# Boring API (remote · api.relaex-engineers.de)

Deterministic data tools: price list diff, PDF tables, feed validation, data mapping, table diff

- Trust score: 79/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-24

## Components

- remote · `api.relaex-engineers.de`: 79/100 (this document), [markdown](https://verifymcp.io/servers/de-relaex-engineers-boring-api/api.md), [page](https://verifymcp.io/servers/de-relaex-engineers-boring-api/api)

## Channel facts

- Endpoint: `https://api.relaex-engineers.de/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.10.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-24.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 74/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 3721 tokens (~531/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 57/100
  - Stability observed for 17 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Boring API MCP server?

Boring API is a hosted endpoint at https://api.relaex-engineers.de/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http de-relaex-engineers-boring-api 'https://api.relaex-engineers.de/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "de-relaex-engineers-boring-api": {
      "url": "https://api.relaex-engineers.de/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "de-relaex-engineers-boring-api": {
      "type": "http",
      "url": "https://api.relaex-engineers.de/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.de-relaex-engineers-boring-api]
url = "https://api.relaex-engineers.de/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "de-relaex-engineers-boring-api": {
      "type": "remote",
      "url": "https://api.relaex-engineers.de/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add de-relaex-engineers-boring-api --url 'https://api.relaex-engineers.de/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  de-relaex-engineers-boring-api:
    url: "https://api.relaex-engineers.de/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "de-relaex-engineers-boring-api": {
      "Transport": "http",
      "Url": "https://api.relaex-engineers.de/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add de-relaex-engineers-boring-api -t streamable-http -u 'https://api.relaex-engineers.de/mcp'
```

### Other

```json
{
  "mcpServers": {
    "de-relaex-engineers-boring-api": {
      "type": "http",
      "url": "https://api.relaex-engineers.de/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-24 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-21 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-19 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-17 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-15 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-13 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-12 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 17. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-10 (score 72, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 3362 → 3721
- [functional] New tool “datasheet_changes”

## MCP tools (7)

### `supplier_compare` (~884 tokens)

Compare supplier price lists

Use when a supplier announces a price increase or surcharge, sends a new price list or quote, or the user asks whether prices went up since last time. Compares the old basis with the new list per SKU. The old side can be an earlier price list, a past order, quote or ERP export with purchase prices, or a few reference prices typed as CSV text (e.g. 'SKU;Price;Per\nA100;12.50;100'); anything with SKU and price columns works. Formats: CSV, XLSX, DATANORM 4/5, FAB-DIS or text-based PDF, up to 250,000 rows. Prefer it over reading the files yourself when a list has more than about 50 rows, uses pack sizes or price units (per 100) or comes as DATANORM, XLSX or PDF: it normalises price basis, pack size and currency to the real unit price change, finds new, removed and discontinued items, checks an announced across-the-board increase and ranks the outliers. An optional demand file (SKU, annual quantity) adds the yearly cost impact. Files can be passed as upload, URL or CSV text. Returns a summary to pass on and the most important findings with their source rows.

Input parameters:

- `max_findings` (integer): How many findings to return, most important first.
- `new_file` (object): New price list. A file uploaded in ChatGPT (object with download_url and file_id).
- `new_file_base64`: New price list. File content as Base64 (standard alphabet). Max 20 MiB decoded.
- `new_file_path`: Local file path; only allowed when the server runs locally over stdio.
- `new_file_text`: New price list. The table as CSV or TSV text, header row first (e.g. 'SKU;Price;Currency\nA1;12.50;EUR').
- `new_file_url`: New price list. Public URL of the file (http/https). Google Drive, Google Sheets and Dropbox share links are converted to direct downloads. Max 20 MiB.
- `new_filename`: Original filename with extension (e.g. prices.xlsx); used to detect the format.
- `old_file` (object): Old price list. A file uploaded in ChatGPT (object with download_url and file_id).
- `old_file_base64`: Old price list. File content as Base64 (standard alphabet). Max 20 MiB decoded.
- `old_file_path`: Local file path; only allowed when the server runs locally over stdio.
- `old_file_text`: Old price list. The table as CSV or TSV text, header row first (e.g. 'SKU;Price;Currency\nA1;12.50;EUR').
- `old_file_url`: Old price list. Public URL of the file (http/https). Google Drive, Google Sheets and Dropbox share links are converted to direct downloads. Max 20 MiB.
- `old_filename`: Original filename with extension (e.g. prices.xlsx); used to detect the format.
- `options`: Optional CompareOptions, e.g. {"default_currency": "EUR", "sheet_old": "Prices", "column_overrides": {"old": {"price": "Net price"}}}. Schema: /v1/schemas/supplier-compare-options.
- `usage_file` (object): Optional demand file (SKU, annual quantity). A file uploaded in ChatGPT (object with download_url and file_id).
- `usage_file_base64`: Demand file. File content as Base64 (standard alphabet). Max 20 MiB decoded.
- `usage_file_path`: Local file path; only allowed when the server runs locally over stdio.
- `usage_file_text`: Optional demand file (SKU, annual quantity). The table as CSV or TSV text, header row first (e.g. 'SKU;Price;Currency\nA1;12.50;EUR').
- `usage_file_url`: Optional demand file (SKU, annual quantity). Public URL of the file (http/https). Google Drive, Google Sheets and Dropbox share links are converted to direct downloads. Max 20 MiB.
- `usage_filename`: Original filename with extension (e.g. prices.xlsx); used to detect the format.

