Skip to main content
Glama

trust_network

Analyze network-wide trust statistics for AI agents, including total agents, stamps, endorsements, and reputation scores to provide social proof for the AgentStamp ecosystem.

Instructions

Network-wide trust statistics: total agents, stamps, endorsements, wishes, average reputation, top categories. Social proof for the AgentStamp network.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • The tool 'trust_network' is registered and implemented directly within src/mcp-server.js. It queries the SQLite database for agent, stamp, endorsement, and wish statistics.
    server.tool(
      'trust_network',
      'Network-wide trust statistics: total agents, stamps, endorsements, wishes, average reputation, top categories. Social proof for the AgentStamp network.',
      {},
      async () => {
        const { getDb } = require('./database');
        const db = getDb();
    
        const agents = db.prepare("SELECT COUNT(*) as count FROM agents WHERE status = 'active'").get();
        const stamps = db.prepare("SELECT COUNT(*) as count FROM stamps WHERE revoked = 0 AND expires_at > datetime('now')").get();
        const endorsements = db.prepare('SELECT COUNT(*) as count FROM endorsements').get();
        const wishes = db.prepare('SELECT COUNT(*) as count FROM wishes').get();
        const wishesGranted = db.prepare('SELECT COUNT(*) as count FROM wishes WHERE granted = 1').get();
    
        const topCategories = db.prepare(
          "SELECT category, COUNT(*) as count FROM agents WHERE status = 'active' AND category IS NOT NULL GROUP BY category ORDER BY count DESC LIMIT 5"
        ).all();
    
        return {
          content: [{ type: 'text', text: JSON.stringify({
            network: {
              active_agents: agents.count,
              active_stamps: stamps.count,
              total_endorsements: endorsements.count,
              total_wishes: wishes.count,
              wishes_granted: wishesGranted.count,
            },
            top_categories: topCategories,
            message: `${agents.count} agents trust AgentStamp. Join them.`,
            register_url: 'https://agentstamp.org/register',
          }, null, 2) }],
        };
      }
    );
    
    // --- Tool: bridge_erc8004_lookup ---
    server.tool(
      'bridge_erc8004_lookup',
      'Look up an ERC-8004 on-chain agent and get their AgentStamp trust score. Free. Returns on-chain identity + trust verdict.',
Behavior3/5

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

No annotations are provided, so the description carries full burden. It discloses return value semantics by listing the specific statistics fields (agents, stamps, endorsements, etc.), which compensates for the missing output schema. However, it lacks operational details such as read-only nature, authentication requirements, or data freshness/caching behavior.

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 sentence front-loads the core value proposition (network-wide statistics) and enumerates the data fields. The second sentence adds domain context ('Social proof for the AgentStamp network'). Every word earns its place.

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?

Given the tool has no parameters and no output schema, the description adequately compensates by enumerating the specific return values (agents, stamps, categories, etc.). For a simple statistics endpoint, this is sufficient, though explicit mention of read-only behavior would improve completeness given the lack of annotations.

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?

With zero parameters, the baseline score is 4. The description correctly implies no filtering is available (network-wide scope) and does not need to compensate for missing schema documentation since there are no parameters to document.

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 uses specific verb+resource ('Network-wide trust statistics') and lists exact metrics returned (agents, stamps, endorsements, wishes, reputation, categories). The 'Network-wide' scope clearly distinguishes it from sibling tools like get_agent, trust_check, and trust_compare which handle individual records or pairwise relationships.

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 'Network-wide' qualifier implies usage context (aggregate data vs individual lookups), distinguishing it from siblings like get_agent or trust_check. However, there is no explicit 'when to use' guidance or named alternatives (e.g., 'for individual agent trust, use X instead').

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