Agent skill

MCP Development

by rohitg00 in rohitg00/awesome-claude-code-toolkit

MCP server development including tool design, resource endpoints, prompt templates, and transport configuration

Apache-2.0Auto-check passedAgent Workflows

Install MCP Development

skills CLI
$ npx skills add rohitg00/awesome-claude-code-toolkit --skill mcp-development -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install rohitg00/awesome-claude-code-toolkit mcp-development --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/rohitg00/awesome-claude-code-toolkit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/mcp-development .claude/skills/mcp-development && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
mcp-development
GitHub stars
2.7k
Token cost
~1.2k tokens
SKILL.md length
146 words
Files
1
Skills in repo
37
Repo updated
First seen
Licence
Apache-2.0

At a glance

MCP server development including tool design, resource endpoints, prompt templates, and transport configuration

  • Tasks that involve Prompt engineering
  • SKILL.md covers MCP Server with Tools, Resources, Prompt Templates and Client Configuration, plus 3 more sections
  • Needs MCP_TOKEN
  • Tasks that involve MCP servers

What it does

MCP Development is an agent skill from rohitg00/awesome-claude-code-toolkit. MCP server development including tool design, resource endpoints, prompt templates, and transport configuration

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Prompt engineering and MCP servers. It works with Model Context Protocol. The repository describes itself as: The most comprehensive toolkit for Claude Code -- 135 agents, 35 curated skills, 42 commands, 176+ plugins, 20 hooks, 15 rules, 7 templates, 14 MCP configs, 26 companion apps, 52… The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Prompt engineering
  • Tasks that involve MCP servers

Example prompts

  • “/mcp-development”

Requirements

  • A credential in MCP_TOKEN

What it can do on your machine

Read from SKILL.md and the folder at commit ebdf1d5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are typescript and json).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • MCP_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

MCP Development loads about 1.2k tokens when it runs. Until then it costs about 32 tokens; SKILL.md has 146 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~32
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from rohitg00/awesome-claude-code-toolkit at commit ebdf1d5, republished under its Apache-2.0 licence (© rohitg00). 146 words, ~1,195 tokens.

Download SKILL.mdSave it as .claude/skills/mcp-development/SKILL.md (or your agent's skills folder).
name
mcp-development
description
MCP server development including tool design, resource endpoints, prompt templates, and transport configuration

MCP Development

MCP Server with Tools

typescript
import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import { z } from "zod";

const server = new McpServer({
  name: "project-tools",
  version: "1.0.0",
});

server.tool(
  "search_files",
  "Search for files matching a glob pattern in the project directory",
  {
    pattern: z.string().describe("Glob pattern (e.g., '**/*.ts')"),
    directory: z.string().optional().describe("Base directory to search from"),
  },
  async ({ pattern, directory }) => {
    const files = await glob(pattern, { cwd: directory ?? process.cwd() });
    return {
      content: [
        {
          type: "text",
          text: files.length > 0
            ? files.join("\n")
            : `No files found matching ${pattern}`,
        },
      ],
    };
  }
);

server.tool(
  "run_query",
  "Execute a read-only SQL query against the application database",
  {
    query: z.string().describe("SQL SELECT query to execute"),
    limit: z.number().default(100).describe("Maximum rows to return"),
  },
  async ({ query, limit }) => {
    if (!query.trim().toUpperCase().startsWith("SELECT")) {
      return {
        content: [{ type: "text", text: "Only SELECT queries are allowed" }],
        isError: true,
      };
    }
    const rows = await db.query(`${query} LIMIT ${limit}`);
    return {
      content: [{ type: "text", text: JSON.stringify(rows, null, 2) }],
    };
  }
);

Resources

typescript
server.resource(
  "schema",
  "db://schema",
  "Current database schema with all tables, columns, and relationships",
  async () => {
    const schema = await db.query(`
      SELECT table_name, column_name, data_type, is_nullable
      FROM information_schema.columns
      WHERE table_schema = 'public'
      ORDER BY table_name, ordinal_position
    `);
    return {
      contents: [
        {
          uri: "db://schema",
          mimeType: "application/json",
          text: JSON.stringify(schema, null, 2),
        },
      ],
    };
  }
);

server.resource(
  "config",
  "config://app",
  "Application configuration (secrets redacted)",
  async () => {
    const config = await loadConfig();
    const safe = redactSecrets(config);
    return {
      contents: [
        {
          uri: "config://app",
          mimeType: "application/json",
          text: JSON.stringify(safe, null, 2),
        },
      ],
    };
  }
);

