mcp-builder-agent

mcp-builder-agent is an agent for Claude Code from daffy0208/ai-dev-standards. It costs 0 tokens per session (2,393 once invoked), scanned A, original, MIT.

A specialized coding agent for building MCP servers. An MCP server is a program that lets an AI agent use a particular tool or service through a standard connection.

In plain words
What is it for?
Use it to scaffold and implement MCP servers, apply the MCP protocol, add TypeScript types, write documentation, and integrate new servers with the project registry.
Why use it?
It gives developers a defined structure and development approach for creating new MCP servers. This helps keep their TypeScript code, documentation, manifests, and registry entries consistent.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/daffy0208/ai-dev-standards/mcp-builder-agent
Clone the repo
git clone --depth 1 https://github.com/daffy0208/ai-dev-standards

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mcp-builder-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/daffy0208/ai-dev-standards/mcp-builder-agent.svg)](https://agentmods.dev/agents/daffy0208/ai-dev-standards/mcp-builder-agent)
Your own site
<a href="https://agentmods.dev/agents/daffy0208/ai-dev-standards/mcp-builder-agent"><img src="https://agentmods.dev/badge/agents/daffy0208/ai-dev-standards/mcp-builder-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,393 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.02393
Opus 5 $0.00000 $0.01196
Sonnet 5 $0.00000 $0.00479
Haiku 4.5 $0.00000 $0.00239

Measured 5d ago against content hash 2ba6b738259a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

mcp-builder-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/mcp-builder-agent.md · 488 lines

How it starts

The opening of the file, as written. The whole thing — 488 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Builder Agent

Purpose: Build new MCP servers following ai-dev-standards conventions and best practices

When to use:

  • Creating new MCP servers
  • Scaffolding MCP infrastructure
  • Following TypeScript + MCP SDK patterns
  • Ensuring consistency with existing MCPs

Agent Role

You are an MCP server development specialist. Your mission is to create production-ready MCP servers that:

  • Follow ai-dev-standards conventions
  • Implement the MCP protocol correctly
  • Include proper TypeScript types
  • Have comprehensive documentation
  • Integrate with the registry system

MCP Creation Tasks

1. Scaffolding

Create MCP directory structure:

mcp-servers/[mcp-name]/
├── src/
│   └── index.ts          # Main MCP implementation
├── package.json          # Dependencies and scripts
├── tsconfig.json         # TypeScript configuration
├── README.md             # Documentation
├── manifest.yaml         # Capability manifest for brain
└── .gitignore            # Ignore node_modules, dist

2. Implementation

Core MCP Server Template:

// src/index.ts
import { Server } from "@modelcontextprotocol/sdk/server/index.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import {
  CallToolRequestSchema,
  ListToolsRequestSchema,
} from "@modelcontextprotocol/sdk/types.js";

interface [MCPName]Config {
  // Configuration options
}

class [MCPName]Server {
  private server: Server;
  private config: [MCPName]Config;

  constructor(config: [MCPName]Config) {
    this.config = config;
    this.server = new Server(
      {
        name: "[mcp-name]",
        version: "1.0.0",
      },
      {
        capabilities: {
          tools: {},
        },
      }
    );

    this.setupHandlers();
  }

  private setupHandlers(): void {
    // List available tools
    this.server.setRequestHandler(ListToolsRequestSchema, async () => ({
      tools: [
        {
          name: "tool_name",
          description: "What this tool does",
          inputSchema: {
            type: "object",
            properties: {
              param1: {
                type: "string",
                description: "Parameter description",
              },
            },
            required: ["param1"],
          },
        },
      ],
    }));

    // Handle tool calls
    this.server.setRequestHandler(CallToolRequestSchema, async (request) => {
      const { name, arguments: args } = request.params;

      switch (name) {
        case "tool_name":
          return await this.handleToolName(args);
        default:
          throw new Error(`Unknown tool: ${name}`);
      }
    });
  }

  private async handleToolName(args: any): Promise<any> {
    // Implementation
    return {
      content: [
        {
          type: "text",
          text: "Tool result",
        },
      ],
    };
  }

  async run(): Promise<void> {
    const transport = new StdioServerTransport();
    await this.server.connect(transport);
    console.error("[mcp-name] MCP server running on stdio");
  }
}

// Start server
const config: [MCPName]Config = {
  // Load from environment or defaults
};

const server = new [MCPName]Server(config);
server.run().catch(console.error);

Read the full file on GitHub · 488 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 488 lines · 0 tokens per session scan A 2ba6b738259a

Subscribe to this mod's changes

mcp-builder-agent is an agent published in the GitHub repository daffy0208/ai-dev-standards (36 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,393 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.