跳到正文
原文
Google AI：DEV 作者专属（RSS）· Shreyansh Agrahari·· 7 小时前AI 评分29

Racksmith：基于 Sanity Context MCP 的自主模块化合成器规划智能体

Racksmith: The Autonomous Modular Synth Planner Powered by Sanity Context MCP

AI 导读

Racksmith 是一款自主 AI 智能体，通过 Sanity Context MCP 服务器查询结构化内容，为 Eurorack 模块化合成器规划安全配置。

正文

This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content

⚡ Quick Links & Production Deployments

What I Built

Building a Eurorack modular synthesizer is notoriously treacherous. Beginners and professional sound designers alike routinely damage expensive hardware due to four silent traps:

  1. Physical Depth Collisions: Eurorack cases are not empty boxes. They contain power distribution bus boards, DC switching supplies, and internal support rails. A module that is 55mm deep (such as a vintage Doepfer A-110-1 VCO) will physically crash against the bus board in a shallow skiff case (such as the Intellijel Palette 62, max clearance 45.5mm), cracking the PCB or shorting pins.
  2. Power Rail Blowouts & Inrush Current: Eurorack power supplies deliver three distinct DC voltage rails: +12V, -12V, and +5V. When powering on, analog oscillators and digital DSP modules draw an inrush surge exceeding 150–200% of steady-state draw. Exceeding 80% of rated rail capacity causes power supplies to brown out, produce high-pitched ground whistle, or fry voltage regulators.
  3. Manufacturer Specification Contradictions: Different sources document conflicting specifications for the exact same module. Printed manuals often cite quiescent (idle) current draw, while official engineering errata or lab oscilloscope tests reveal peak current under heavy modulation. Similarly, through-hole (THT) vintage revisions often measure 15–20mm deeper than modern surface-mount (SMD) re-issues.
  4. The Catastrophic Failure of Unstructured Vector RAG: Standard vector embeddings fail on Eurorack planning. If an LLM performs cosine similarity over raw forum threads or PDF scrapes, it conflates revision years, hallucinates dimensions, and fails elementary arithmetic on multi-rail power sums.

The Solution: Racksmith

Racksmith solves this by pairing an autonomous AI agent (powered by the Vercel AI SDK and Gemini 3.8 Flash) with a Sanity Knowledge Lake via a standards-compliant Model Context Protocol (MCP) server. The agent queries structured documents with field-level provenance, evaluates safety through a deterministic mathematical validation engine, surfaces real-world manufacturer errata in an interactive resolution modal, and renders the result in a photorealistic 3D interactive hardware visualizer.

               +------------------------------------------------+
               |              User Browser Client               |
               | (Next.js 16 + React Three Fiber 3D + Zustand)  |
               +-----------------------+------------------------+
                                       |
                   +-------------------+-------------------+
                   | User Prompt / GUI Actions             |
                   v                                       v
         +--------------------+                 +---------------------+
         |  AI Agent Router   |                 | 5-Step Golden Path  |
         |  (Vercel AI SDK +  |                 | Demo Controller     |
         |  Gemini 3.8 Flash) |                 +----------+----------+
         +---------+----------+                            |
                   | Tool Calls                            |
                   v                                       |
         +-------------------------------------+           |
         | Model Context Protocol (MCP) Client |           |
         |  - searchSanityKnowledge            |           |
         |  - getModule / getCase              |           |
         |  - getContradictions                |           |
         |  - validateRackDeterministic        |           |
         |  - saveUserDecision                 |           |
         +-----------------+-------------------+           |
                           | Linked Transport              |
                           v                               |
         +-------------------------------------+           |
         |      Sanity Context MCP Server      |           |
         | (Model Context Protocol Spec 1.2.0) |           |
         +-----------------+-------------------+           |
                           | GROQ / Lake Fetch             |
                           v                               |
         +-------------------------------------+           |
         |     Sanity Lake (r674mqrk)          |           |
         |  - 33 Modules                       |           |
         |  - 4 Cases                          |           |
         |  - 8 Manufacturers                  |           |
         |  - 6 Claims with Provenance         |           |
         |  - 3 Contradictions with Errata     |           |
         |  - UserDecisions (Persisted)        |           |
         +-----------------+-------------------+           |
                           |                               |
                           +---------------+---------------+
                                           |
                                           v
                       +---------------------------------------+
                       |    Deterministic Validation Engine    |
                       |  - HP Width Boundary Check            |
                       |  - Mechanical Depth Collision Check   |
                       |  - 3-Rail Power & 80% Headroom Buffer |
                       +-------------------+-------------------+
                                           |
                                           v
                       +---------------------------------------+
                       |   Photorealistic 3D Eurorack Rack     |
                       | (Anodized Faceplates, Jacks, Collide) |
                       +---------------------------------------+

Demo

🤖 End-to-End Walkthrough: Autonomous AI Agent via Sanity MCP

In this demonstration, the AI Agent plans a modular synth system autonomously using natural language while querying real content from Sanity:

1. AI Agent Standby State

The user navigates to the AI Agent tab. The agent is initialized with direct tool bindings to the Sanity Context MCP server.

