# Whatic Datasheets MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.whatic%2Fdatasheets
Registry id: `mcp-registry/io.whatic/datasheets`
Status: live (checked 2026-10-27T16:01:01.699Z)

## Verdict

Whatic Datasheets MCP server answered 100% of Glimind's liveness checks over 30 days, better than 42% of MCP servers, with 1053 ms median handshake and 5 outages in 90 days. Its agent-readiness grade is A (100/100) across 7 tools, costing an agent about 2,180 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 100% | 42% of MCP servers |
| Median handshake latency | 1053 ms | 14% of MCP servers |
| p95 handshake latency | 4017 ms | — |
| Checks in 30 days | 5,034 | — |
| Outages, 90 days | 5 | — |
| Median recovery | 4 min | — |
| Agent-readiness score | 100/100 (A) | 93% of MCP servers |
| Tools | 7 | — |
| Tool-list size for an agent | ~2,180 tokens | 51% of MCP servers |
| Days observed | 29 | — |

## Install

```json
{
  "mcpServers": {
    "whatic-datasheets-mcp-server": {
      "type": "http",
      "url": "https://whatic.io/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http whatic-datasheets-mcp-server https://whatic.io/mcp
```

## Tools (7)

- `compare_parts`: Relative price tier, stock posture, and library class for a set of IC part numbers (a ranking from a distributor snapshot, not a live quote).
- `find_parts`: Shortlist IC part numbers by parametric spec constraints, ranked by how many constraints each part satisfies, then by headroom past those thresholds, and spread
- `get_image`: Fetch datasheet figure images (PNG/JPEG) for opaque `ref` tokens obtained from search/lookup/get_segments. Returns each image plus its caption/description/page 
- `get_segments`: Expand opaque `ref` tokens (from search/lookup) into full datasheet segment content.
- `get_specs`: Read canonical extracted specs (min/typ/max, unit, conditions) for known IC part numbers from a pre-extracted parametric index — not from datasheet text. This i
- `lookup`: One-shot spec/section retrieval: full content of the most relevant datasheet segments for one or more parts (fuses search+get_segments). Already groups results 
- `search`: Search the datasheet corpus; returns hit records (metadata + snippet, each with an opaque `ref`). Pass a ref list to `get_segments` for full content. If you alr

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.