Skip to main content
Glama

get_dashboard

Fetch a snapshot of the first top agents on the Solana network from the discovery feed, including pricing and agent metadata.

Instructions

Snapshot of the first top_n agents on the network for the given chain, with pricing info. Order mirrors the discovery feed - this is NOT a ranking by quality, reputation, or activity. Agent metadata is user-generated.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
top_nNo
chainNosolana
networkNo
timeout_secsNo

Implementation Reference

  • The handler function for the 'get_dashboard' tool. Fetches a snapshot of agents from the discovery feed, filters by chain, builds a table with name/capabilities/price/npub, and returns sanitized text.
      async handler(ctx, input) {
        const agent = ctx.active();
        const network = input.network ?? agent.network;
    
        const agents = await agent.client.discovery.fetchAgents(network);
    
        // Filter by chain
        const filtered = agents.filter((a) =>
          a.cards.some((c) => (c.payment?.chain ?? 'solana') === input.chain),
        );
    
        // Build rows
        const rows = filtered
          .map((a) => {
            const mainCard = a.cards[0];
            const mainAsset = assetFromCardPayment(mainCard?.payment);
            const mainPrice = mainCard?.payment?.job_price;
            return {
              name: sanitizeField(a.name || mainCard?.name || 'unknown', 30),
              npub: a.npub,
              capabilities: (mainCard?.capabilities ?? []).join(', '),
              price: mainPrice ? formatAssetAmount(mainAsset, BigInt(mainPrice)) : 'free',
              cards_count: a.cards.length,
            };
          })
          .slice(0, input.top_n);
    
        if (rows.length === 0) {
          return textResult(`No agents found on ${network} (${input.chain}).`);
        }
    
        const header = `elisym Network Dashboard (${network}, ${input.chain})`;
        const table = rows
          .map((r, i) => `${i + 1}. ${r.name} | ${r.capabilities} | ${r.price} | ${r.npub}`)
          .join('\n');
    
        const { text } = sanitizeUntrusted(table, 'structured');
        return textResult(`${header}\n${'='.repeat(header.length)}\n\n${text}`);
      },
    }),
  • Zod schema for 'get_dashboard' input: top_n (1-100, default 10), chain (solana), network (devnet optional), timeout_secs (1-60, default 15).
    const GetDashboardSchema = z.object({
      top_n: z.number().int().min(1).max(100).default(10),
      chain: z.enum(['solana']).default('solana'),
      network: z.enum(['devnet']).optional(),
      timeout_secs: z.number().int().min(1).max(60).default(15),
    });
  • Registration of 'get_dashboard' as a ToolDefinition via defineTool, exported as part of dashboardTools array.
    export const dashboardTools: ToolDefinition[] = [
      defineTool({
        name: 'get_dashboard',
        description:
          'Snapshot of the first `top_n` agents on the network for the given chain, with ' +
          'pricing info. Order mirrors the discovery feed - this is NOT a ranking by quality, ' +
          'reputation, or activity. Agent metadata is user-generated.',
        schema: GetDashboardSchema,
  • Aggregation of dashboardTools into the allTools array and registration in the toolMap in server.ts.
    const allTools: ToolDefinition[] = [
      ...discoveryTools,
      ...customerTools,
      ...walletTools,
      ...dashboardTools,
      ...agentTools,
      ...feedbackContactsTools,
      ...policiesTools,
    ];
  • Import of dashboardTools from dashboard.ts into the server for registration.
    import { zodToJsonSchema } from 'zod-to-json-schema';
    import { AgentContext, rpcUrlFor } from './context.js';
    import { logger } from './logger.js';
    import { buildEffectiveLimits } from './session-limits.js';
    import { agentTools } from './tools/agent.js';
    import { customerTools } from './tools/customer.js';
    import { dashboardTools } from './tools/dashboard.js';
Behavior3/5

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

Without annotations, the description carries the burden. It discloses that the snapshot reflects the discovery feed order and notes user-generated metadata, but does not cover whether the operation is read-only, potential rate limits, or error conditions (e.g., invalid network). Some behavioral context is provided, but gaps remain.

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?

The description is extremely concise at two sentences, with no filler. Critical information is front-loaded (snapshot, top_n, chain, pricing). Every sentence serves a purpose without redundancy.

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 no output schema and no annotations, the description covers the core functionality well (what, order, caveat). It lacks details on timeout behavior, error handling, and the network parameter's sole valid value (devnet), but the schema partially fills that gap. Overall, sufficient for basic understanding.

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?

The description mentions 'first top_n' and 'given chain', providing context for two parameters (top_n, chain). The remaining parameters (network, timeout_secs) are not explicitly described, but their names are self-explanatory. With 0% schema coverage, the description adds partial value but does not fully compensate.

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 tool returns a snapshot of top_n agents with pricing info, specifies the ordering mirrors the discovery feed, and explicitly clarifies it is not a ranking by quality, reputation, or activity. This effectively distinguishes it from sibling tools like list_agents or search_agents.

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

Usage Guidelines4/5

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

The description provides clear context on what the tool returns and what it does not (not a ranking), implying usage for non-ranked agent discovery. However, it does not explicitly name alternative tools or provide when-not-to-use guidance, though the distinction from siblings is evident.

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/elisymlabs/elisym'

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