Agent Step 1 - Ready State

2. Natural Language Prompt

The user enters a complex hardware request:

"Build an ambient sound design rack with complex modulation and reverb, make sure modules fit in depth and don't exceed power limits."

Agent Step 2 - Prompt Typed

3. Agent Execution & Sanity MCP Tool Calling

The agent executes tool calls against the Sanity MCP Server:

  • searchSanityKnowledge: Queries Sanity for ambient sound sources and filters.
  • getModule: Retrieves exact dimensions and multi-rail power draws.
  • validateRackDeterministic: Passes candidate configurations through the mathematical engine, automatically rejecting modules that exceed case depth or violate the 80% power headroom ceiling.

Agent Step 3 - MCP Execution

4. Autonomous 3D Rack Population

The agent presents its verified reasoning, citing the exact GROQ documents retrieved from Sanity, and directly mounts the optimal modules (Plaits, Rings, Beads, Maths SMD) onto the 3D hardware rack without human intervention.

Agent Step 4 - Rack Built

Code

The complete source code is public and open source on GitHub:

GitHub Repository

👉 https://github.com/Shreyansh00987/Racksmith

Tech Stack:

  • Framework: Next.js 16 (App Router, React 19, Turbopack)
  • Content & Knowledge Lake: Sanity Lake (r674mqrk, dataset production)
  • Protocol: Model Context Protocol (MCP Standard Spec 1.2.0)
  • AI Engine: Vercel AI SDK (ai/rsc) + Google Gemini 3.8 Flash
  • 3D Visualization: React Three Fiber + Three.js + Drei
  • State Management: Zustand
  • Deployment: Vercel

How I Used Sanity

Why Structured Content Beats Unstructured Vector RAG

If Sanity were replaced with a generic vector database, Racksmith would fail.

A modular synthesizer build requires strict relational invariants:

  • module.depthMM + clearanceBuffer <= case.maxDepthMM
  • sum(module.powerPlus12) <= case.powerCapacityPlus12 * 0.80

In an unstructured vector store, a search for "Make Noise Maths power draw" returns chunk embeddings where "Draws 60mA" and "Draws 90mA under active cycle" look like identical high-confidence semantic matches. An LLM has no mechanism to determine which claim corresponds to which revision or test methodology.

With Sanity, specifications are stored as typed, structured entities with field-level provenance.

Structured Schemas in Sanity:

  1. module: Encapsulates width (hp), mechanical depth (depthMM), 3-rail current (powerPlus12, powerMinus12, powerPlus5), category, and manufacturer reference.
  2. case: Defines total HP, row count, depth clearance (maxDepthMM), and power supply ratings (powerPlus12, powerMinus12, powerPlus5).
  3. manufacturer: Authoritative maker profile with website and technical support links.
  4. claim: Represents a specific technical assertion (field, value, unit, sourceURL, revision, confidence).
  5. contradiction: First-class document linking conflicting claims (claimA <-> claimB) with explanation, conflictType, and impactAnalysis.
  6. userDecision: Records the user's resolution back into the Sanity dataset so that future AI agent invocations honor the user's vetted hardware reality.

MCP Tools Built on Sanity Context:

The Next.js application exposes an MCP server (/api/mcp) implementing 5 core tools:

// Example: Sanity MCP Tool for Discrepancy & Errata Retrieval
server.tool(
  'getContradictions',
  'Retrieve known specification contradictions and manufacturer errata',
  { moduleId: z.string().optional() },
  async ({ moduleId }) => {
    const query = moduleId
      ? `*[_type == "contradiction" && (claimA->module._ref == $moduleId || claimB->module._ref == $moduleId)]{
          _id, title, explanation, impactAnalysis,
          claimA->{ field, value, unit, source, revision },
          claimB->{ field, value, unit, source, revision }
        }`
      : `*[_type == "contradiction"]{
          _id, title, explanation, impactAnalysis,
          claimA->{ field, value, unit, source, revision },
          claimB->{ field, value, unit, source, revision }
        }`;
    const result = await sanityClient.fetch(query, { moduleId });
    return { content: [{ type: 'text', text: JSON.stringify(result, null, 2) }] };
  }
);

