io.github.octoco-ltd/sheetsdata-mcp

Official12 tools

by octoco-ltd · JavaScript

Electronic component datasheets for AI agents — specs, pinouts, package data on demand.

Electronic component datasheets with specs, pinouts, and package data.

Captured live from the server via tools/list.

search_parts

Search for electronic components by part number, description, or keyword. Start here — this is the best entry point for finding components. Queries all configured providers in parallel. Results are merged by MPN with indicative pricing and stock from each source. Each result includes datasheet_status so you know which parts have datasheets available for read_datasheet. Best with specific part numbers or keywords (e.g. 'STM32F103', 'buck converter 3A'). For spec-based discovery in natural language, use search_datasheets instead. When the calling org has a private parts library, matching org-uploaded parts are appended to the results with source='private_library' and any tags the team has applied — including private parts whose MPN, manufacturer, description, type, category, or tag matches the query. DATASHEET STATUS VALUES: - 'ready' — extracted and indexed; call read_datasheet, search_datasheets, or analyze_image. - 'extracting' / 'in_progress' / 'queued' / 'pending' — extraction running or scheduled. Poll check_extraction_status every 5-10s until 'ready' or 'failed'. Typical time: 30s-2min. - 'not_extracted' — known part but datasheet hasn't been fetched yet. Trigger it via prefetch_datasheets (cheapest) or by calling read_datasheet (auto-triggers on first read). - 'no_source' — we couldn't find a public datasheet URL for this MPN. First, retry prefetch_datasheets in 10-30s (the URL resolver re-runs and often finds a source on the second pass). If still 'no_source', the agent can upload the PDF manually via request_datasheet_upload + confirm_datasheet_upload (see those tools). Org-uploaded datasheets are private to the org. - 'unsupported' — PDF exists but can't be extracted (scanned image-only, encrypted, or corrupted). Upload a clean text-based PDF via request_datasheet_upload to override. - 'failed' / 'error' — extraction errored. The response includes the error reason. Retry via prefetch_datasheets or escalate to support. - 'rejected' — input wasn't a real MPN (bare value like '100nF', description, or reference designator). Fix the input and re-call. - 'deduplicated' — another part in the family already has this datasheet; same content is returned under the primary MPN.

Parameters (3)

querystringrequired
Search query (part number or keyword)
limitinteger
Max results per provider (default 20). With providers='all', total results can be up to 3× this value (one set per provider).
providersstring
Which providers to query: 'all' (default), 'jlcpcb', 'mouser', or 'digikey'

search_datasheets

Semantic search across all extracted datasheets. Finds components matching natural language queries about specifications, features, or capabilities. Best for broad spec-based discovery across all parts (e.g. 'low-noise LDO with PSRR above 70dB'). Only searches datasheets that have been previously extracted — not all parts that exist. For finding specific parts by number, use search_parts instead.

Parameters (3)

querystringrequired
Natural language search query
section_typestring
Optional: limit search to a specific section type
limitinteger
Max results (default 15)

prefetch_datasheets

Trigger background datasheet extraction for multiple parts at once (up to 20). Non-blocking — returns immediately with the status of each part. Use this to warm up datasheets for a BOM before calling read_datasheet. Example: prefetch_datasheets(['TPS54302', 'ADS1115', 'LP5907']) If a part comes back 'no_source' on the first call, retry prefetch for that MPN once after 10-30s — the URL resolver is retriable and often finds a source on the second pass. If still 'no_source', use request_datasheet_upload + confirm_datasheet_upload to attach your own PDF (org-private). Part numbers must be specific MPNs (e.g. 'STM32F446RCT6', 'TPS54302DDCR') or LCSC numbers (e.g. 'C2837938'). Do NOT pass bare values ('100nF', '10K'), descriptions, BOM reference designators, test points, or board/module names — see the server instructions for the full rule set. When a BOM has values-only rows, use search_parts first to resolve each to an MPN. DATASHEET STATUS VALUES: - 'ready' — extracted and indexed; call read_datasheet, search_datasheets, or analyze_image. - 'extracting' / 'in_progress' / 'queued' / 'pending' — extraction running or scheduled. Poll check_extraction_status every 5-10s until 'ready' or 'failed'. Typical time: 30s-2min. - 'not_extracted' — known part but datasheet hasn't been fetched yet. Trigger it via prefetch_datasheets (cheapest) or by calling read_datasheet (auto-triggers on first read). - 'no_source' — we couldn't find a public datasheet URL for this MPN. First, retry prefetch_datasheets in 10-30s (the URL resolver re-runs and often finds a source on the second pass). If still 'no_source', the agent can upload the PDF manually via request_datasheet_upload + confirm_datasheet_upload (see those tools). Org-uploaded datasheets are private to the org. - 'unsupported' — PDF exists but can't be extracted (scanned image-only, encrypted, or corrupted). Upload a clean text-based PDF via request_datasheet_upload to override. - 'failed' / 'error' — extraction errored. The response includes the error reason. Retry via prefetch_datasheets or escalate to support. - 'rejected' — input wasn't a real MPN (bare value like '100nF', description, or reference designator). Fix the input and re-call. - 'deduplicated' — another part in the family already has this datasheet; same content is returned under the primary MPN.

