# Patchwell (remote · patchwell.io)

Cited web research, transcription with word timestamps, and CSV/Excel cleaning with a change log.

- Trust score: 84/100 (high trust)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `patchwell.io`: 84/100 (this document), [markdown](https://verifymcp.io/servers/io-patchwell-patchwell/patchwell.md), [page](https://verifymcp.io/servers/io-patchwell-patchwell/patchwell)

## Channel facts

- Endpoint: `https://patchwell.io/mcp/`
- Transports: `streamable-http`
- Auth: `required (not validated)`
- Version: `1.3.0`

## 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 2026-11-21.

- **Endpoint Security**: 89/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - 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 (good).
  - Context-footprint check failed: tool/resource definitions use about 1683 tokens (~280/item across 6 items; 5 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 47/100
  - Stability observed for 14 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.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.
  - Supports UI / widget rendering.

## Install

### How do I install the Patchwell MCP server?

Patchwell is a hosted endpoint at https://patchwell.io/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 io-patchwell-patchwell 'https://patchwell.io/mcp/'
```

### Cursor

```json
{
  "mcpServers": {
    "io-patchwell-patchwell": {
      "url": "https://patchwell.io/mcp/"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "io-patchwell-patchwell": {
      "type": "http",
      "url": "https://patchwell.io/mcp/"
    }
  }
}
```

### Codex

```toml
[mcp_servers.io-patchwell-patchwell]
url = "https://patchwell.io/mcp/"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "io-patchwell-patchwell": {
      "type": "remote",
      "url": "https://patchwell.io/mcp/",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add io-patchwell-patchwell --url 'https://patchwell.io/mcp/' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  io-patchwell-patchwell:
    url: "https://patchwell.io/mcp/"
```

### Netclaw

```json
{
  "McpServers": {
    "io-patchwell-patchwell": {
      "Transport": "http",
      "Url": "https://patchwell.io/mcp/"
    }
  }
}
```

### Vellum

```bash
assistant mcp add io-patchwell-patchwell -t streamable-http -u 'https://patchwell.io/mcp/'
```

### Other

```json
{
  "mcpServers": {
    "io-patchwell-patchwell": {
      "type": "http",
      "url": "https://patchwell.io/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.

### 2026-11-21 (score 84, +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.

### 2026-11-19 (score 83, +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.

### 2026-11-17 (score 82, +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.

### 2026-11-15 (score 81, +1)

- [security] Tool “research” rewrote its description, which is the text the model reads

### 2026-11-13 (score 80, +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.

### 2026-11-11 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-10 (score 78, 0)

- [security] Tool “transcribe” rewrote its description, which is the text the model reads
- [security] Tool “clean_data” rewrote its description, which is the text the model reads
- [security] Tool “get_job_result” rewrote its description, which is the text the model reads
- [security] Tool “research” rewrote its description, which is the text the model reads
- [security] Tool “transcribe” is now declared destructive
- [security] Tool “clean_data” is now declared destructive
- [security] Tool “research” is now declared destructive
- [cosmetic] “research” reworded the description of “context”
- [cosmetic] “get_job_result” reworded the description of “job_id”

### 2026-11-09 (score 78, +2)

- [functional] First check of Schema quality: 100
- [functional] Schema quality: excellent → good
- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

## MCP tools (5)

### `transcribe` (~313 tokens)

Transcribe speech in an audio or video file. Use it when you need the words in a recording, quotes with
        their time, who said what, or subtitles. Returns text, sentence segments, each word with start/end seconds,
        confidence and speaker (`spk`: 1, 2, ... told apart by voice), `turns` (speaker, start, end, text),
        `speakers` with talk time (and a `name` with its supporting quote when the recording says who someone is:
        "My name is...", "the next question comes from..."), SRT and VTT with speaker labels, and `flags` listing any phrase the guards removed (Whisper's invented phrases over silence and
        repetition loops) with its original text and time. Files over about 100 seconds of processing return
        {"status": "running", "job_id"}: call get_job_result with it. Price: $0.14 per audio hour, minimum $0.02 a file; failed
        downloads are free.

Input parameters:

- `language`: Two-letter language code such as en, es or ja. Leave it out to detect the language from the audio.
- `url` (string, required): Direct http(s) link to an audio or video file: mp3, wav, m4a, ogg, flac, mp4, mov, webm and most others. Up to 3 hours. YouTube page links don't work; pass the media file itself.

### `research` (~279 tokens)

Research a question on the live web and get an answer in which each sentence cites the page it came
        from. Use it for facts you can't answer from memory or that may have changed. Returns `answer` (sentences
        with [url] citations), `claims` (each sentence with its url and the quote found on that page), `sources`,
        `gaps` (what the sources couldn't confirm) and `confidence` (high/medium/low). About 73 seconds at the median, longer when the research model starts cold; a slow question
        returns {"status": "running", "job_id"} for get_job_result. Declines questions about private individuals and
        about anyone's personal details (where they live, contact details, family, health, finances, tracking
        someone) and returns a `category` saying why; public figures' public roles and statements are fine. Price:
        $0.15 per answered question; declined and unanswered questions are free.

Input parameters:

- `context` (string): Optional constraints the answer must respect, such as country, date range or audience. Leave out personal details.
- `question` (string, required): The question in plain language, up to 4,000 characters. Ask about topics, markets, products, prices, companies, regulations, places, events or published research.

### `listen_clip` (~72 tokens)

Used by the transcript card to play a spot the speaker labels are unsure of. Free.

Input parameters:

- `end` (number, required): End, in seconds (at most 20 s after start).
- `start` (number, required): Start, in seconds.
- `url` (string, required): The audio or video link that was transcribed.

