Architector Query Slices

    1

    Looks up APIs, domain terms, persistence, flows, and other architecture facts via MCP Architector slices and search without loading the full project into context.

    Free

    2 usesSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Architector Query Slices

    Example session with this skill installed

    What API endpoints and database entities are defined in the current project? Give me a compact list.

    • Read your context and instructions
    • Compiled the architector query slices

    I have retrieved the architectural facts for project shop-backend-v2 (ID: proj_98234). I queried the api and persistence slices to identify current entry points and data structures.

    Project Architecture Summary: shop-backend-v2

    KindNameModuleDescription/Snippet
    http-endpointPOST /ordersordering-serviceCreates new customer orders
    http-endpointGET /cataloginventory-serviceLists available products
    grpc-methodUpdateStockinventory-serviceInternal inventory sync
    db-tableordersordering-servicePrimary order records
    db-tableorder_itemsordering-serviceLine item details
    entityProductinventory-serviceCore domain product model
    entityStockLevelinventory-serviceReal-time availability

    Note: Results are limited to the first 20 entries. More entries are available in the api slice.

    Next steps

    • Run get-entry on POST /orders to see specific validation logic.
    • Query the events slice to see how these services communicate.
    • Use list-modules to see the full dependency graph between ordering and inventory.

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

    About this skill

    Looks up APIs, domain terms, persistence, flows, and other architecture facts via MCP Architector slices and search without loading the full project into context. Use when the user asks what endpoints or entities exist, wants a compact architecture view, or needs to find a fact by name in architector.

    Requires pre-onboarded Architector project. Does not perform write operations or fix broken graphs. Requires Node.js 18+ and mcp-architector server.

    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

    2 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Requires

    Node.js
    Architector MCP
    Architect MCP

    Permissions

    Terminal / Shell
    Network Access
    Write Files
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    Unlike standard RAG that pulls in raw code chunks, this skill queries a structured architectural graph. This prevents your LLM from being overwhelmed by file-level noise and ensures it understands high-level relationships and domain rules instead of just text snippets.

    This skill requires an active installation of the `mcp-architector` server and Node.js 18+. It is compatible with any AI agent or IDE that supports the Model Context Protocol (MCP), such as Claude Desktop or various agentic IDE extensions.

    No, the skill operates on a pre-indexed architectural graph. You must first onboard your project using Architector so the skill can query the existing metadata, API endpoints, and domain facts without needing to parse the entire codebase in real-time.

    You receive the pre-configured MCP skill definitions, detailed documentation on the available tools (like slice fetching and entry searching), and instructions for connecting it to your Architector workspace.

    This skill is highly effective for polyglot environments. Since it queries architectural facts rather than raw syntax, it can provide a unified view of endpoints and entities across microservices written in different programming languages.

    New in LLM Ops