Parameters (1)

part_numbersarrayrequired
List of MPNs to prefetch (max 20). Must be specific manufacturer part numbers, not values or descriptions.

check_extraction_status

Check the extraction status of one or more parts. Free. Each entry includes the current extraction step, elapsed seconds, and document ID. Use after prefetch_datasheets or after read_datasheet triggers a new extraction. Recommended polling cadence: every 5-10 seconds. Extraction typically takes 30s-2min for new parts, so polling faster than every 5s wastes calls. Stop polling once status is 'ready', 'failed', 'no_source', or 'unsupported'. DATASHEET STATUS VALUES: - 'ready' — extracted and indexed; call read_datasheet, search_datasheets, or analyze_image. - 'extracting' / 'in_progress' / 'queued' / 'pending' — extraction running or scheduled. Poll check_extraction_status every 5-10s until 'ready' or 'failed'. Typical time: 30s-2min. - 'not_extracted' — known part but datasheet hasn't been fetched yet. Trigger it via prefetch_datasheets (cheapest) or by calling read_datasheet (auto-triggers on first read). - 'no_source' — we couldn't find a public datasheet URL for this MPN. First, retry prefetch_datasheets in 10-30s (the URL resolver re-runs and often finds a source on the second pass). If still 'no_source', the agent can upload the PDF manually via request_datasheet_upload + confirm_datasheet_upload (see those tools). Org-uploaded datasheets are private to the org. - 'unsupported' — PDF exists but can't be extracted (scanned image-only, encrypted, or corrupted). Upload a clean text-based PDF via request_datasheet_upload to override. - 'failed' / 'error' — extraction errored. The response includes the error reason. Retry via prefetch_datasheets or escalate to support. - 'rejected' — input wasn't a real MPN (bare value like '100nF', description, or reference designator). Fix the input and re-call. - 'deduplicated' — another part in the family already has this datasheet; same content is returned under the primary MPN.

Parameters (1)

part_numbersarrayrequired
1-20 MPNs to check. Must be specific manufacturer part numbers, not values or descriptions.

get_part_details

Get full details for a specific electronic component by manufacturer part number (MPN) or LCSC number. Returns specs, pricing, and stock from all configured providers, plus the cached datasheet summary if available. Includes datasheet_status and available_sections when ready. Set prefetch_datasheet=true to trigger background extraction — no extra charge. Use after search_parts to drill into a specific result. The part_number must be a specific manufacturer part number (e.g. 'TPS54302DDCR', 'STM32F446RCT6') or LCSC number (e.g. 'C2837938'). Do NOT pass bare component values ('100nF', '10K'), descriptions ('buck converter'), or reference designators ('R1', 'U3'). DATASHEET STATUS VALUES: - 'ready' — extracted and indexed; call read_datasheet, search_datasheets, or analyze_image. - 'extracting' / 'in_progress' / 'queued' / 'pending' — extraction running or scheduled. Poll check_extraction_status every 5-10s until 'ready' or 'failed'. Typical time: 30s-2min. - 'not_extracted' — known part but datasheet hasn't been fetched yet. Trigger it via prefetch_datasheets (cheapest) or by calling read_datasheet (auto-triggers on first read). - 'no_source' — we couldn't find a public datasheet URL for this MPN. First, retry prefetch_datasheets in 10-30s (the URL resolver re-runs and often finds a source on the second pass). If still 'no_source', the agent can upload the PDF manually via request_datasheet_upload + confirm_datasheet_upload (see those tools). Org-uploaded datasheets are private to the org. - 'unsupported' — PDF exists but can't be extracted (scanned image-only, encrypted, or corrupted). Upload a clean text-based PDF via request_datasheet_upload to override. - 'failed' / 'error' — extraction errored. The response includes the error reason. Retry via prefetch_datasheets or escalate to support. - 'rejected' — input wasn't a real MPN (bare value like '100nF', description, or reference designator). Fix the input and re-call. - 'deduplicated' — another part in the family already has this datasheet; same content is returned under the primary MPN.