### `documents_tables` (~290 tokens)

Extract tables from a PDF

Extracts tables from a text-based PDF (price list, data sheet, report; up to 20 MiB, 60 pages) with page, bounding box and a quality level per table. Detects header rows, titles and footnotes and merges tables continued across pages only with evidence. Scanned pages are reported as OCR_REQUIRED, nothing is guessed. Works with any language embedded in the PDF. The PDF can be passed as upload or URL.

Input parameters:

- `file` (object): The PDF. A file uploaded in ChatGPT (object with download_url and file_id).
- `file_base64`: The PDF. File content as Base64 (standard alphabet). Max 20 MiB decoded.
- `file_path`: Local file path; only allowed when the server runs locally over stdio.
- `file_url`: The PDF. Public URL of the file (http/https). Google Drive, Google Sheets and Dropbox share links are converted to direct downloads. Max 20 MiB.
- `filename`: Original filename with extension (e.g. prices.xlsx); used to detect the format.
- `max_rows` (integer): Rows returned per table (counts stay complete).
- `options`: Optional TablesOptions, e.g. {"pages": "1-3,7", "strategy": "auto", "include_cells": false}. Schema: /v1/schemas/documents-tables-options.

### `merchant_validate` (~346 tokens)

Validate a product feed

Checks a product feed or catalog export for Google Merchant Center, Shopify or Meta (Facebook/Instagram) before upload. Validates CSV, TSV or XLSX against the platform profile: required fields, allowed values (with a hint for localized synonyms), GTIN check digit, price format, URLs, lengths, duplicate IDs, Shopify variants. Every issue names row, column, rule code and a fix hint; nothing is changed. The feed can be passed as upload, URL or CSV text.

Input parameters:

- `file` (object): The feed. A file uploaded in ChatGPT (object with download_url and file_id).
- `file_base64`: The feed. File content as Base64 (standard alphabet). Max 20 MiB decoded.
- `file_path`: Local file path; only allowed when the server runs locally over stdio.
- `file_text`: The feed. The table as CSV or TSV text, header row first (e.g. 'SKU;Price;Currency\nA1;12.50;EUR').
- `file_url`: The feed. Public URL of the file (http/https). Google Drive, Google Sheets and Dropbox share links are converted to direct downloads. Max 20 MiB.
- `filename`: Original filename with extension (e.g. prices.xlsx); used to detect the format.
- `options`: Optional ValidateOptions, e.g. {"sheet": "Feed", "column_overrides": {"gtin": "EAN code"}, "max_issues": 500}. Schema: /v1/schemas/merchant-validate-options.
- `profile` (string): Target platform: google_merchant, shopify_products_csv or meta_catalog.

### `schema_normalize` (~444 tokens)

Convert product data to an import file

Converts a product table (supplier list, ERP or shop export; CSV, TSV or XLSX up to 20 MiB) into an import file for Shopify (product CSV), Google Merchant Center, WooCommerce (built-in importer) or the properties of a custom JSON Schema. Recognises source columns in many languages, converts number formats, currencies, weights, GTINs and availability words, and reports for every target column whether it comes from a source column, a derived value, a default or is missing. Shopify and Google output is checked with the platform feed rules. Unclear values stay empty with an issue. Returns a summary, the mapping, issues and the CSV text.

