More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    MCP Server Architect for AI Coding Agents

    1

    Most MCP servers fail the same five checks — no Resource Server metadata, unpinned tools, prose-narrating returns. Design and review yours like a production system.

    $15

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    MCP Server Architect for AI Coding Agents

    MCP Server Architect for AI Coding Agents

    Example session with this skill installed

    Review my MCP server implementation. It uses stdio transport and provides tools for interacting with a local Postgres database. I need a security audit and spec compliance check.

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

    I have analyzed the provided MCP server implementation for the Postgres local domain. The server uses stdio transport, which is appropriate for this local-only use case.

    MCP Design Review — postgres-local-server

    Verdict: FIX-BEFORE-SHIP

    Spec compliance matrix

    AreaRequirementStatusNote
    TransportstdioPASSCorrect for local single-user tool.
    AuthStatelessPASSNo session state identified in core dispatch.
    ToolsMRTR PatternFAILquery_db returns prose narration instead of raw JSON.
    ToolsHash-pinningFAILNo definition hashing detected; vulnerable to poisoning.
    ListingsCacheablePASSETag support implemented for tools/list.

    Findings (by severity)

    High / Tools / MRTR Violation: The query_db tool returns "Found X rows: [data]" which forces the model to parse prose.

    Fix: Return raw JSON result set and count.

    High / Security / Tool Poisoning: Tool definitions are loaded without integrity checks.

    Fix: Implement hash-pinning at registration; block execution on mismatch.

    • Med / Naming / snake_case: Tool RunQuery uses PascalCase. Fix: Rename to run_query.

    Tool surface audit

    toolscopesMRTR ok?naming ok?poisoning-safe?
    get_tablesN/AYESYESNO
    query_dbN/ANOYESNO

    Architecture notes

    The server correctly identifies as a local stdio transport. Since this is stdio, OAuth is skipped, but the lack of tool integrity checks remains a critical risk for local execution.

    Ship checklist

    1. Refactor query_db to return structured JSON only.
    2. Implement SHA-256 hash validation for tool definitions.
    3. Pass MCP Inspector locally.
    4. Generate claude_desktop_config.json snippet.

    Next steps

    • Apply the MRTR fix to the query_db function to ensure clean model interpretation.
    • Add the hash-pinning logic to the server bootstrap sequence.
    • Run the MCP Inspector and provide the logs for final verification.

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

    About this skill

    About this skill

    MCP is the integration layer between agents and real tools — which makes a badly designed server an attack surface with a friendly JSON API. This skill encodes the full production architecture: stateless core, correct transport, OAuth 2.1 Resource Server with CIMD, per-tool scopes, tool-poisoning defense, and dual-era protocol support — plus a review method that catches the failures everyone actually ships.

    What it does

    • Enforces one-server-one-domain boundaries and correct transport selection
    • Designs OAuth 2.1 correctly: protected-resource metadata, CIMD, PKCE, DPoP
    • Audits tool surfaces: naming, MRTR structured returns, per-tool scopes, hash-pinning
    • Plans dual-era protocol support with a deprecation path
    • Outputs a compliance matrix + ship checklist (Inspector, registry, CVE watch)

    Why this beats prompting it yourself

    "Design an MCP server" produces a tutorial-shaped answer: a couple of tools and maybe auth. It will not mention tool-definition pinning, MRTR violations, removed session headers, or CIMD — because those live in the gap between "it connects" and "it survives production". This skill is that gap, codified.

    Does not build client-side agent logic. Focuses exclusively on server-side architecture. Requires external verification for spec changes released after the skill's last update.

    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 10 days ago

    Requires

    Non MCP
    Method MCP
    Name MCP

    Permissions

    No special permissions declared or detected

    Listed10 days ago

    What's inside

    Frequently Asked Questions

    This skill provides specialized architectural oversight for Model Context Protocol (MCP) servers, ensuring they are secure, stateless, and fully compliant with the latest specifications to prevent secret leaks and tool-poisoning.

    Yes, it is designed to work with any environment that supports MCP, including Claude Desktop, Cursor, and custom IDE integrations, providing production-ready configurations for each.

    The architect can perform a full audit of your current implementation, providing a severity-ranked findings report and a specific migration path to bring legacy servers up to the current protocol standards.

    While it specializes in MCP-specific security like MRTR patterns and hash-pinning, it also enforces enterprise-grade auth standards including OAuth 2.1 with PKCE and DPoP.

    You receive a comprehensive architectural agent capable of four distinct modes: Greenfield Design, Code Review, Migration Mapping, and General Advice, along with a spec-compliance matrix for your projects.

    This skill focuses exclusively on the server-side architecture and tool definitions; it does not build the client-side agents that consume the MCP services.

    New in APIs & Backend