Parameters (3)

part_numberstringrequired
Specific manufacturer part number (MPN) or LCSC number (e.g. 'C2837938'). Not a value or description.
providerstring
Which provider to query: 'all' (default), 'jlcpcb', 'mouser', or 'digikey'
prefetch_datasheetboolean
Trigger background datasheet extraction (no extra charge). Default false.

read_datasheet

Read from a component's datasheet. Two modes: **Section mode** (default): Returns a named section. Start with section='summary' to get an overview and a list of available_sections. Then request specific sections by name. Section names are dynamic — any heading in the actual datasheet works (e.g. 'register_map', 'i2c_interface', 'power_management'). If a section name isn't found, automatically falls back to search mode. **Search mode**: Semantic search within the part's datasheet. Best for targeted questions (register bit fields, I2C config, specific specs). Use when you need to find specific information rather than a whole section. First call for a new part triggers extraction (30s-2min). Subsequent calls are cached. **Datasheet vs Reference Manual**: Manufacturer datasheets cover high-level specs, pinout, absolute maximum ratings, and package info. For microcontrollers (STM32, nRF52, RP2040), register-level programming details (I2C CR1/CR2, DMA config, interrupt bits) are in a separate Reference Manual, not the datasheet. The summary's available_sections will show what's actually present. The part_number must be a specific manufacturer part number (e.g. 'TPS54302', 'STM32F446RCT6') or LCSC number (e.g. 'C2837938'). Do NOT pass bare component values ('100nF', '10K'), descriptions, or reference designators. DATASHEET STATUS VALUES: - 'ready' — extracted and indexed; call read_datasheet, search_datasheets, or analyze_image. - 'extracting' / 'in_progress' / 'queued' / 'pending' — extraction running or scheduled. Poll check_extraction_status every 5-10s until 'ready' or 'failed'. Typical time: 30s-2min. - 'not_extracted' — known part but datasheet hasn't been fetched yet. Trigger it via prefetch_datasheets (cheapest) or by calling read_datasheet (auto-triggers on first read). - 'no_source' — we couldn't find a public datasheet URL for this MPN. First, retry prefetch_datasheets in 10-30s (the URL resolver re-runs and often finds a source on the second pass). If still 'no_source', the agent can upload the PDF manually via request_datasheet_upload + confirm_datasheet_upload (see those tools). Org-uploaded datasheets are private to the org. - 'unsupported' — PDF exists but can't be extracted (scanned image-only, encrypted, or corrupted). Upload a clean text-based PDF via request_datasheet_upload to override. - 'failed' / 'error' — extraction errored. The response includes the error reason. Retry via prefetch_datasheets or escalate to support. - 'rejected' — input wasn't a real MPN (bare value like '100nF', description, or reference designator). Fix the input and re-call. - 'deduplicated' — another part in the family already has this datasheet; same content is returned under the primary MPN.

Parameters (5)

part_numberstringrequired
Specific manufacturer part number (MPN) or LCSC number. Not a value or description.
modestring
Reading mode: 'section' (default) returns a named section, 'search' does semantic search
sectionstring
Section name for section mode. Start with 'summary' to discover available sections. Common: summary, pinout, electrical, abs_max, register_map, timing, package. Any heading in the datasheet works (slugified).
querystring
Search query — REQUIRED when mode='search', ignored when mode='section'. Example: 'charge voltage register', 'I2C address'.
limitinteger
Max search results for search mode (default 10). Each result includes adjacent context chunks for continuity.

compare_parts

Compare 2-5 electronic components side by side in a single call. For each part, returns merged provider data (pricing, stock, structured parameters, package) plus the cached datasheet summary if one exists, plus datasheet_status ('ready', 'extracting', or 'not_extracted'). Use this instead of calling get_part_details in a loop — it fans out provider queries in parallel and merges by MPN. For *discovering* candidates, use search_parts or find_alternative first; compare_parts assumes you already know which MPNs you want to compare. Behavior: - Uses only cached datasheet summaries — does not trigger extraction. Call prefetch_datasheets first if you need summaries for parts that haven't been extracted yet. - Validates every MPN upfront. If *any* input is not a real part number (value, description, reference designator), the whole call is rejected with a 'rejected' map listing the offenders — other parts are not compared. Filter your list before calling. - If a valid MPN is not found at any provider, that part still appears in the response with an 'error' field; the other parts are compared normally. IMPORTANT — part_numbers must be specific manufacturer part numbers (e.g. 'TPS54302DDCR', 'STM32F446RCT6') or LCSC numbers (e.g. 'C2837938'). Do NOT pass component values ('100nF', '10K'), descriptions ('buck converter'), or reference designators ('U3', 'R1'). Example: compare_parts(['TPS54302', 'LM2596', 'MP2359']) DATASHEET STATUS VALUES: - 'ready' — extracted and indexed; call read_datasheet, search_datasheets, or analyze_image. - 'extracting' / 'in_progress' / 'queued' / 'pending' — extraction running or scheduled. Poll check_extraction_status every 5-10s until 'ready' or 'failed'. Typical time: 30s-2min. - 'not_extracted' — known part but datasheet hasn't been fetched yet. Trigger it via prefetch_datasheets (cheapest) or by calling read_datasheet (auto-triggers on first read). - 'no_source' — we couldn't find a public datasheet URL for this MPN. First, retry prefetch_datasheets in 10-30s (the URL resolver re-runs and often finds a source on the second pass). If still 'no_source', the agent can upload the PDF manually via request_datasheet_upload + confirm_datasheet_upload (see those tools). Org-uploaded datasheets are private to the org. - 'unsupported' — PDF exists but can't be extracted (scanned image-only, encrypted, or corrupted). Upload a clean text-based PDF via request_datasheet_upload to override. - 'failed' / 'error' — extraction errored. The response includes the error reason. Retry via prefetch_datasheets or escalate to support. - 'rejected' — input wasn't a real MPN (bare value like '100nF', description, or reference designator). Fix the input and re-call. - 'deduplicated' — another part in the family already has this datasheet; same content is returned under the primary MPN.

