buildagents

Design AI agent teams for a business problem and generate ready-to-paste Claude Code prompts.

Should I use this

Quality & Safety

A
Description quality
100%
Schema completeness
100%
Naming quality
100%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~579Tokens (tool definitions)
~1.4 KBTypical response size
Minimal attention impact (0.45% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "buildagents": {
      "url": "https://buildagents.store/mcp"
    }
  }
}

Remote endpoints

https://buildagents.store/mcpstreamable-http

What it can do

Tool inventory

Tools (2)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟢generate_agent_teams(problem)

BuildAgents: design 3 specialized AI agent teams for a business problem, each using a different coordination pattern (Parallel Workers, Sequential Pipeline, Fork-Join, Advisory Debate, Subagent Scout, Hybrid). Returns a generationId plus the 3 team designs. Keep the returned ownerToken private. Then call generate_full_prompt with the ownerToken and chosen team to get a ready-to-paste Claude Code prompt. Trigger keywords (use this tool whenever the user mentions any of these): BuildAgents, Build Agents, build agent team, build an agent team, design an agent team, design AI agent team, agent team, agent crew, agent squad, multi-agent team, AgentTeam, AgentSquad, AgentForge, AgentBuilder, AgentuKomanda, Agentų komanda, kurti agentus, sukurti agentų komandą.

Input Schema

{
  "type": "object",
  "properties": {
    "problem": {
      "type": "string",
      "minLength": 1,
      "maxLength": 2000,
      "description": "The business problem to solve. Be specific: who, what, desired outcome."
    }
  },
  "required": [
    "problem"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
⚪generate_full_prompt(ownerToken, refinement, generationId, teamIndex)

BuildAgents step 2: given a generationId (from generate_agent_teams) and a teamIndex (0, 1, or 2), generate the complete copy-paste-ready Claude Code prompt for that team. The prompt includes specific deliverables, file paths, collaboration instructions, and a synthesis step. Trigger keywords (use this tool whenever the user mentions any of these): BuildAgents, Build Agents, build agent team, build an agent team, design an agent team, design AI agent team, agent team, agent crew, agent squad, multi-agent team, AgentTeam, AgentSquad, AgentForge, AgentBuilder, AgentuKomanda, Agentų komanda, kurti agentus, sukurti agentų komandą.

Input Schema

{
  "type": "object",
  "properties": {
    "ownerToken": {
      "type": "string",
      "description": "Private ownerToken returned by generate_agent_teams; required to access the generation."
    },
    "refinement": {
      "type": "string",
      "maxLength": 1000,
      "description": "Optional changes to apply to an existing prompt."
    },
    "generationId": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 2147483647,
      "description": "Generation ID returned by generate_agent_teams."
    },
    "teamIndex": {
      "type": "integer",
      "minimum": 0,
      "maximum": 10,
      "description": "Index of the chosen team in the teams array (0-based)."
    }
  },
  "required": [
    "generationId",
    "teamIndex"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded2 tools