Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    MCP Contract Guard Review

    1

    Catch changes to MCP tool descriptions, schemas and annotations before granting access. Compare exports locally, explain what needs review and produce JSON or SARIF evidence for CI.

    $10

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    MCP Contract Guard Review

    MCP Contract Guard Review

    Example session with this skill installed

    Compare the bundled candidate catalog against the reviewed baseline. Should this MCP update proceed without another review?

    • Read your context and instructions
    • Compiled the mcp contract guard

    Review required. The local CLI exited with code 2. In this synthetic catalog, one tool was added, one removed, four changed and one stayed unchanged. The report contains six surface signals and one advisory text finding.

    • record.archive: The schema no longer requires confirmation and the destructive-action hint changed. Ask where confirmation is enforced.
    • report.export: The schema added a destination and broadened accepted inputs. Verify which destinations the implementation actually accepts.
    • record.bulk_update was added and legacy.lookup was removed. Review the new tool’s authorization and check callers of the removed tool.
    • catalog.search and document.preview: Review the changed descriptions and the advisory text signal in the preview description.

    The unchanged control returned exit 0. An incomplete export returned exit 1 with no report. The changed export produced JSON, SARIF and HTML evidence.

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

    About this skill

    Know what changed before you approve an MCP server update.

    A tool can keep its name while its description, inputs or declared behavior change. MCP Contract Guard Review gives your agent a reproducible way to compare a candidate tool catalog against a reviewed reference and tell you what needs a second look.

    • Compare complete tools/list exports with the local Contract Guard CLI.
    • See additions, removals, schema and annotation changes, and advisory text findings.
    • Get a review handoff with evidence paths and questions for the tool owner.
    • Use the same decision in CI and export JSON, SARIF or HTML.

    The skill includes the review workflow, setup and CI guidance. The comparator is available separately from the project’s public source. Your team decides when to approve a baseline.

    Try the browser demo with synthetic data

    Compares complete exported tool definitions against a reviewed baseline. Requires Node.js 22+ and the local CLI. It cannot verify live behavior, authorization, or the completeness of the export.

    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 5 days ago

    Requires

    Node.js
    Contract Guard CLI MCP
    Contract Guard MCP
    Git

    Permissions

    Read Files
    Write Files
    Terminal / Shell

    Reads only the selected baseline and candidate JSON files and writes a new report when requested. Comparisons run locally. First-time setup fetches pinned source and dependencies from GitHub and npm.

    Listed5 days ago

    What's inside

    Frequently Asked Questions

    It compares exported tool definitions against an explicit baseline and gives reviewers specific changed fields, fingerprints, and a repeatable CI decision. It complements code review.

    Use an agent with a local terminal and Node.js 22+. A CI runner can use the CLI exit code and keep JSON or SARIF as evidence. The setup guide pins a publicly available revision.

    Provide a complete candidate export, an acknowledged baseline and the matching scope. The agent runs the local CLI and explains the observed changes.

    The local comparator calculates the decision and the exact evidence. The agent summarizes the report and proposes questions for a human reviewer.

    The skill is focused on structural governance and does not validate live server behavior, runtime authorization logic, or network connectivity. It requires complete JSON exports of your tool definitions to provide a reliable verdict.

    The purchase includes the agent review workflow, reproducible CLI setup and CI integration guidance. Install the comparator separately from the linked public repository.

    New in LLM Ops