Parameters (1)

part_numbersarrayrequired
2-5 specific manufacturer part numbers or LCSC numbers to compare head-to-head. Must be real MPNs — the call is rejected upfront if any entry is a value, description, or reference designator.

check_design_fit

Validate whether a component will work within your operating conditions. Compares your design parameters against the datasheet's absolute maximum ratings and recommended operating conditions. Returns PASS/FAIL/WARNING per parameter with margin percentages. Parameter mapping by component type: - Buck/boost converters: input_voltage, output_voltage, output_current, ambient_temp - MOSFETs: supply_voltage=VDS, output_current=ID (drain current), ambient_temp - LDOs: input_voltage, output_voltage, output_current, ambient_temp - Logic ICs: supply_voltage=VCC, ambient_temp Result semantics (per-parameter 'result' field): - PASS: comfortable margin. For a recommended-operating RANGE, any value inside the range (including the exact edges) is PASS. For an absolute-MAX rating, PASS means more than 10% below the limit. - WARNING: for absolute-max ratings only, the user value is within 10% of the limit (but not over) — part will work but with thin margin for part-to-part variation, temperature drift, and transients. Consider derating. - FAIL: user value is outside the allowed range / exceeds the limit — part is out of spec and will be stressed or damaged. - INSUFFICIENT_DATA: the check could not be completed safely — most commonly an ambient_temp input that could not be translated to a junction-temperature check (see the temperature note below). INSUFFICIENT_DATA never counts as a PASS: it pulls the overall verdict down to at-least-WARNING. Each check also reports 'limit_type' (max / min / range / fixed) so you can see whether it was judged against an operating range, an absolute-max rating, or a fixed-output setpoint. Temperature honesty: - ambient_temp is NOT silently treated as a junction temperature. The stored operating-temperature limit is junction-suspect, so a bare ambient input is never reported as a clean PASS on thermal grounds. If you also supply input_voltage, output_voltage and output_current AND a thermal-resistance (RthJA) value is available, the tool estimates Tj = Ta + Pd·RthJA (Pd ≈ (Vin-Vout)·Iout, a documented approximation) and checks the junction estimate — reported as 'temperature (junction est.)' with the assumptions in the note. Otherwise the temperature check returns INSUFFICIENT_DATA asking you to pull RthJA via read_datasheet. The 'temperature_basis' field (junction / ambient / unknown) tells you which basis was used. Behavior: - Two-tier validation. For parameters in our structured database (Vin, Iout, operating temp, etc.), returns instantly and free of LLM cost. For parameters only found in the datasheet text, falls back to an LLM read of the absolute-max and recommended-operating-conditions sections. The 'validation_method' field in the response tells you which path was used. - If the part hasn't been extracted yet and the LLM fallback is needed, this call triggers extraction (30s-2min). Returns status='extracting' if so — poll check_extraction_status and retry. When NOT to use: - You need power dissipation or junction-temperature rise — this tool only checks nameplate limits. Pull RthJA from read_datasheet and calculate yourself. - You need SOA (safe-operating-area) curve checks for MOSFETs — use analyze_image on the SOA graph. - You're checking a passive or mechanical part with no abs-max table — there's nothing for this tool to compare against. Example: check_design_fit('TPS54302', input_voltage=24, output_current=2.5, ambient_temp=70)

Parameters (7)

part_numberstringrequired
Specific manufacturer part number to validate. Not a value or description.
input_voltagenumber
Input voltage / VIN (V). For converters.
output_voltagenumber
Output voltage / VOUT (V). For converters/LDOs.
output_currentnumber
Output current / IOUT (A). For MOSFETs, this is drain current ID.
supply_voltagenumber
Supply voltage / VCC / VDD (V). For MOSFETs, this is VDS (drain-source voltage). NOT used for power dissipation — compared against VDS(max) only.
ambient_tempnumber
Ambient temperature TA (°C).
switching_frequencynumber
Switching frequency FSW (kHz). For converters.

analyze_image

Analyze an image from a component's datasheet using vision AI. Use this when read_datasheet returns a section containing images and you need to extract data from a graph, package drawing, pin diagram, or circuit schematic. Pass the image_key from the read_datasheet response (the storage path in the image URL). Optionally pass a specific question to focus the analysis. IMPORTANT: For precise numeric values (electrical specs, max ratings), prefer read_datasheet text tables first — they are more reliable than vision-extracted graph data. Use analyze_image for visual information not available in text: package dimensions from drawings, pin assignments from diagrams, graph trends, and approximate values from characteristic curves. Examples: - analyze_image(part_number='IRFZ44N', image_key='images/abc123.png') -> classifies and describes the image - analyze_image(part_number='IRFZ44N', image_key='images/abc123.png', question='What is the drain current at Vgs=5V?')

Parameters (3)

part_numberstringrequired
MPN of the component
image_keystringrequired
Image storage path from read_datasheet output (e.g. 'images/abc123.png')
questionstring
Optional specific question about the image (e.g. 'What are the package dimensions?')

find_alternative

Find alternative / second-source components for a given MPN. Returns parts ranked by how closely their specs, package, and category match the reference part, with a match_score and match_notes explaining each match. When to use: - Original part is out of stock or end-of-life. - You need a cheaper equivalent with similar specs. - You need a second source for supply-chain resilience. - You need a drop-in replacement on an existing PCB (use constraints=['same_package']). When NOT to use: - You're browsing a category from scratch — use search_parts. - You already have candidates and want a head-to-head comparison — use compare_parts directly. Behavior: - Eval boards, dev kits, and breakout modules are filtered out — results are IC-level alternatives only. - 'same_package' uses fuzzy matching, so SOT-23 ≡ SOT23, SOIC-8 ≡ SOP-8, LQFP64 ≡ TQFP64, etc. Exact string match is not required. - If provider search returns few candidates, the tool falls back to semantic search across extracted datasheets to surface niche alternatives. - The response includes a 'hint' field pointing to compare_parts / read_datasheet for drilling into promising alternatives. Example: find_alternative('TPS54302', constraints=['same_package', 'in_stock']) DATASHEET STATUS VALUES: - 'ready' — extracted and indexed; call read_datasheet, search_datasheets, or analyze_image. - 'extracting' / 'in_progress' / 'queued' / 'pending' — extraction running or scheduled. Poll check_extraction_status every 5-10s until 'ready' or 'failed'. Typical time: 30s-2min. - 'not_extracted' — known part but datasheet hasn't been fetched yet. Trigger it via prefetch_datasheets (cheapest) or by calling read_datasheet (auto-triggers on first read). - 'no_source' — we couldn't find a public datasheet URL for this MPN. First, retry prefetch_datasheets in 10-30s (the URL resolver re-runs and often finds a source on the second pass). If still 'no_source', the agent can upload the PDF manually via request_datasheet_upload + confirm_datasheet_upload (see those tools). Org-uploaded datasheets are private to the org. - 'unsupported' — PDF exists but can't be extracted (scanned image-only, encrypted, or corrupted). Upload a clean text-based PDF via request_datasheet_upload to override. - 'failed' / 'error' — extraction errored. The response includes the error reason. Retry via prefetch_datasheets or escalate to support. - 'rejected' — input wasn't a real MPN (bare value like '100nF', description, or reference designator). Fix the input and re-call. - 'deduplicated' — another part in the family already has this datasheet; same content is returned under the primary MPN.

Parameters (3)

part_numberstringrequired
The MPN to find alternatives for
constraintsarray
Optional filters to narrow alternatives. 'in_stock' = only parts with non-zero stock at any provider. 'same_package' = package footprint must match (fuzzy). 'jlcpcb' = must be available at JLCPCB (useful for JLCPCB-assembled boards — also restricts the provider search to JLCPCB).
limitinteger
Max alternatives to return (default 5, max 20).

request_datasheet_upload

Request a signed URL to upload a datasheet PDF for a component whose datasheet we don't have. Use this when search_parts / get_part_details / prefetch_datasheets return datasheet_status='no_source' (and a retry didn't help) or 'unsupported'. Free — the upload fee is only charged on confirm_datasheet_upload after we validate the file. Flow (3 steps): 1. Call request_datasheet_upload with the MPN, the file's SHA-256, and its byte size. You get back an upload_url, upload_method ('PUT'), upload_headers, and an opaque upload_token. 2. Upload the PDF directly to the returned URL with curl: `curl -X PUT -H 'Content-Type: application/pdf' --data-binary @file.pdf "$UPLOAD_URL"` (add any headers from upload_headers). 3. Call confirm_datasheet_upload with the upload_token. Server verifies the bytes, re-hashes, checks for the MPN on the first page, charges the upload fee (50¢), and queues extraction. Returns document_id + status='pending'. Validation rules (checked at confirm time, refunded on failure): - File must be a valid PDF (magic bytes + parseable). - Actual SHA-256 must match expected_sha256. - Actual byte size must match size_bytes (±0). - MPN or its core stem must appear in the first page text (catches wrong-file uploads). Scanned image-only PDFs will fail this check — upload a text-based PDF. - Max 50MB per file. No dev-kit manuals / BOB schematics / app-notes as datasheets — use the matching MPN's actual datasheet. Uploaded datasheets are scoped to your organization (private). They satisfy read_datasheet, search_datasheets, check_design_fit, and analyze_image for your org's tokens only. Tokens expire after 15 minutes. If upload fails or times out, just call request_datasheet_upload again.

