_source === 'boolean') params.set('open_source', String(open_source));
        if (sort) params.set('sort', sort);
        if (typeof limit === 'number') params.set('limit', String(limit));
        const data = (await fetchJSON(`/premium/agents/directory?${params}`, { auth: true })) as {
          total: number;
          returned: number;
          sort: string;
          agents: {
            id: string;
            name: string;
            provider: string;
            category: string;
            live_status: string;
            recent_news_count: number;
            flagship_pricing: { model: string; blended: number } | null;
            trending_score: number;
          }[];
          billing?: { credits_remaining?: number };
        };
        const list = data.agents
          .map(
            a =>
              `  ${a.name} (${a.provider}) [${a.category}] status=${a.live_status} score=${a.trending_score} news=${a.recent_news_count}` +
              (a.flagship_pricing ? ` flagship=${a.flagship_pricing.model} $${a.flagship_pricing.blended}/1M` : ''),
          )
          .join('\n');
        return {
          content: [
            {
              type: 'text' as const,
              text: `Agents (sort: ${data.sort}, ${data.returned} of ${data.total}):\n\n${list}\n\nCredits remaining: ${data.billing?.credits_remaining ?? '?'}`,
            },
          ],
        };
      },
    );
  • Tool registered via server.tool('premium_agents_directory', ...) on the McpServer instance. This is the registration point that makes the tool available in the MCP protocol.
    // ── Tool: premium_agents_directory (1 credit) ───────────────────────
    
    server.tool(
      'premium_agents_directory',
      'Enriched AI agents catalog joined with live status, recent news, agent traffic, flagship pricing, and a 0-100 trending_score. Costs 1 credit.',
      {
        category: z.string().optional().describe('coding, research, general, creative, frameworks'),
        status: z.enum(['operational', 'degraded', 'down', 'unknown']).optional(),
        open_source: z.boolean().optional(),
        sort: z.enum(['trending', 'alphabetical', 'status', 'price_low', 'price_high', 'news_count']).optional(),
        limit: z.number().min(1).max(100).optional(),
      },
      async ({ category, status, open_source, sort, limit }) => {
        const params = new URLSearchParams();
        if (category) params.set('category', category);
        if (status) params.set('status', status);
        if (typeof open_source === 'boolean') params.set('open_source', String(open_source));
        if (sort) params.set('sort', sort);
        if (typeof limit === 'number') params.set('limit', String(limit));
        const data = (await fetchJSON(`/premium/agents/directory?${params}`, { auth: true })) as {
          total: number;
          returned: number;
          sort: string;
          agents: {
            id: string;
            name: string;
            provider: string;
            category: string;
            live_status: string;
            recent_news_count: number;
            flagship_pricing: { model: string; blended: number } | null;
            trending_score: number;
          }[];
          billing?: { credits_remaining?: number };
        };
        const list = data.agents
          .map(
            a =>
              `  ${a.name} (${a.provider}) [${a.category}] status=${a.live_status} score=${a.trending_score} news=${a.recent_news_count}` +
              (a.flagship_pricing ? ` flagship=${a.flagship_pricing.model} $${a.flagship_pricing.blended}/1M` : ''),
          )
          .join('\n');
        return {
          content: [
            {
              type: 'text' as const,
              text: `Agents (sort: ${data.sort}, ${data.returned} of ${data.total}):\n\n${list}\n\nCredits remaining: ${data.billing?.credits_remaining ?? '?'}`,
            },
          ],
        };
      },
    );
  • TypeScript type definitions for the API response types: EnrichedAgentRecord, AgentsDirectorySort, and PremiumAgentsDirectoryResponse. Defines the shape of the enriched agent records with fields like live_status, flagship_pricing, trending_score, etc.
    export interface EnrichedAgentRecord {
      id: string;
      name: string;
      provider: string;
      category: string;
      description: string;
      url: string;
      pricing?: string;
      launched?: number | string;
      capabilities?: string[];
      openSource?: boolean;
      live_status: 'operational' | 'degraded' | 'down' | 'unknown';
      status_page_url: string | null;
      recent_news_count: number;
      recent_news: { title: string; url: string; published_at: string; source: string }[];
      agent_traffic_24h: number;
      flagship_pricing: { model: string; input: number; output: number; blended: number } | null;
      trending_score: number;
    }
  • JavaScript SDK client method premiumAgentsDirectory(). Wraps the GET /premium/agents/directory endpoint with parameter building and token requirement. Provides typed access to the premium agents directory API.
    async premiumAgentsDirectory(options?: {
      category?: string;
      status?: 'operational' | 'degraded' | 'down' | 'unknown';
      openSource?: boolean;
      capability?: string;
      sort?: AgentsDirectorySort;
      limit?: number;
    }): Promise<PremiumAgentsDirectoryResponse> {
      this.requireToken('premiumAgentsDirectory');
      const params: Record<string, unknown> = {
        category: options?.category,
        status: options?.status,
        capability: options?.capability,
        sort: options?.sort,
        limit: options?.limit,
      };
      if (options?.openSource === true) params.open_source = 'true';
      else if (options?.openSource === false) params.open_source = 'false';
      return this.request<PremiumAgentsDirectoryResponse>('GET', '/premium/agents/directory', {
        params,
        requireToken: true,
      });
  • Python SDK client method premium_agents_directory(). Wraps the GET /premium/agents/directory endpoint with parameter building and token requirement. Python equivalent of the JS SDK method.
    def premium_agents_directory(
        self,
        *,
        category: str | None = None,
        status: str | None = None,
        open_source: bool | None = None,
        capability: str | None = None,
        sort: str | None = None,
        limit: int | None = None,
    ) -> dict[str, Any]:
        """Enriched agents directory: catalog joined with live signals.
    
