Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    mcp server publish gate

    1

    A 7-gate pre-flight audit for MCP servers to ensure tool schema validity, agent-readability, and runtime safety.

    $14.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    mcp server publish gate

    mcp server publish gate

    Example session with this skill installed

    Audit my MCP server at /src/payments-server. I have a 'transfer' tool and a 'balance' tool. I want to publish this to Smithery next week.

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

    I have completed the 7-gate pre-flight audit for the payments-server. The server is currently unfit for publishing due to protocol-breaking transport issues and missing safety annotations for financial transactions.

    MCP Audit Results: /src/payments-server

    GateStatusFindings
    G1: SchemaPASSValid inputSchema for all tools; no additionalProperties.
    G2: DescriptionsWARNtransfer lacks "what it returns" in the description string.
    G3: SafetyFAILtransfer tool is missing destructiveHint: true.
    G4: SecretsPASSNo hardcoded keys found; .env.example is present.
    G5: ErrorsFAILtransfer returns Error: 500 instead of a structured explanation.
    G6: TransportFAILFound console.log("Processing...") in the stdio stream.
    G7: RailsWARNNo daily limit or confirm parameter on transfer calls.

    Remediation List (Priority Order)

    Protocol Fix: Remove console.log in src/index.ts. All non-protocol output must go to process.stderr to avoid corrupting the JSON-RPC transport.
    2. Safety Fix: Add destructiveHint: true to the transfer tool definition in your manifest.
    3.

    Logic Fix: Update the transfer error handler to return a tool result containing a clear message (e.g., "Insufficient funds: required 50.00, available 10.00").
    4.

    Clarification: Update the description for balance to explicitly state if it returns current available funds or total ledger balance.

    Next steps

    • Move all logging to stderr.
    • Implement a confirm: boolean parameter for the transfer tool.
    • Rerun the audit to verify Gate 3 and Gate 6 compliance.

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

    About this skill

    Model Context Protocol (MCP) servers often fail in production because agents cannot interpret their tools or because they lack safety guards. This skill provides a rigorous pre-flight audit for MCP servers before they are published to registries like Smithery or deployed to internal teams. It identifies silent protocol failures, ambiguous tool descriptions, and security risks.

    What it does

    • Schema validation checks that inputSchema uses narrow types and explicit properties while blocking additionalProperties injection surfaces.
    • Agent clarity scoring evaluates tool descriptions to ensure they specify exact triggers and return values for LLM reasoning.
    • Safety annotation audit identifies missing destructiveHint or readOnlyHint flags on sensitive operations like payments or deletions.
    • Transport verification scans for console.log statements in stdio paths that corrupt the protocol and cause silent agent crashes.
    • Error path analysis flags tools that return empty objects or stack traces instead of actionable instructions for agent self-correction.

    How it works

    1. Point the skill to your server manifest (package.json) and tool implementation source files.
    2. The agent executes a 7-gate audit covering schema, descriptions, safety, secrets, errors, transport, and runtime rails.
    3. It generates a status table showing PASS/FAIL/WARN for every gate across your toolset.
    4. You receive a prioritized remediation list ordered by severity to fix before publishing.

    Frameworks & tools

    Works with any MCP server implementation, specifically targeting stdio and sse transport layers. Supports Node.js, Python, and Go implementations following the Model Context Protocol specification.

    Why this beats prompting it yourself

    Generic prompts miss the subtle technicalities of the MCP spec, such as how stray stdout logs break the JSON-RPC framing or why agents ignore tools with broad schemas. This skill uses a structured 7-gate framework developed specifically for agentic interoperability and safety.

    Use cases

    • Auditing a server before submitting to the Smithery or Agensi registries.
    • Debugging a tool that an agent refuses to call or calls with the wrong parameters.
    • Performing a safety review on inherited code before granting an agent write access.
    • Hardening a wrapper for a paid API to prevent unexpected token usage or costs.

    Known limitations

    Performs static analysis of code and manifests only. It does not execute tools against live environments or verify third-party API credentials. Audit results for registry requirements are advisory.

    Static analysis only; no live tool execution. Registry requirements (Smithery/Agensi) are subject to change. Safety hints do not replace code-level runtime enforcement.

    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

    Permissions

    Read Files
    Network Access
    Terminal / Shell

    Static code audit of MCP server repositories: reads source files (Read Files) and runs local inspection commands (Terminal). Network is declared defensively — the checklist references network/API error-handling and timeouts as review criteria for the server under audit; this skill makes no runtime network calls.

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    This skill prevents 'silent failures' where an agent ignores a tool or crashes due to protocol corruption, specifically by catching schema errors and stray logs that standard linters miss.

    It is compatible with any MCP-compliant server written in Node.js, Python, or Go, and works whether your server uses stdio or SSE transport layers.

    Simply point the skill to your server's manifest and source files; the agent will then automatically process the code through the 7-gate framework without requiring manual configuration.

    The audit performs deep static analysis of your code and schemas, so it does not require live API keys or a running environment to identify security risks or protocol errors.

    You receive the full 7-gate diagnostic engine, a structured PASS/FAIL/WARN status report for your tools, and a prioritized remediation list for immediate fixes.

    New in LLM Ops