### `get_job_result` (~120 tokens)

Fetch the result of a long transcribe or research call that returned {"status": "running", "job_id"}.
        Call it again every 20 to 30 seconds until status is 'done'; the finished result has the same shape as the
        original tool's. Patchwell settles the call's charge when the job finishes, whether you fetch it or not; a
        failed job costs nothing. This tool is free.

Input parameters:

- `job_id` (string, required): The job_id from a transcribe or research call that returned status 'running'.

### `clean_data` (~875 tokens)

Clean a messy spreadsheet or JSON export into typed, deduplicated records with a log of each change.
        Use it when a spreadsheet or export needs cleaning or deduplicating before analysis or import. It finds the header row, works out each
        column's type from the values (ids incl. barcodes/ISBN/IBAN check digits, emails, phones, dates, times,
        durations, money, percents, quantities with units, ZIP and postal codes, states, countries, US street
        addresses, coordinates, URLs, names, booleans), keeps leading zeros, reads European decimals, repairs
        broken encodings and merges duplicate records. It flags what deserves a look without changing it:
        disposable or role emails, phone numbers that can't exist, failed check digits. Returns `rows`, `changes`
        (row, column, before, after, rule), `review` (each with a `type`: invalid, conflict, possible_duplicate (a group of records that look
        like the same person or company, with a `confidence`, the evidence and the strongest pairs' likelihoods; never
        merged), shared_email (records sharing an email whose names, birth dates, ID numbers or Jr./Sr. say different
        people, kept apart), totals_row or note_row,
        and the reason),
        `columns` (with the evidence for each choice), `quality` (share of clean cells before and after),
        `clusters` (likely typos), a JSON `schema`, a reusable `recipe` and `stats`, whose counts always add up to
        the input rows. A file holding several tables (stacked, titled, or side by side) is split: the largest is
        the main result and every other table comes back cleaned under `other_tables`. Price: $0.50 per 1,000
        rows across all tables, minimum $0.01.

Input parameters:

- `content_base64` (string): The file itself, base64-encoded, for small files you hold locally. Use this or url.
- `dedupe_on`: Columns that identify a record; rows matching on them merge into one. Default: the email column, else the whole row.
- `filename` (string): File name with extension (e.g. customers.csv). Required with content_base64 so the format is known.
- `fix_email_typos` (boolean): Correct obvious typos in big mail providers (gmial.com -> gmail.com). Every fix is in the change log.
- `header_row`: The file line holding the column names, if the automatic choice is wrong (1 = first line).
- `hints`: Force a column's type, e.g. {"Joined": "date"}. Types: id, email, phone, date, datetime, time, duration, money, percent, number, quantity, zip, postcode, us_state, state, country, address, latitude,…
- `min_duplicate_confidence` (number): List look-alike records as possible duplicates from this likelihood (0-1). Default 0.5; 0.9 for only the near-certain ones; 1 means only the surest (99.5%).
- `phone_format` (string): 'national' like (415) 555-0100, or 'e164' like +14155550100.
- `phone_region` (string): Two-letter country for phone numbers written without a country code, e.g. US, GB, DE.
- `recipe`: The `recipe` from an earlier run. Pass it to clean a new file with the same column types and rules.
- `required`: Columns a row must have; rows missing one go to the review list.
- `sheet` (string): Excel only: the sheet to clean. Default: the first sheet with data.
- `table`: When the file holds several tables, which one is the main result (1 = first). Default: the largest; the others are in `other_tables`.
- `url` (string): Public http(s) link to a CSV, TSV, XLSX or JSON file, up to 100 MB. Use this or content_base64.

## Diagnostics

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

## Score history

- 2026-11-21: 84
- 2026-11-20: 83
- 2026-11-19: 83
- 2026-11-18: 82
- 2026-11-17: 82
- 2026-11-16: 81
- 2026-11-15: 81
- 2026-11-14: 80
- 2026-11-13: 80
- 2026-11-12: 79
- 2026-11-11: 79
- 2026-11-10: 78
- 2026-11-09: 78
- 2026-11-08: 76
- 2026-11-07: 76

## Common questions

### What is the Patchwell MCP server?

Patchwell is an MCP server listed in the public MCP registry as io.patchwell/patchwell. Cited web research, transcription with word timestamps, and CSV/Excel cleaning with a change log. This page covers its hosted endpoint (https://patchwell.io/mcp/).

### Is the Patchwell MCP server safe to use?

Patchwell scores 84 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 Patchwell MCP server expose?

Patchwell exposes 5 tools: transcribe, research, listen_clip, get_job_result, clean_data. Their descriptions and schemas cost roughly 1,659 tokens of context every time the server is loaded.

### Does the Patchwell MCP server require authentication?

Yes. Patchwell asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the Patchwell MCP server still maintained?

Patchwell is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Patchwell MCP server?

VerifyMCP ran 14 checks on Patchwell, covering TLS certificate, Authorization, HTTPS, HSTS header and 10 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://patchwell.io/mcp/
- Authorisation metadata: https://patchwell.io/.well-known/oauth-protected-resource/mcp
- Repository: https://github.com/aidan-mccollum/patchwell
- Website: https://patchwell.io/
- Changelog RSS feed: https://verifymcp.io/servers/io-patchwell-patchwell/patchwell.xml
- Changelog JSON feed: https://verifymcp.io/servers/io-patchwell-patchwell/patchwell/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/io-patchwell-patchwell/patchwell.json
- HTML version of this page: https://verifymcp.io/servers/io-patchwell-patchwell/patchwell