Prompt Templates

typescript
server.prompt(
  "review-code",
  "Review code changes for bugs, security issues, and style",
  {
    diff: z.string().describe("Git diff or code to review"),
    focus: z.enum(["security", "performance", "style", "all"]).default("all"),
  },
  async ({ diff, focus }) => ({
    messages: [
      {
        role: "user",
        content: {
          type: "text",
          text: `Review this code diff. Focus: ${focus}\n\n${diff}`,
        },
      },
    ],
  })
);

Client Configuration

json
{
  "mcpServers": {
    "project-tools": {
      "command": "node",
      "args": ["./mcp-server/dist/index.js"],
      "env": {
        "DATABASE_URL": "postgres://localhost:5432/app"
      }
    },
    "remote-server": {
      "url": "https://mcp.example.com/sse",
      "headers": {
        "Authorization": "Bearer ${MCP_TOKEN}"
      }
    }
  }
}

Transport Setup

typescript
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";

const transport = new StdioServerTransport();
await server.connect(transport);

For HTTP-based servers, use the SSE transport for streaming responses to clients.

Anti-Patterns

  • Creating tools with vague descriptions that don't explain when to use them
  • Not validating inputs with Zod schemas before processing
  • Returning raw error stack traces to the client
  • Missing isError: true flag on error responses
  • Creating too many fine-grained tools instead of composable ones
  • Not redacting secrets in resource responses

Checklist

  • Each tool has a clear description explaining when and why to use it
  • Input parameters validated with Zod schemas and descriptive messages
  • Error responses include isError: true with user-friendly messages
  • Resources expose read-only data with secrets redacted
  • Prompt templates provide structured starting points for common tasks
  • Server handles graceful shutdown on SIGINT/SIGTERM
  • Tools are composable (do one thing well) rather than monolithic
  • Client configuration documented with required environment variables

© rohitg00, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/mcp-development of rohitg00/awesome-claude-code-toolkit.

Open the folder on GitHubat commit ebdf1d5

Compare with similar skills

MCP Development next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

MCP Development compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
MCP Development this skillrohitg00/awesome-claude-code-toolkit2.7k—~1.2kAutomated safety check: PassApache-2.0
Workflow Schema Tuningbreaking-brake/cc-wf-studio5.4k—~1.3kAutomated safety check: PassCustom licence
Add Promptcyanheads/pubmed-mcp-server155—~1.6kAutomated safety check: PassApache-2.0
Spring AI MCP Server Patternsgiuseppe-trisciuoglio/developer-kit3551 repos~2.7kAutomated safety check: NotesMIT
Cco Overheadegorfedorov/claude-context-optimizer114—~606Automated safety check: PassMIT
Agentforce GenerateSalesforceAIResearch/agentforce-adlc1141 repos~7.4kAutomated safety check: PassCustom licence

Similar skills

  • Workflow Schema Tuning

    breaking-brake/cc-wf-studio

    Guides edits to cc-wf-studio's workflow schema so AI agents generate better workflows, treating schema text as prompt engineering rather than validation.

    5.4k GitHub stars~1.3k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Add Prompt

    cyanheads/pubmed-mcp-server

    Scaffold a new MCP prompt template. An agent skill from cyanheads/pubmed-mcp-server.

    155 GitHub stars~1.6k tokensUpdated 4 days ago
    Agent WorkflowsAuto-check passed
  • Spring AI MCP Server Patterns

    giuseppe-trisciuoglio/developer-kit

    Provides Spring Boot MCP server patterns that create Model Context Protocol servers with Spring AI by defining tool handlers, exposing resources, configuring prompt templates, and setting up…

    355 GitHub starsUsed in 1 repo~2.7k tokens
    Agent WorkflowsAuto-check: notes
  • Cco Overhead

    egorfedorov/claude-context-optimizer

    Audit the fixed context overhead every session starts with — system prompt, MCP tools, agents, CLAUDE.md, memory — measured from real transcript usage

    114 GitHub stars~606 tokensUpdated 8 days ago
    Agent WorkflowsAuto-check passed
  • Agentforce Generate

    SalesforceAIResearch/agentforce-adlc

    Build, modify, audit, repair, optimize, debug, and deploy agents with Agentforce Agent Script.

