Sheetsdata Mcp

Created By
octoco-ltd3 months ago
Instant access to electronic component datasheets for AI agents — specs, pinouts, package info, absolute max ratings, and application circuits extracted from manufacturer PDFs on demand. Ask your AI for any component's electrical characteristics, pin assignments, or package dimensions and get structured answers without downloading a single PDF. Built for hardware engineers designing PCBs, writing firmware, reviewing BOMs, and selecting parts.
Overview

SheetsData MCP

Your AI already knows how to code. Now it knows how to read datasheets.

SheetsData is an MCP server that gives AI agents instant, structured access to electronic component data — specs, pinouts, package dimensions, absolute max ratings, application circuits — extracted directly from manufacturer datasheets. No PDFs to upload. No context windows to stuff. Just ask.

The Problem

Every hardware engineer knows the drill. You're deep in a schematic, you need one spec — the SPI clock max, the dropout voltage, the pin assignment for TSSOP-20 — and suddenly you're downloading a 200-page PDF, scrolling to page 47, squinting at a table.

Your AI assistant can write firmware, review schematics, and catch design mistakes. But the moment it needs a datasheet, it's blind.

SheetsData fixes that.

How It Works

Connect SheetsData to any MCP-compatible AI tool — Claude, Cursor, Windsurf, VS Code Copilot, or any other agent — and your AI gains direct access to datasheet intelligence for millions of electronic components.

No SDK. No integration work. Add one config block and you're done.

Agent: What's the pinout for the STM32G030 in TSSOP-20? → Full pin table with alternate functions, pulled from the datasheet

Agent: Compare the TPS54302 and MP2315 — which handles 85°C better? → Side-by-side thermal specs from both datasheets

Agent: Will this LDO work at 12V input, 2A output, 85°C ambient? → PASS — all parameters within datasheet limits

What Your AI Can Do

  • Read any datasheet section — Pinouts, electrical characteristics, absolute maximum ratings, timing diagrams, package info, application circuits
  • Search for components — Find parts by specs, not just part numbers. "Low-noise LDO with PSRR above 70dB and dropout below 200mV"
  • Compare parts side by side — Real specs from real datasheets, not marketing summaries
  • Validate your design — Check operating conditions against datasheet limits before you commit
  • Find alternatives — Drop-in replacements matched by package, specs, and availability
  • Analyze datasheet images — Extract data from graphs, package drawings, and pin diagrams using vision AI

Built For Real Engineering Workflows

PCB layout — Get pin assignments and package dimensions without leaving your editor.

Firmware development — Your AI reads the register map, clock limits, and peripheral specs while you write code.

BOM review — Look up every part, check stock and lifecycle, flag risks, suggest alternatives — automatically.

Part selection — Define your requirements, search candidates, compare specs, validate fit — all in one conversation.

Design review — Check every component against its operating conditions. Catch out-of-spec parameters before they reach production.

Private Part Libraries

Upload proprietary datasheets for custom parts, in-house modules, or NDA-protected components. Your AI sees both public components and your private library in one unified search — scoped to your organization.

Set Up in 30 Seconds

  1. Sign up at sheetsdata.com/signup — free credits included
  2. Create an API key at Dashboard → API Keys
  3. Add the config to your AI tool:
{
  "mcpServers": {
    "sheetsdata": {
      "url": "https://mcp.sheetsdata.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

Works with Claude Desktop, Claude Code, Cursor, Windsurf, VS Code Copilot,
Cline, Amp, Zed, Continue, and any MCP-compatible agent.

Spend Your Time Designing, Not Reading PDFs

https://sheetsdata.com/signup · https://sheetsdata.com/pricing ·
https://github.com/octoco-ltd/sheetsdata-mcp

Server Config

{
  "mcpServers": {
    "sheetsdata": {
      "url": "https://mcp.sheetsdata.com/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_API_KEY>"
      }
    }
  }
}
Project Info
Created At
3 months ago
Updated At
3 months ago
Author Name
octoco-ltd
Star
-
Language
-
License
-
Category

Recommend Servers

View All
//beforeyouship — LLM Cost Modeling From Your Editor
@Indiegoing

Query realistic LLM cost models without leaving your editor. beforeyouship models the **true monthly cost** of an LLM app architecture — retries, prompt caching, batch discounts, infra overhead, and 3×/10× growth — across GPT-5.x, Claude, Gemini, DeepSeek, and more. Not a token calculator: a planning tool for the design phase, before you commit to a stack. **No API key needed to try it** — demo mode covers the six free-tier models. A Pro key from [beforeyouship.dev](https://beforeyouship.dev) unlocks the full 18-model catalog. ## What you can ask - "How much will a RAG chatbot cost at 10,000 requests/day?" - "Compare Claude Haiku vs Gemini Flash pricing for my workload" - "What's the cheapest model for a multi-step agent at scale?" - "Show me current per-token prices for Anthropic models" ## Tools ### `estimate_cost` Full cost model for an architecture at a given usage level. Returns Naive / Realistic / Worst Case monthly cost per model, 3×/10× growth scenarios, and an opinionated recommendation with reasoning. ### `get_model_prices` Current per-1M-token pricing — input, output, cached input, batch — with context windows and staleness metadata. ### `list_archetypes` Seven preset architecture patterns (simple chatbot, chatbot with history, RAG pipeline, multi-model router, coding assistant, document processor, multi-step agent) used as starting points for estimates. ## Setup **Claude Code:** ​```bash claude mcp add --transport http beforeyouship https://beforeyouship.dev/api/mcp ​``` **Cursor / other clients** — add a remote server: ​```json { "mcpServers": { "beforeyouship": { "type": "streamable-http", "url": "https://beforeyouship.dev/api/mcp" } } } ​``` Add an `Authorization: Bearer bys_...` header with a Pro key for the full catalog. ## Try it > Estimate the monthly cost of a RAG pipeline at 10,000 requests/day

16 hours ago