Parameters (4)

part_numberstringrequired
Manufacturer part number the PDF belongs to. Must be a real MPN, not a value or description.
expected_sha256stringrequired
Lowercase hex SHA-256 of the PDF bytes (64 chars). Used both as the storage key (content-addressed) and to detect tampering. Compute with `shasum -a 256 file.pdf`.
size_bytesintegerrequired
Size of the PDF in bytes. Must be ≤ 50_000_000 (50MB) and > 1024.
manufacturerstring
Optional. Manufacturer name (e.g. 'Texas Instruments') if the MPN alone doesn't disambiguate.

confirm_datasheet_upload

Confirm a datasheet upload started via request_datasheet_upload. Pass the upload_token you got back from the request step. The server downloads the uploaded bytes, re-hashes to verify integrity, validates that it's a real PDF with the MPN on the first page, creates the private Document + Component records, charges the upload fee (50¢), and queues extraction. Success response: document_id, mpn, sha256, file_size_bytes, status='pending'. Poll check_extraction_status with the MPN to wait for extraction to finish (30s-2min typically). Failure modes: - 'upload_not_found' — no bytes at the upload URL yet. Retry your curl upload. - 'sha256_mismatch' — uploaded bytes hash differs from expected_sha256. Re-compute the hash and re-request. - 'invalid_pdf' — bytes aren't a parseable PDF. No charge. - 'mpn_not_in_pdf' — MPN (or its stem) isn't on the first page. Either you uploaded the wrong file or it's a scanned image-only PDF. No charge. - 'token_expired' — upload token is older than 15 minutes. Restart via request_datasheet_upload.

Parameters (1)

upload_tokenstringrequired
Opaque token returned by request_datasheet_upload.

README.md15 KBView on GitHub

SheetsData MCP

Electronic component datasheets for AI agents — specs, pinouts, package data on demand. No PDFs required.

SheetsData is an MCP server that gives AI agents instant, structured access to electronic component data. One tool call returns the pinout. Another returns electrical specs. No PDFs. No uploads. No context window stuffing.

Beta — SheetsData is currently in public beta. APIs, pricing, and features may change. See Disclaimer below.

<p align="center"> <a href="https://sheetsdata.com/signup">Sign up & connect via OAuth</a>  ·  <a href="https://sheetsdata.com/dashboard/keys">API key (fallback)</a>  ·  <a href="https://sheetsdata.com">Website</a> </p>

Demo

code

Agent: read_datasheet("TPS54302", section="pinout")
→ Pin table: BOOT(6), EN(5), FB(4), GND(1), SW(2), VIN(3)

Agent: check_design_fit("TPS54302", input_voltage=12, output_current=2)
→ PASS — all parameters within datasheet limits

Agent: "What's the maximum SPI clock frequency for the STM32G030?"
→ Uses read_datasheet to find electrical specs — returns 32 MHz

Agent: find_alternative("TPS54302", constraints="in_stock")
→ MP2315, TPS54331 ranked by package/spec match

The agent never sees a PDF. The engineer never uploads one.

Tools

Tool	Description
`search_parts`	Search for components by part number or keyword. Results merged by MPN with pricing and stock.
`search_datasheets`	Semantic search across all extracted datasheets. Natural language queries like "low-noise LDO with PSRR above 70dB".
`prefetch_datasheets`	Batch warm-up extraction for up to 20 parts. Fire-and-forget — reduces wait times.
`check_extraction_status`	Poll extraction progress after prefetch or read_datasheet.
`get_part_details`	Full component details — specs, parameters, pricing, and stock.
`read_datasheet`	Structured datasheet sections (summary, pinout, electrical, abs_max, package) or semantic search within a datasheet.
`compare_parts`	Compare 2–5 parts side by side on real datasheet specs.
`check_design_fit`	Validate operating conditions against datasheet limits. PASS/FAIL/WARNING per parameter.
`find_alternative`	Find alternative/substitute components by specs, package, or availability.
`analyze_image`	Vision AI analysis of datasheet images — graphs, package drawings, pin diagrams.
`request_datasheet_upload`	Request a signed URL to upload a datasheet PDF when we don't have one (`datasheet_status` = `no_source` or `unsupported`). Free — fee is only charged on confirm.
`confirm_datasheet_upload`	Confirm an upload: verifies SHA-256, validates PDF, checks MPN on first page, charges the upload fee, and queues extraction. Datasheets are private to your org.

