Whatic IC Datasheets

Query real IC datasheets: parametric part search, spec lookup, price comparison, and datasheet-grounded answers for electronic components, extracted and…

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Find Parts: Shortlist IC part numbers by parametric spec constraints, ranked by how many constraints each part satisfies. Each constraint is {canonical, op: gte|lte|eq|range, value, unit?}. Returns pe
  • Get Specs: Read canonical extracted specs (min/typ/max, unit, conditions) for known IC part numbers. Optionally restrict to specific canonical parameter names.
  • 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).

What data it sees

Do you need an account

No: the server works without sign-in

Query real IC datasheets: parametric part search, spec lookup, price comparison, and datasheet-grounded answers for electronic components, extracted and verified against manufacturer PDFs.

How to connect

How to connect Whatic IC Datasheets to Claude

The server address to paste into Claude settings:

https://whatic.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect Whatic IC Datasheets to ChatGPT

The server address to paste into ChatGPT settings:

https://whatic.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect Whatic IC Datasheets to Cursor

The server address to paste into Cursor settings:

https://whatic.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (7)

Raw names from tools/list. Only developers need these.

find_partsShortlist IC part numbers by parametric spec constraints, ranked by how many constraints each part satisfies. Each constraint is {canonical, op: gte|lte|eq|range, value, unit?}. Returns per-constraint pass/fail/unknown. `canonical` MUST be one of the exact names below (case-sensitive): adc_resolution, block_erase_time, breakdown_voltage_ds, channel_count, clamping_voltage, clock_frequency, cmrr, cmti, coil_power, coil_resistance, coil_voltage, collector_emitter_voltage, contact_current, contact_resistance, core_size, cpu_speed, current_rating, dark_current, data_rate, data_retention, dc_resistance, drain_current, driver_count, dropout_voltage, eeprom_size, emitter_base_voltage, fall_time, forward_current, forward_voltage, gain_bandwidth, gate_charge, impedance, input_bias_current, input_capacitance, input_offset_current, input_offset_current_drift, input_offset_voltage, input_offset_voltage_drift, input_voltage_noise_density, insertion_loss, io_count, isolation_voltage, junction_capacitance, load_capacitance, memory_size, operate_time, operating_frequency, operating_temperature, output_capacitance, output_count, output_current, output_noise_voltage, output_power, output_voltage, output_voltage_high, output_voltage_low, page_program_time, peak_pulse_current, power_dissipation, program_erase_cycles, program_memory_size, propagation_delay, psrr, quiescent_current, ram_size, rds_on, receiver_count, rectified_current, release_time, response_time, reverse_leakage_current, reverse_recovery_time, reverse_transfer_capacitance, reverse_voltage, rise_time, sample_rate, sensitivity, settling_time, slew_rate, standby_current, supply_voltage_range, switching_frequency, switching_voltage, vgs_threshold, zener_voltage
get_specsRead canonical extracted specs (min/typ/max, unit, conditions) for known IC part numbers. Optionally restrict to specific canonical parameter names.
compare_partsRelative price tier, stock posture, and library class for a set of IC part numbers (a ranking from a distributor snapshot, not a live quote).
searchSearch the datasheet corpus; returns hit records (metadata + snippet, each with an opaque `ref`). Pass a ref list to `get` for full content. For part-specific queries, pass scope='device:<MPN>' (e.g. scope='device:NE5532') to restrict hits to that part and avoid cross-part contamination.
lookupOne-shot spec/section retrieval: full content of the most relevant datasheet segments for one or more parts (fuses search+get). Already groups results per part (via `parts`), so prefer `lookup` over `search` when you know the part(s).
getExpand opaque `ref` tokens (from search/lookup) into full datasheet segment content.
get_imageFetch datasheet figure images (PNG/JPEG) for opaque `ref` tokens obtained from search/lookup/get. Returns each image plus its caption/description/page metadata. Only `type='image'` segments have image data.