        Costs 1 credit per call. Each agent record includes ``live_status``,
        ``status_page_url``, ``recent_news_count``, ``recent_news`` (top 3),
        ``agent_traffic_24h``, ``flagship_pricing`` (with blended $/1M),
        and a derived ``trending_score`` (0-100).
    
        Args:
            category: Filter to one category id (e.g. "coding", "research",
                "general", "creative", "frameworks").
            status: Filter to one live status: "operational", "degraded",
                "down", or "unknown".
            open_source: True for OSS-only, False for closed-only.
            capability: Substring match against an agent's capabilities tags.
            sort: One of "trending" (default), "alphabetical", "status",
                "price_low", "price_high", "news_count".
            limit: Max records to return (1-100, default 50).
    
        Returns:
            Dict with ``agents`` (list), ``total``, ``returned``,
            ``filters_applied``, ``sort``, ``data_freshness``, and ``billing``.
    
        Raises:
            ValueError: if no token is set on the client
            PaymentRequired: if the token has insufficient credits
        """
        self._require_token("premium_agents_directory")
        params: dict[str, Any] = {}
        if category is not None:
            params["category"] = category
        if status is not None:
            params["status"] = status
        if open_source is True:
            params["open_source"] = "true"
        elif open_source is False:
            params["open_source"] = "false"
        if capability is not None:
            params["capability"] = capability
        if sort is not None:
            params["sort"] = sort
        if limit is not None:
            params["limit"] = limit
        return self._request(
            "GET", "/premium/agents/directory", params=params, require_token=True,
        )
Behavior2/5

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

No annotations are present, so the description carries full weight. It mentions a cost of 1 credit, which is a behavioral trait, but lacks details on auth, rate limits, data freshness, or pagination. Without annotations, this is insufficient.

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

Conciseness4/5

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

The description is a single sentence that is concise and front-loaded with key value. However, it could be more structured to list data fields or parameters. Still, it avoids unnecessary details.

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

Completeness2/5

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

No output schema exists, and the description does not explain the return format or what 'trending_score' means beyond a range. Given the tool's complexity (5 params, composite data), more completeness is needed.

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

Parameters2/5

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

Schema description coverage is only 20% (only category has a description). The description does not explain parameters like status, open_source, sort, or limit beyond what the schema provides. No compensation for low coverage.

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 it is an 'Enriched AI agents catalog' with specific data joins (status, news, traffic, pricing, trending_score). This differentiates it from sibling tools like get_ai_news or get_ai_status which provide only individual data types.

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

Usage Guidelines3/5

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

The description implies usage for a comprehensive catalog but does not explicitly state when to use this tool versus siblings. No guidance on alternatives or when not to use it.

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/RipperMercs/tensorfeed'

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