    114 GitHub starsUsed in 1 repo~7.4k tokens
    Agent WorkflowsAuto-check passed
  • Natural

    NPC-Worldwide/npcpy

    Render the provided prompt template with Jinja context and send it to the active NPC's LLM.

    1.5k GitHub stars~161 tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check passed

More from rohitg00/awesome-claude-code-toolkit

All 37 skills in this repo
  • Accessibility Wcag

    rohitg00/awesome-claude-code-toolkit

    Web accessibility patterns for WCAG 2.2 compliance including ARIA, keyboard navigation, screen readers, and testing

    2.7k GitHub stars~1.4k tokensUpdated 4 mo ago
    Auto-check passed
  • API Design Patterns

    rohitg00/awesome-claude-code-toolkit

    REST API design with resource naming, pagination, versioning, and OpenAPI spec generation

    2.7k GitHub stars~1.2k tokensUpdated 4 mo ago
    Auto-check passed
  • Authentication Patterns

    rohitg00/awesome-claude-code-toolkit

    Authentication and authorization patterns including OAuth2, JWT, RBAC, session management, and PKCE flows

    2.7k GitHub stars~1.4k tokensUpdated 4 mo ago
    Auto-check passed
  • AWS Cloud Patterns

    rohitg00/awesome-claude-code-toolkit

    AWS cloud patterns for Lambda, ECS, S3, DynamoDB, and Infrastructure as Code with CDK/Terraform

    2.7k GitHub stars~1.1k tokensUpdated 4 mo ago
    Auto-check passed
  • CI CD Pipelines

    rohitg00/awesome-claude-code-toolkit

    CI/CD pipeline patterns for GitHub Actions, GitLab CI, testing strategies, and deployment automation

    2.7k GitHub stars~1.1k tokensUpdated 4 mo ago
    Auto-check passed
  • Continuous Learning

    rohitg00/awesome-claude-code-toolkit

    Auto-extract patterns from coding sessions, track corrections, and build reusable knowledge with confidence scoring

    2.7k GitHub stars~1.4k tokensUpdated 4 mo ago
    Auto-check passed

Questions about MCP Development

What does MCP Development do?

MCP server development including tool design, resource endpoints, prompt templates, and transport configuration. MCP Development is an agent skill from rohitg00/awesome-claude-code-toolkit.

When should I use MCP Development?

MCP Development fits situations like: tasks that involve Prompt engineering; tasks that involve MCP servers.

How do I install MCP Development in Claude Code?

Run `npx skills add rohitg00/awesome-claude-code-toolkit --skill mcp-development -a claude-code`. Or copy the skill folder (skills/mcp-development in rohitg00/awesome-claude-code-toolkit) into .claude/skills/mcp-development in your project. Claude Code loads it when a task matches its description.

How do I install MCP Development in Codex?

Run `npx skills add rohitg00/awesome-claude-code-toolkit --skill mcp-development -a codex`. Or copy the skill folder (skills/mcp-development in rohitg00/awesome-claude-code-toolkit) into .agents/skills/mcp-development in your project. Codex loads it when a task matches its description.

Can I use MCP Development in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add rohitg00/awesome-claude-code-toolkit --skill mcp-development -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mcp-development, .gemini/skills/mcp-development, .github/skills/mcp-development and .opencode/skills/mcp-development in your project.

What does MCP Development need to run?

Going by SKILL.md and its folder, MCP Development needs credentials named MCP_TOKEN. Our summary lists: A credential in MCP_TOKEN.

Does MCP Development access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is MCP Development safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does MCP Development use?

MCP Development is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does MCP Development use?

About 1.2k tokens (SKILL.md is roughly 4.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to MCP Development?

Skills that share tags, products or a category with MCP Development: Workflow Schema Tuning (breaking-brake/cc-wf-studio, 5.4k stars), Add Prompt (cyanheads/pubmed-mcp-server, 155 stars), Spring AI MCP Server Patterns (giuseppe-trisciuoglio/developer-kit, 355 stars) and Cco Overhead (egorfedorov/claude-context-optimizer, 114 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains MCP Development?

rohitg00 (a GitHub user) maintains it in rohitg00/awesome-claude-code-toolkit, which has 2,685 GitHub stars. The repository holds 37 skills in this directory. The repository was last updated on May 12, 2026.

Source: rohitg00/awesome-claude-code-toolkit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.