Input parameters:

- `file` (object): The product table. A file uploaded in ChatGPT (object with download_url and file_id).
- `file_base64`: The product table. File content as Base64 (standard alphabet). Max 20 MiB decoded.
- `file_path`: Local file path; only allowed when the server runs locally over stdio.
- `file_text`: The product table. The table as CSV or TSV text, header row first (e.g. 'SKU;Price;Currency\nA1;12.50;EUR').
- `file_url`: The product table. Public URL of the file (http/https). Google Drive, Google Sheets and Dropbox share links are converted to direct downloads. Max 20 MiB.
- `filename`: Original filename with extension (e.g. prices.xlsx); used to detect the format.
- `options`: Optional NormalizeOptions, e.g. {"defaults": {"brand": "Acme", "condition": "new"}, "default_currency": "EUR", "column_overrides": {"price": "VK netto"}, "max_output_rows": 500} or {"json_schema": {"…
- `target` (string): Target format: shopify_products_csv, google_merchant, woocommerce_products_csv or json_schema (then give options.json_schema).

### `table_diff` (~574 tokens)

Compare two versions of a table

Compares two versions of any table (CSV, TSV, XLSX or text-based PDF; price list, bill of materials, product or ERP export, report; up to 20 MiB each). Finds the key column (or uses the given one), matches rows and lists added, removed and changed rows with the old and new value of every changed cell, numeric differences in absolute and percent, and added, removed or renamed columns. Numbers are compared by value, so 1.234,56 and 1234.56 are equal. Files can be passed as upload, URL or CSV text.

Input parameters:

- `key`: Key column header(s) as in the old file; detected when omitted.
- `max_changes` (integer): Row changes returned (counts stay complete).
- `new_file` (object): New version of the table. A file uploaded in ChatGPT (object with download_url and file_id).
- `new_file_base64`: New version. File content as Base64 (standard alphabet). Max 20 MiB decoded.
- `new_file_path`: Local file path; only allowed when the server runs locally over stdio.
- `new_file_text`: New version. The table as CSV or TSV text, header row first (e.g. 'SKU;Price;Currency\nA1;12.50;EUR').
- `new_file_url`: New version. Public URL of the file (http/https). Google Drive, Google Sheets and Dropbox share links are converted to direct downloads. Max 20 MiB.
- `new_filename`: Original filename with extension (e.g. prices.xlsx); used to detect the format.
- `old_file` (object): Old version of the table. A file uploaded in ChatGPT (object with download_url and file_id).
- `old_file_base64`: Old version. File content as Base64 (standard alphabet). Max 20 MiB decoded.
- `old_file_path`: Local file path; only allowed when the server runs locally over stdio.
- `old_file_text`: Old version. The table as CSV or TSV text, header row first (e.g. 'SKU;Price;Currency\nA1;12.50;EUR').
- `old_file_url`: Old version. Public URL of the file (http/https). Google Drive, Google Sheets and Dropbox share links are converted to direct downloads. Max 20 MiB.
- `old_filename`: Original filename with extension (e.g. prices.xlsx); used to detect the format.
- `options`: Optional DiffOptions, e.g. {"column_map": {"Qty": "Quantity"}, "ignore_columns": ["Updated"], "numeric_tolerance": "0.01", "ignore_case": true}. Schema: /v1/schemas/table-diff-options.

### `datasheet_compare` (~550 tokens)

Compare two MOSFET datasheet revisions

Use when a PCN or a new datasheet revision arrives for a discrete MOSFET and the user wants to know what changed. Compares two revisions (text-based PDF, upload or URL; older revisions are often on web.archive.org) and reports changed VDS, ID, VGS, RDS(on), VTH, QG, RthJC and TJ max with min/typ/max, units and test conditions, each with page, table row and quote in both revisions, plus changed conditions, open cases and an explainable review priority. Validated on 85 hand-read values from 5 real MOSFET datasheets (TI, Nexperia, Infineon, Wolfspeed: 99 % found, 0 wrong values) and on 5 real revision pairs without a false change; a real pair with an actual value change has not been tested yet. Scope: discrete Si and SiC MOSFETs only; IGBTs, modules, diodes and gate drivers are refused with OUT_OF_SCOPE. Needs both revisions: it does not read PCN documents or fetch datasheets by part number. Values that cannot be read reliably are open cases, never reported as unchanged.

