Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    MCP Server v2 Production Pack

    1

    Eight agent skills and two scripts that make your AI agent write MCP servers for SDK v2 and spec 2026-07-28: hints, OAuth, security, tests, registry.

    $24

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    MCP Server v2 Production Pack

    MCP Server v2 Production Pack

    Example session with this skill installed

    OpenAI's plugin form rejected our MCP server and a trust index flagged it. Our server has one tool called run that takes a free-form command string and passes it straight to git through a shell, with only readOnlyHint: true set. Fix it.

    • Read your context and instructions
    • Compiled the mcp server v2

    Summary

    The linter found 3 errors and 5 warnings: two missing hints OpenAI requires, a shell-injection parameter, a generic executor and a read-only hint on a tool that can run git push. The agent replaced it with one tool per operation and the rerun is clean.

    Linter, before

    $ node lint-mcp-server.mjs -- node dist/server.js
    server: repo-tools 1.0.0  protocol: 2025-11-25 (legacy)  tools: 1
    ERROR run  risky-shell-param  Parameter "command" looks like free-form shell or code input.
    ERROR run  hint-missing       destructiveHint is not set; OpenAI plugin review requires an explicit boolean.
    ERROR run  hint-missing       openWorldHint is not set; OpenAI plugin review requires an explicit boolean.
    WARN  run  generic-executor   Generic executor name. Expose each operation as its own tool.
    WARN  run  description-weak   Description is 2 word(s).
    WARN  run  param-undocumented Parameters without a description: command.
    WARN  run  hint-missing       idempotentHint is not set.
    WARN  run  hint-mismatch      Name starts with a write verb but readOnlyHint=true.
    3 error(s), 5 warning(s), 2 note(s)
    

    Fixed tool

    const run = promisify(execFile);
    
    server.registerTool(
      'git_log',
      {
        title: 'Git log',
        description: 'List the latest commits on one branch of the configured repository. Returns up to 20 one-line entries. Read-only.',
        inputSchema: z.object({
          branch: z.string().regex(/^[A-Za-z0-9._\/-]{1,100}$/).describe('Branch name, for example main'),
          limit: z.number().int().min(1).max(20).default(10).describe('Number of commits to return')
        }),
        annotations: { readOnlyHint: true, destructiveHint: false, idempotentHint: true, openWorldHint: false }
      },
      async ({ branch, limit }) => {
        if (branch.startsWith('-')) return { content: [{ type: 'text', text: 'Branch names cannot start with "-".' }], isError: true };
        try {
          const { stdout } = await run('git', ['log', '--oneline', '-n', String(limit), branch, '--'], { timeout: 10_000, maxBuffer: 1_000_000 });
          return { content: [{ type: 'text', text: stdout || 'No commits.' }] };
        } catch {
          return { content: [{ type: 'text', text: `Unknown branch "${branch}". Call git_branches to list branches.` }], isError: true };
        }
      }
    );
    

    Linter, after

    server: repo-tools 1.1.0  protocol: 2025-11-25 (legacy)  tools: 1
    INFO  git_log  output-schema-missing  No outputSchema. Add one and return structuredContent when callers need typed results.
    0 error(s), 0 warning(s), 1 note(s)
    

    Both servers were built against @modelcontextprotocol/server 2.3.1 and this is the linter's real output.

    Next steps

    • Add git_branches the same way and server instructions.
    • Add the contract test from mcp-testing so CI fails if any tool loses a hint.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Ask an agent for an MCP server today and you get last year's code: @modelcontextprotocol/sdk imports and server.tool(...) (removed in SDK v2), the deprecated SSE transport, a shared bearer token passed off as auth, zod 3 that compiles and then breaks the first tools/list, and tools with one annotation hint or none. That last one now blocks OpenAI plugin submission, which requires explicit readOnlyHint, destructiveHint and openWorldHint on every tool, and gets servers flagged by trust indexes.

    This pack gives the agent current rules, checked against the 2026-07-28 specification, the TypeScript SDK 2.3 source and docs, and the Python and Go SDKs.

    What's inside

    • mcp-server-production: version table, routing, pre-flight checklist, the boundaries that change behaviour.
    • mcp-v2-server: factory pattern, registerTool/resources/prompts with zod 4, serveStdio and createMcpHandler serving both protocol eras, elicitation, Python MCPServer and Go equivalents.
    • mcp-tool-design: names, descriptions, schemas, structured output, all four hints with a decision table, isError vs protocol errors, OpenAI review rules, trust-index flags.
    • mcp-v1-to-v2-migration: the official codemod, then the silent breaks it cannot see (raw -32001 checks, falsy structuredContent, legacy OAuth errors that turn 401s into 500s).
    • mcp-remote-auth: Streamable HTTP on Node, Express, Hono and Workers; Host/Origin checks; an OAuth resource server with protected resource metadata and audience validation, tested end to end.
    • mcp-security: path traversal, command injection, SSRF, secrets, error leakage, tool poisoning, token passthrough, with tested guard code.
    • mcp-testing: Inspector CLI, in-process tests, stdio, pytest and Go recipes, CI.
    • mcp-distribution: npm, Docker, .mcpb bundles, official registry server.json, configs for Claude Code, Codex, Cursor and Gemini CLI.

    Scripts included

    lint-mcp-server.mjs connects to any MCP server over stdio or HTTP and flags missing hints, weak or injected descriptions and risky parameters. migrate-imports.mjs rewrites v1 imports and lists every leftover v1 idiom with file and line. Both are zero-dependency Node.

    Versions

    MCP spec 2026-07-28, TypeScript SDK 2.3, Python mcp 2.3, Go go-sdk 1.8, Inspector 2.10, registry schema 2025-12-11.

    Requires Node 20+ and Zod 4.2.0+. No support for deprecated SSE transport in v2. Python requires mcp 2.x (FastMCP is renamed). Stdio transport forbids stdout logging.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    Requires

    @modelcontextprotocol/inspector
    Node.js
    @modelcontextprotocol/codemod
    Lint MCP
    Python
    V2 Server MCP
    Tool Design MCP
    pkg
    Protocol Version MCP
    Method MCP
    Name MCP
    Param MCP
    installs
    Publisher MCP
    When Preparing An MCP
    uv (Python tool runner)
    @acme/notes-mcp
    tsc
    macOS

    Permissions

    Terminal / Shell
    Read Files
    Network Access
    Environment Variables
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    This skill is specifically tuned for the 2026-07-28 protocol and v2 SDKs, preventing the common issue where generic LLMs generate outdated v1 code that causes breaking changes in modern environments.

    It supports TypeScript (Node 20+), Python (MCPServer), and Go (v1.8+), and provides migration paths from the deprecated monolithic SDK to the new modular v2 packages.

    Both. The migration skill runs the official codemod, then finds the v1 leftovers it misses (raw -32001 checks, falsy structuredContent checks, legacy OAuth errors) with file and line, and the linter checks every tool for the explicit hints OpenAI's plugin review requires.

    It provides production-grade security patterns, including path traversal protection and RFC 9728 OAuth metadata, to ensure your server is safe for remote deployment and registry submission.

    Servers built with this skill are fully compatible with any host using the latest protocol revision, including Claude Code, Cursor, and other modern LLM environments.

    Eight skills (server setup, tool design, v1 to v2 migration, remote auth, security, testing, distribution and an entry checklist) and two zero-dependency Node scripts: an MCP server linter that connects over stdio or HTTP, and a v1 import migrator.

    New in APIs & Backend