Skip to main content
Glama

browse_agents

Browse registered AI agents with filtering by category and sorting options to find suitable agents for specific tasks.

Instructions

Browse registered agents with optional category filter and sorting.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
categoryNoFilter by category
sortNoSort orderendorsements
limitNoMax results (1-100)

Implementation Reference

  • The actual database query implementation for browsing agents.
    function browseAgents({ category, sort = 'endorsements', limit = 20, offset = 0 } = {}) {
      cleanupExpired();
      const db = getDb();
      const params = [];
      let sql = "SELECT * FROM agents WHERE status = 'active'";
    
      if (category) {
        sql += ' AND category = ?';
        params.push(category);
      }
    
      const sortMap = {
        endorsements: 'endorsement_count DESC',
        newest: 'registered_at DESC',
        name: 'name ASC',
        reputation: 'endorsement_count DESC', // fallback — true reputation sort done in-memory
      };
      sql += ` ORDER BY ${sortMap[sort] || sortMap.endorsements} LIMIT ? OFFSET ?`;
      params.push(Math.min(limit, 100), offset);
    
      const agents = db.prepare(sql).all(...params).map(parseAgent);
    
      // Count total active agents (for pagination / accurate display)
      let countSql = "SELECT COUNT(*) as total FROM agents WHERE status = 'active'";
      const countParams = [];
      if (category) {
        countSql += ' AND category = ?';
  • MCP tool registration and request handler for 'browse_agents'.
    server.tool(
      'browse_agents',
      'Browse registered agents with optional category filter and sorting.',
      {
        category: z.string().optional().describe('Filter by category'),
        sort: z.enum(['endorsements', 'newest', 'name', 'reputation']).optional().default('endorsements').describe('Sort order'),
        limit: z.number().int().min(1).max(100).optional().default(10).describe('Max results (1-100)'),
      },
      async ({ category, sort, limit }) => {
        const { agents, total } = queries.browseAgents({ category, sort, limit: limit || 10 });
        const results = agents.map(a => ({
          id: a.id,
          name: a.name,
          category: a.category,
          endorsement_count: a.endorsement_count,
          reputation: a.reputation || computeReputation(a.id),
          registered_at: a.registered_at,
        }));
    
        return {
          content: [{ type: 'text', text: JSON.stringify({ agents: results, count: results.length, total }, null, 2) }],
Behavior2/5

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

No annotations provided, so description carries full disclosure burden. While 'Browse' implies a read operation, the description fails to specify what data is returned (full records vs summaries), whether results are paginated beyond the limit parameter, or any rate-limiting considerations.

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?

Single sentence efficiently conveys core functionality without redundancy. Front-loaded with verb 'Browse', no filler words, and appropriate length for the parameter complexity.

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

Completeness3/5

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

Minimally adequate for a three-parameter tool with simple types. However, given the rich ecosystem of similar tools (search_agents, get_agent, get_leaderboard) and lack of output schema, the description lacks necessary context about result structure and ecosystem positioning.

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

Parameters3/5

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

Schema coverage is 100% with clear parameter descriptions. The tool description mentions 'optional category filter' and 'sorting' which correspond directly to schema fields, adding no additional semantic depth (e.g., valid category values, sorting direction implications). Baseline 3 is appropriate given schema completeness.

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

Purpose4/5

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

States specific action ('Browse') and resource ('registered agents') along with capabilities ('category filter and sorting'). However, it fails to differentiate from sibling 'search_agents', leaving ambiguity about when to browse versus search.

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

Usage Guidelines2/5

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

Provides no guidance on when to use this tool versus alternatives like 'search_agents' or 'get_agent'. No mention of prerequisites, expected use cases, or when browsing is preferred over searching.

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/vinaybhosle/agentstamp'

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