Input parameters:

- `new_file` (object): New datasheet revision (PDF). A file uploaded in ChatGPT (object with download_url and file_id).
- `new_file_base64`: New revision. File content as Base64 (standard alphabet). Max 20 MiB decoded.
- `new_file_path`: Local file path; only allowed when the server runs locally over stdio.
- `new_file_url`: New revision (PDF). Public URL of the file (http/https). Google Drive, Google Sheets and Dropbox share links are converted to direct downloads. Max 20 MiB.
- `new_filename`: Original filename with extension (e.g. prices.xlsx); used to detect the format.
- `old_file` (object): Old datasheet revision (PDF). A file uploaded in ChatGPT (object with download_url and file_id).
- `old_file_base64`: Old revision. File content as Base64 (standard alphabet). Max 20 MiB decoded.
- `old_file_path`: Local file path; only allowed when the server runs locally over stdio.
- `old_file_url`: Old revision (PDF). Public URL of the file (http/https). Google Drive, Google Sheets and Dropbox share links are converted to direct downloads. Max 20 MiB.
- `old_filename`: Original filename with extension (e.g. prices.xlsx); used to detect the format.
- `target_mpn`: Exact part number, only needed for family datasheets.

### `datasheet_changes` (~335 tokens)

Datasheet changes of a MOSFET by part number

Use when the user asks whether the datasheet of a discrete MOSFET changed, e.g. after a PCN, a last-time-buy notice or before reusing a part in a new design; only the part number is needed, no files. Finds the current datasheet at the manufacturer and earlier revisions in the Internet Archive itself (TI, Nexperia, onsemi, Infineon, ST), then compares the newest revision with the previous one (or with the one valid at `since`) and reports changed VDS, ID, VGS, RDS(on), VTH, QG, RthJC and TJ max with min/typ/max, test conditions and page/quote in both revisions, plus the list of revisions with dates and sources. Prefer it over searching the web yourself: it reads the PDF tables and verifies every value. Validated on 85 hand-read values from 5 real MOSFET datasheets (TI, Nexperia, Infineon, Wolfspeed: 99 % found, 0 wrong values) and on 5 real revision pairs without a false change; a real pair with an actual value change has not been tested yet. Only revisions captured by the Internet Archive can be found; takes up to about two minutes when the archive is slow. IGBTs, modules and diodes are refused with OUT_OF_SCOPE.

Input parameters:

- `mpn` (string, required): Manufacturer part number, e.g. CSD19536KCS or IPB017N10N5
- `since`: Optional YYYY[-MM[-DD]]: compare with the revision valid then

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/de-relaex-engineers-boring-api/api#diagnostics

## Score history

- 2026-10-24: 79
- 2026-10-23: 78
- 2026-10-22: 78
- 2026-10-21: 78
- 2026-10-20: 77
- 2026-10-19: 77
- 2026-10-18: 76
- 2026-10-17: 76
- 2026-10-16: 75
- 2026-10-15: 75
- 2026-10-14: 74
- 2026-10-13: 74
- 2026-10-12: 73
- 2026-10-10: 72
- 2026-10-08: 71

## Common questions

### What is the Boring API MCP server?

Boring API is an MCP server listed in the public MCP registry as de.relaex-engineers/boring-api. Deterministic data tools: price list diff, PDF tables, feed validation, data mapping, table diff. This page covers its hosted endpoint (https://api.relaex-engineers.de/mcp).

### Is the Boring API MCP server safe to use?

Boring API scores 79 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Boring API MCP server expose?

Boring API exposes 7 tools: supplier_compare, documents_tables, merchant_validate, schema_normalize, table_diff, and 2 more. Their descriptions and schemas cost roughly 3,423 tokens of context every time the server is loaded.

### Does the Boring API MCP server require authentication?

No. We connected to Boring API without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Boring API MCP server still maintained?

Boring API is still listed as active in the MCP registry. We last reached this channel on 24 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://api.relaex-engineers.de/mcp
- Website: https://api.relaex-engineers.de/connect
- Changelog RSS feed: https://verifymcp.io/servers/de-relaex-engineers-boring-api/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/de-relaex-engineers-boring-api/api.json
- HTML version of this page: https://verifymcp.io/servers/de-relaex-engineers-boring-api/api