Deterministic Validation Engine

The agent does not guess math. When an agent wants to evaluate a rack configuration, it calls the validateRackDeterministic MCP tool:

export function validateRack(modules: Module[], targetCase: Case): ValidationResult {
  const totalHp = modules.reduce((acc, m) => acc + m.hp, 0);
  const hpOverflow = totalHp > targetCase.totalHp;

  const depthCollisions = modules
    .filter(m => m.depthMM > targetCase.maxDepthMM)
    .map(m => ({ module: m.name, moduleDepth: m.depthMM, maxDepth: targetCase.maxDepthMM }));

  const currentPlus12 = modules.reduce((acc, m) => acc + m.powerPlus12, 0);
  const maxPlus12Safe = targetCase.powerCapacityPlus12 * 0.80;
  const power12Overload = currentPlus12 > maxPlus12Safe;

  return {
    isValid: !hpOverflow && depthCollisions.length === 0 && !power12Overload,
    metrics: { totalHp, currentPlus12, maxPlus12Safe },
    depthCollisions,
    hpOverflow,
    power12Overload
  };
}

Sanity Project Details

  • Sanity Project ID: r674mqrk
  • Dataset: production
  • Live Embedded Studio: https://racksmith.vercel.app/studio
  • CORS Origins Configured: https://racksmith.vercel.app, http://localhost:3000
  • Public Dataset Query Endpoint: 
  https://r674mqrk.api.sanity.io/v2024-01-01/data/query/production?query=*[_type=="module"][0...5]{name,hp,depthMM,powerPlus12}

Agent Session

Below is a curated transcript excerpt demonstrating how the agent invokes Sanity MCP tools to safely resolve an ambiguous hardware request:

[
  {
    "role": "user",
    "content": "Build an ambient sound design rack with complex modulation and reverb, make sure modules fit in depth and don't exceed power limits."
  },
  {
    "role": "assistant",
    "thought": "The user wants an ambient rack. I must query Sanity Knowledge Lake for modules tagged with 'ambient', 'reverb', or 'modulation'. I will check their depths against standard case clearances.",
    "tool_call": {
      "name": "searchSanityKnowledge",
      "arguments": { "query": "ambient modulation reverb granular" }
    }
  },
  {
    "role": "tool",
    "name": "searchSanityKnowledge",
    "content": [
      { "name": "Mutable Instruments Beads", "category": "granular", "hp": 14, "depthMM": 25, "powerPlus12": 100 },
      { "name": "Mutable Instruments Rings", "category": "resonator", "hp": 14, "depthMM": 25, "powerPlus12": 120 },
      { "name": "Make Noise Maths", "category": "modulation", "hp": 20, "depthMM": 25, "powerPlus12": 90 }
    ]
  },
  {
    "role": "assistant",
    "thought": "I will check for known contradictions on Make Noise Maths before adding it.",
    "tool_call": {
      "name": "getContradictions",
      "arguments": { "moduleId": "module-make-noise-maths" }
    }
  },
  {
    "role": "tool",
    "name": "getContradictions",
    "content": [
      {
        "title": "Make Noise Maths Power & Depth Errata",
        "explanation": "Vintage THT units draw 60mA quiescent and measure 45mm deep. Modern SMD units draw up to 90mA active cycle and measure 25mm deep.",
        "impactAnalysis": "Vintage revision will collide with shallow skiff cases (Palette 62)."
      }
    ]
  },
  {
    "role": "assistant",
    "thought": "Selecting the Modern SMD revision guarantees 25mm depth, safely fitting within the 45.5mm skiff limit. Now validating total power.",
    "tool_call": {
      "name": "validateRackDeterministic",
      "arguments": {
        "caseId": "case-palette-62",
        "moduleIds": ["module-plaits", "module-rings", "module-beads", "module-maths-smd"]
      }
    }
  },
  {
    "role": "tool",
    "name": "validateRackDeterministic",
    "content": {
      "isValid": true,
      "totalHp": 60,
      "maxHp": 62,
      "powerPlus12": 360,
      "maxPowerPlus12Allowed": 960,
      "depthCollision": null
    }
  },
  {
    "role": "assistant",
    "content": "I have assembled an ambient sound design rack for you! I verified through the Sanity Knowledge Lake that Make Noise Maths has a known errata between vintage THT (45mm) and modern SMD (25mm). By selecting the modern SMD revision, all 4 modules (Plaits, Rings, Beads, and Maths) safely fit into your 62HP case with 0 depth collisions and consume only 360mA on the +12V rail (well below your 80% safety threshold of 960mA)."
  }
]

Built with ❤️ for the DEV & Sanity Community by Shreyansh (@Shreyansh00987)

来源：Google AI：DEV 作者专属（RSS） · dev.to

#产品更新#MCP/工具调用#Agent#部署/工程#Google