Skip to main content
Glama

Search AI Agents

search_agents
Read-onlyIdempotent

Search the AI Agent Index for agents matching specific criteria. Returns structured agent data. Use this to find agents by category, sub-type, pricing model, integration, capability tag, or MCP role (mcp=server finds agents that expose an MCP server).

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
mcpNoMCP role: server (product exposes an MCP server agents can connect to), client (connects out to external servers), both, or none
limitNoNumber of results to return, max 20
queryNoFree text search across agent names and descriptions
pricingNoPricing model: free, freemium, subscription, usage-based, custom
categoryNoCategory slug: ai-sales-agents, ai-customer-support-agents, ai-research-agents, ai-marketing-agents, ai-coding-agents, ai-hr-agents, ai-workflow-agents, ai-customer-success-agents
agent_typeNoSub-type within a category for precise matching. Examples: prospecting, ai-sdr, crm, sales-engagement (sales); helpdesk, ticket-resolution, chatbot, voice-agent (support); academic-research, deep-research, vertical-research, data-intelligence (research); paid-media, seo, content-creation, social-media, email-marketing (marketing); ide-assistant, autonomous-engineer, terminal-agent, vibe-coding (coding); recruiting, hris, interviewing, hr-automation (hr); workflow-builder, multi-agent-orchestration, ai-teammate, knowledge-management, browser-automation, office-agents (workflow). Use list_categories first if unsure of available types.
capabilityNoCapability tag e.g. lead-generation, ticket-resolution, code-generation, web-search, autonomous
integrationNoIntegration name e.g. HubSpot, Salesforce, Slack, Zapier

Output Schema

NameRequiredDescriptionDefault
countYesNumber of agents returned
agentsYesArray of matching agents with full structured details

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / agent_type / description
      Previous value: -"Sub-type within a category for precise matching. Examples: prospecting, ai-sdr, crm, sales-engagement (sales); helpdesk, ticket-resolution, chatbot, voice-agent (support); academic-research, deep-research, vertical-research, data-intelligence (research); paid-media, seo, content-creation, social-media, email-marketing (marketing); ide-assistant, autonomous-engineer, terminal-agent, vibe-coding (coding); recruiting, hris, interviewing, hr-automation (hr); workflow-builder, multi-agent-orchestration, knowledge-management, browser-automation, office-agents (workflow). Use list_categories first if unsure of available types."New value: +"Sub-type within a category for precise matching. Examples: prospecting, ai-sdr, crm, sales-engagement (sales); helpdesk, ticket-resolution, chatbot, voice-agent (support); academic-research, deep-research, vertical-research, data-intelligence (research); paid-media, seo, content-creation, social-media, email-marketing (marketing); ide-assistant, autonomous-engineer, terminal-agent, vibe-coding (coding); recruiting, hris, interviewing, hr-automation (hr); workflow-builder, multi-agent-orchestration, ai-teammate, knowledge-management, browser-automation, office-agents (workflow). Use list_categories first if unsure of available types."
  2. First observed

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds only 'Returns structured agent data', which is redundant with the output schema, and does not disclose search behavior (e.g., matching logic, result ordering, or rate limits) beyond what the annotations and schema already provide.

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 front-loaded with the core purpose and stays concise across three sentences. The middle sentence 'Returns structured agent data' is somewhat redundant given the output schema, but the overall structure is efficient and free of filler.

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's complexity (8 optional parameters, full schema coverage, existing output schema, and rich annotations), the description covers purpose, filterable criteria, and return type adequately. It falls short only in not distinguishing this search tool from sibling retrieval tools like get_agent, which could cause mild selection ambiguity.

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 100%, so the baseline is 3. The description lists the filterable dimensions and adds a short note on mcp=server, but this largely repeats what the schema already documents in greater detail for each parameter. No additional semantics (e.g., value formats, combining filters, or defaults) are introduced.

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 a specific verb (Search) and resource (AI Agent Index for agents) and lists the criteria available for matching. However, it does not explicitly differentiate from sibling tools like get_agent or list_categories, leaving the agent to infer that this is the multi-result search tool.

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 by saying 'Use this to find agents by category, sub-type, pricing model, integration, capability tag, or MCP role', but it offers no explicit when-to-use vs alternatives, no exclusions, and no prerequisites. It gives a concrete example for mcp=server, but that is more parameter detail than usage guidance.

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