Prompts

Built-in prompt templates that guide the agent through common hardware engineering tasks:

Prompt	Description
`component-selection`	Walk through selecting a component: define requirements, search candidates, compare specs, validate design fit.
`bom-review`	Review a bill of materials: look up each part, check stock and lifecycle, flag risks, suggest alternatives.
`datasheet-deep-dive`	Deep-dive into a specific part: summarize, extract pinout, electrical specs, absolute max ratings, and application circuit.
`design-validation`	Validate a design: check each component against operating conditions, flag out-of-spec parameters.
`second-source`	Find second-source alternatives for a part: match package, specs, and availability across providers.
`interface-check`	Check electrical and protocol compatibility between two ICs on a shared bus (SPI, I2C, UART). Verifies VOH/VOL vs VIH/VIL, flags level-shifter needs, extracts protocol config (SPI mode, I2C address, pull-up values).
`firmware-kickstart`	Extract register map, init sequence, and protocol details from a peripheral IC datasheet. Generates a firmware integration guide with register writes, transaction examples, and common pitfalls.
`thermal-review`	Thermal and derating analysis: compare operating conditions against abs max AND recommended limits, estimate junction temperature, check SOA derating curves, flag exposed-pad requirements.

Resources

Data the server exposes for agent context:

Resource	Description
`sheetsdata://workflow`	Recommended tool workflow for component selection — search, evaluate, read datasheet, validate, compare.
`sheetsdata://tips/datasheet-pitfalls`	The 8 most common datasheet interpretation mistakes — abs max confusion, typical vs worst-case, thermal derating, voltage levels, I2C/SPI gotchas, decoupling, exposed pads, lifecycle risks.
`sheetsdata://tips/design-review-checklist`	Hardware design review checklist covering power supply, signal interfaces, component selection, and firmware integration.

Authentication — pick OAuth, fall back to API key

SheetsData supports two auth paths. Use whichever works best for your client; both bill against the same org.

	OAuth 2.0	API key
Best for	Interactive MCP clients (Claude Desktop, Cursor, etc.)	CI, scripts, headless agents, or clients that don't speak MCP OAuth
What you do	Click Connect in your client → log in here → done	Generate a key in the dashboard, paste as a `Bearer` header
Setup	Just paste a URL	Paste a URL + a header
Discovery	Automatic via RFC 8414 / RFC 9728	n/a
Spec compliance	PKCE-mandatory, dynamic client registration (RFC 7591), refresh-token rotation	RFC 6750 Bearer
Revoke	Per-client, from `/dashboard/keys`	Delete the key

Recommended: OAuth. It's a single URL paste, no copy-pasting secrets, and you can yank a connected app from the dashboard at any time.

Quickest paths (one-click install)

Claude Desktop — download the .mcpb bundle from the latest GitHub release and drag-and-drop it into the Claude Desktop window. The install dialog will surface every tool the bundle provides before confirming. Leave the API key field blank to use OAuth (recommended) — Claude Desktop will open a browser tab on first use to authorize. No JSON editing.

Cursor or VS Code — single-click install pre-fills the config and prompts to authorize on first use.

For everything else, copy the snippet from the right section below.

Install

Claude Desktop

Easiest — drag-and-drop the bundled extension. Download the latest sheetsdata-x.y.z.mcpb from the Releases page and drop the file onto the Claude Desktop window. Claude shows the list of tools the bundle provides and installs it. Leave the API key field blank to use OAuth (recommended) — a browser tab opens on first use to authorize. No JSON editing, no npm install.

Or — add a remote connector via the UI. Open Claude Desktop → Settings → Connectors → Add custom connector at the bottom of the list.

Field	Value
Name	`SheetsData`
URL	`https://mcp.sheetsdata.com/mcp`

Click Add. Claude Desktop will open a browser tab to the SheetsData consent screen — pick the org to authorize, and you're done. Tools appear in Claude immediately.

Note: The claude_desktop_config.json file does not support the OAuth flow on Claude Desktop. The Connectors UI is the right path for OAuth — only fall back to the JSON config if you want to use an API key instead.

<details> <summary>Use an API key instead (via JSON config)</summary>

Open Claude Desktop → Settings → Developer → Edit Config, then add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

json

{
  "mcpServers": {
    "sheetsdata": {
      "url": "https://mcp.sheetsdata.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

Restart Claude Desktop. Get a key from sheetsdata.com/dashboard/keys.

</details>

Claude Code

bash

claude mcp add sheetsdata --transport http "https://mcp.sheetsdata.com/mcp"

Claude Code will print a one-time OAuth URL — open it, authorize, done.

<details> <summary>Use an API key instead</summary>

bash

claude mcp add sheetsdata \
  --transport http \
  "https://mcp.sheetsdata.com/mcp" \
  --header "Authorization: Bearer YOUR_API_KEY"

</details>

Cursor

Click the Install in Cursor badge above, or add to .cursor/mcp.json:

json

{
  "mcpServers": {
    "sheetsdata": {
      "url": "https://mcp.sheetsdata.com/mcp"
    }
  }
}

Restart Cursor → MCP panel → SheetsData → Connect.

<details> <summary>Use an API key instead</summary>

json

{
  "mcpServers": {
    "sheetsdata": {
      "url": "https://mcp.sheetsdata.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

</details>

VS Code (GitHub Copilot)

Click the Install in VS Code badge above, or add to .vscode/mcp.json:

json

{
  "servers": {
    "sheetsdata": {
      "type": "http",
      "url": "https://mcp.sheetsdata.com/mcp"
    }
  }
}

VS Code will prompt you to authorize on first use.

<details> <summary>Use an API key instead</summary>

json

{
  "servers": {
    "sheetsdata": {
      "type": "http",
      "url": "https://mcp.sheetsdata.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

</details>

Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

json

{
  "mcpServers": {
    "sheetsdata": {
      "url": "https://mcp.sheetsdata.com/mcp"
    }
  }
}

Restart Windsurf and click Connect on the SheetsData entry.

<details> <summary>Use an API key instead</summary>

json

{
  "mcpServers": {
    "sheetsdata": {
      "url": "https://mcp.sheetsdata.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

</details>

Amp (Sourcegraph)

Add to your Amp settings:

json

{
  "amp.mcpServers": {
    "sheetsdata": {
      "url": "https://mcp.sheetsdata.com/mcp"
    }
  }
}

Amp will run the OAuth flow on first use.

<details> <summary>Use an API key instead</summary>

json

{
  "amp.mcpServers": {
    "sheetsdata": {
      "url": "https://mcp.sheetsdata.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

</details>

Cline

Cline doesn't yet support the MCP OAuth flow — use an API key.

In VS Code, open Cline → gear icon → MCP Servers:

json

{
  "mcpServers": {
    "sheetsdata": {
      "url": "https://mcp.sheetsdata.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      },
      "disabled": false
    }
  }
}

Zed

Zed doesn't yet support the MCP OAuth flow — use an API key.

Add to Zed settings.json:

json

{
  "context_servers": {
    "sheetsdata": {
      "settings": {
        "url": "https://mcp.sheetsdata.com/mcp",
        "headers": {
          "Authorization": "Bearer YOUR_API_KEY"
        }
      }
    }
  }
}

Continue.dev

Continue doesn't yet support the MCP OAuth flow — use an API key.

Add to ~/.continue/config.yaml:

yaml

mcpServers:
  - name: sheetsdata
    url: https://mcp.sheetsdata.com/mcp
    headers:
      Authorization: "Bearer YOUR_API_KEY"

npx (stdio proxy for any client)

For clients that only support stdio transport:

bash

SHEETSDATA_API_KEY=your_key npx @sheetsdata/mcp

Need an API key?

Sign up at sheetsdata.com/signup (30 seconds, free credits)
Go to Dashboard → API Keys
Click Create key, copy the token, paste it into your config

You can also manage OAuth-authorized apps from the same page — see who has connected, when, and revoke any of them with one click.

Recommended Workflow

code

1. search_parts       → Find candidates by keyword or part number
2. get_part_details    → Evaluate pricing, stock, parameters
3. read_datasheet      → Get detailed specs (pinout, electrical, package)
4. check_design_fit    → Validate against your operating conditions
5. find_alternative    → Find substitutes if needed
6. compare_parts       → Side-by-side comparison of finalists

Support

Email: support@octoco.ltd
Issues: github.com/octoco-ltd/sheetsdata-mcp/issues
Website: sheetsdata.com

Disclaimer

SheetsData is currently in public beta. Data is extracted from publicly available manufacturer datasheets using automated tools including AI. It may contain errors, omissions, or inaccuracies.

SheetsData and Octoco Ltd provide this data on an "as is" basis and make no warranties, express or implied, regarding the accuracy, completeness, or fitness for any particular purpose. Always verify critical specifications against the official manufacturer datasheet before making design, purchasing, or manufacturing decisions.

By using this service, you acknowledge that:

Extracted data may differ from the original manufacturer datasheet
SheetsData is not a substitute for reviewing official documentation
Octoco Ltd is not liable for any damages, losses, or design failures arising from the use of this data
Features, APIs, and pricing are subject to change during the beta period

For terms of use, see sheetsdata.com/terms.

License

MIT

Install

Configuration

Environment variables

SHEETSDATA_API_KEYsecret

Optional — if omitted, OAuth login opens in your browser. Get a key at https://sheetsdata.com/dashboard/keys

claude_desktop_config.json

{
  "mcpServers": {
    "sheetsdata-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@sheetsdata/mcp@1.3.2"
      ],
      "env": {
        "SHEETSDATA_API_KEY": "<YOUR_SHEETSDATA_API_KEY>"
      }
    }
  }
}