Skip to main content
Glama

Search agents

search_agents
Read-onlyIdempotent

Search the lcas directory of ERC-8004 agents. Returns newest first, one entry per group of copies, with which service types passed lcas's last check. Use get_agent for full details.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_agents"
  }
}

Input Schema

NameRequiredDescriptionDefault
chainNoChain ID: 1 = Ethereum, 8453 = Base. Omit for both.
limitNo
moneyNoMoney hint: moves = a tool or skill says it moves funds (transfer, swap, trade, ...); pays = asks the caller for payment (x402 or HTTP 402); reads = prices, balances, tokenized assets. Word matches, not verified.
queryNoWords to match in names, descriptions, MCP tool names and A2A skill names. Omit to list all.
cursorNonext_cursor from the previous page.
serviceNoOnly agents that declare this service type.
steady_onlyNoOnly steady agents: the same owner wallet for at least 90 days, and an MCP, A2A or web endpoint that lcas checked on at least 30 days and found working on at least 90% of them.
tested_onlyNoOnly agents whose last weekly live test passed: lcas called one read-only MCP tool or sent one A2A skill example and got an answer.
working_onlyNoOnly agents whose MCP, A2A or web endpoint passed its last check (of `service`, if set). OASF is a description, never checked.
tool_findingsNoTool-poisoning scan of tools' own text (instruction phrasing aimed at the reading app, invisible Unicode, asks for secrets or to send data out, orders about other tools). exclude = hide matches, only = show only matches. Patterns catch lazy attacks only.
in_mcp_registryNoOnly agents with an MCP endpoint listed (same remote URL) in the official MCP Registry. The registry verifies the publisher's namespace, not who runs the URL.
domain_proved_onlyNoOnly agents with a working endpoint whose domain names the agent in /.well-known/agent-registration.json (ERC-8004's optional domain proof). Shows the domain's owner agrees; no signature is checked.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / domain_proved_only
      Added value: +{
      +  "default": false,
      +  "description": "Only agents with a working endpoint whose domain names the agent in /.well-known/agent-registration.json (ERC-8004's optional domain proof). Shows the domain's owner agrees; no signature is checked.",
      +  "type": "boolean"
      +}
  2. Changed1 schema field changed
    • addedInput schema / properties / steady_only
      Added value: +{
      +  "default": false,
      +  "description": "Only steady agents: the same owner wallet for at least 90 days, and an MCP, A2A or web endpoint that lcas checked on at least 30 days and found working on at least 90% of them.",
      +  "type": "boolean"
      +}
  3. Changed1 schema field changed
    • addedInput schema / properties / in_mcp_registry
      Added value: +{
      +  "default": false,
      +  "description": "Only agents with an MCP endpoint listed (same remote URL) in the official MCP Registry. The registry verifies the publisher's namespace, not who runs the URL.",
      +  "type": "boolean"
      +}
  4. Changed1 schema field changed
    • addedInput schema / properties / tool_findings
      Added value: +{
      +  "description": "Tool-poisoning scan of tools' own text (instruction phrasing aimed at the reading app, invisible Unicode, asks for secrets or to send data out, orders about other tools). exclude = hide matches, only = show only matches. Patterns catch lazy attacks only.",
      +  "enum": [
      +    "exclude",
      +    "only"
      +  ],
      +  "type": "string"
      +}
  5. Changed1 schema field changed
    • addedInput schema / properties / tested_only
      Added value: +{
      +  "default": false,
      +  "description": "Only agents whose last weekly live test passed: lcas called one read-only MCP tool or sent one A2A skill example and got an answer.",
      +  "type": "boolean"
      +}
  6. Changed1 schema field changed
    • addedInput schema / properties / money
      Added value: +{
      +  "description": "Money hint: moves = a tool or skill says it moves funds (transfer, swap, trade, ...); pays = asks the caller for payment (x402 or HTTP 402); reads = prices, balances, tokenized assets. Word matches, not verified.",
      +  "enum": [
      +    "moves",
      +    "pays",
      +    "reads"
      +  ],
      +  "type": "string"
      +}
  7. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, and the description is consistent with that. It adds real behavioral context beyond the annotations: result ordering (newest first), de-duplication into copy groups, and the fact that service-type status reflects lcas's last check. It doesn't cover result size or empty-result behavior, keeping it below a 5.

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?

Three short sentences, all load-bearing: purpose, return semantics, and the handoff to get_agent. Nothing is repeated from the schema and the routing hint is placed last where it belongs.

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 12-parameter, fully-optional filter tool with no output schema, the description adequately frames what comes back (ordering, grouping, service-type status) and where to get more. It could say more about pagination via cursor or what an empty result means, but nothing essential is missing to call it correctly.

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 description coverage is 92%, and the per-parameter text is unusually detailed (e.g. money, steady_only, tool_findings all explain their semantics and limitations). The description itself adds no parameter-level meaning, so the baseline of 3 is appropriate — the schema does the work.

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?

States a specific verb and resource ("Search the lcas directory of ERC-8004 agents") and adds distinguishing scope: newest-first ordering, one entry per group of copies, and per-entry service-type status. It explicitly separates itself from get_agent, so an agent can choose between search and detail lookup without inspecting schemas.

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 names one clear alternative with its condition ("Use get_agent for full details"), which is the main routing decision an agent faces here. It does not address the other siblings (check_agent, find_tools, directory_status), so the guidance is clear but not exhaustive.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources