Patchwell

io.patchwellPublished by patchwell.ioOfficial publisherv1.1.0Updated Nov 7, 2026

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

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingData & AnalyticsMedia & Design

Overview

AI-generated overview

Remote MCP server for cited web research, speaker-labelled transcription with word timestamps, and spreadsheet/JSON cleaning, billed per call.

What you can do
  • Research a question on the live web and get an answer where each sentence cites its source page, plus sources, gaps and a confidence grade
  • Transcribe audio or video URLs up to 3 hours into text, word-level timings, speaker turns, SRT and VTT
  • Clean messy CSV, Excel or JSON into typed, deduplicated rows with a log of every changed value, detected column types and a reusable recipe
  • Fetch the result of a long-running job by job id
When to use it
Useful when an assistant needs current facts it cannot answer from memory and must show where they came from, when you need transcripts with timings and speaker attribution, or when tabular data has to be normalised before analysis or import.
Requirements
A remote endpoint; no local install. A Patchwell API key sent as a bearer token in the Authorization header; a free trial key is available by email. Network access to the service. Paid per call, with credit purchased in advance.
Before you install
Calls cost money: research is charged per answered question, transcription per audio minute and cleaning per 1,000 rows, so usage spends prepaid credit. Audio and files are sent to a third-party service. Research questions are kept for 30 days unless retention is turned off per key or per request. Research declines questions about private individuals and may pause keys that keep asking.

Installation

In SourceWeft

  1. Open Patchwell in the dashboard and add it to a workspace.
  2. Connect Authorization token credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.patchwell%2Fpatchwell/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "patchwell": {
      "type": "http",
      "url": "https://patchwell.io/mcp/",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

README

[Patchwell]

Patchwell

Cited web research, transcription with word timestamps, and spreadsheet cleaning with a change log, for AI agents.
Remote MCP server and plain HTTP API. Pay per call, no subscription.

patchwell.io · Quickstart · API reference · MCP Registry

Tools

ToolWhat it returnsPrice
researchAn answer where each sentence cites the page it came from, what the sources couldn't confirm, and a confidence grade. Topics, markets, products, companies, regulations, published research. Won't look up private people.$0.15 per answered question. Declined or unanswered: free
transcribeText, word-level start/end times and confidence, who said each word (Speaker 1, 2, ..., or their name when the recording says it, with the quote as evidence), speaker turns, sentence segments, SRT and VTT with speaker tags. Audio or video URLs up to 3 hours. When Whisper invents a phrase or loops on a line, you get a flag with the original text and timestamps.$0.008 per audio minute
clean_dataClean rows from a CSV, Excel or JSON file, plus a log of every changed value, a review list, detected column types, a JSON Schema and a reusable recipe.$2 per 1,000 rows
get_job_resultThe result of a long job (anything over about 100 seconds returns a job_id).Free

Measured on real files: a 45-minute earnings call with 7 speakers took about 90 seconds, speaker labels included. On 24 public recordings (AMI meetings, VoxConverse debates and news, Earnings-21 calls), 97% of words were credited to the right speaker. A messy 352-row customer file took 2.2 seconds to clean, with 45 duplicates merged and 1,435 values fixed, each one logged. A research question takes about a minute.

Get a key

Free $1 key, no card, one per email:

bash
curl -X POST https://patchwell.io/v1/credits/trial \  -H "Content-Type: application/json" -d '{"email": "[email protected]"}'

Or buy credit at patchwell.io. Keys look like pw_live_....

Connect

Claude (web and desktop) or ChatGPT

Add a custom connector with the address https://patchwell.io/connect/. The app opens a Patchwell page where you paste your key or get a free one, then sends you back. In Claude it's under Customize, then Connectors, then Add. In ChatGPT, use developer mode.

Claude Code

bash
claude mcp add --transport http patchwell https://patchwell.io/mcp/ --header "Authorization: Bearer YOUR_KEY"

Cursor, Windsurf and other clients that take JSON config

json
{  "mcpServers": {    "patchwell": {      "type": "http",      "url": "https://patchwell.io/mcp/",      "headers": { "Authorization": "Bearer YOUR_KEY" }    }  }}

Claude Desktop (through the mcp-remote bridge)

json
{  "mcpServers": {    "patchwell": {      "command": "npx",      "args": ["-y", "mcp-remote", "https://patchwell.io/mcp/", "--header", "Authorization: Bearer YOUR_KEY"]    }  }}

Plain HTTP

bash
curl https://patchwell.io/v1/research \  -H "Authorization: Bearer $PATCHWELL_KEY" -H "Content-Type: application/json" \  -d '{"ask": "What does Stripe charge for online card payments in the US?"}'

What a research answer looks like

Real output, shortened:

json
{  "answer": "Stripe charges 2.9% + 30 cents for standard online domestic card payments in the US [https://www.swipesum.com/insights/guide-to-stripe-fees-rates-for-2025][https://checkoutpage.com/blog/stripe-processing-fees]. PayPal's standard merchant fee is 3.49% + 49¢ per online transaction [https://merchantinsiders.com/blogs/paypal-fees/]. ...",  "confidence": "medium",  "gaps": ["2 claims left out because the sources found did not clearly support them."],  "billing": { "price": 0.15 }}

Before you see the answer, a separate step compares each claim with the text of the page it cites. It drops the claims that page doesn't support and counts them in gaps.

Also on Apify

The same tools run as Apify Actors, billed through your Apify account: research · transcribe · clean data

Privacy and limits

  • Patchwell processes audio and files in temporary containers and discards them. It keeps no copies.
  • Patchwell keeps research questions for 30 days, with contact details removed, to improve accuracy. Switch that off per key at patchwell.io/privacy, or per request with the header X-Patchwell-Retain: off.
  • Research declines questions about private individuals (addresses, phone numbers, relatives, profiles). If a key keeps asking, Patchwell pauses it.
  • The tools refuse URLs that point at private or internal network addresses.

About this repository

This repo holds the MCP Registry entry (server.json) and these docs. The service runs at patchwell.io.

Questions: [email protected]

Source: README.md at commit e0c0e14

Tools

4

transcribe

Transcribe audio or video

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: $0.008 per audio minute; failed downloads are free.

Parametersurlrequiredlanguage

research

Research a question with cited sources

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), `sources`, `gaps` (what the sources couldn't confirm) and `confidence` (high/medium/low). Takes about a minute; a slow question returns {"status": "running", "job_id"} for get_job_result. Declines questions about private individuals (addresses, contact details, relatives, profiles) and returns a `category` saying why. Price: $0.15 per answered question; declined and unanswered questions are free.

Parameterscontextquestionrequired

get_job_result

Get a research result

Fetch the result of a long call that returned {"status": "running", "job_id"}. Call it every 20 to 30 seconds until status is 'done'; the finished result has the same shape as the original tool's. Free.

Parametersjob_idrequired

clean_data

Clean a CSV or Excel file

Clean a messy spreadsheet or JSON export into typed, deduplicated records with a log of each change. Use it before you analyse, import or act on tabular data. It works out each column's type from the values, normalises emails, phones, dates, money, names and states, repairs broken encodings, and merges duplicate records. Returns `rows`, `changes` (row, column, before, after, rule), `review` (rows held back, with the reason), `columns`, `clusters` (likely typos), a JSON `schema`, a reusable `recipe` and `stats`, whose counts always add up to the input rows. Price: $2 per 1,000 rows, minimum $0.02.

Parametersurlhintsrecipefilenamerequireddedupe_onphone_formatphone_regioncontent_base64

Version history

1
  1. v1.1.0LatestNov 7, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts