Name: Patchwell
Author: patchwell

Patchwell MCP

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

Tool-list grade A Remote · Streamable HTTP API key 4 tools v1.1.0 MIT

No reviews yet by patchwellGitHub The publisher’s own endpoint — this marketplace is not in the path

93/100

tool-list score

tools declared

remote

at its publisher

—

calls last 7d

What it does

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

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user --transport http patchwell-mcp https://patchwell.io/mcp/ --header 'Authorization: Bearer ${AUTHORIZATION}'

# 2 — ask your agent for something these tools do
#   transcribe, research, get_job_result and 1 more

It needs AUTHORIZATION (Bearer <your Patchwell API key>. Free $1 key: POST https://patchwell.io/v1/credits/trial): this sends it in the Authorization header from your environment, so export it first — its endpoint answers 401 without it.

Patchwell costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publishernot claimed

patchwell1 server

1 category

All 1 server

Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.

Installation

Where are you running it?

Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.

Claude Codedeclared by this listing

This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it. Claude Code reads AUTHORIZATION (Bearer <your Patchwell API key>. Free $1 key: POST https://patchwell.io/v1/credits/trial) from your environment each time it connects and sends it in the Authorization header — its endpoint answers 401 without it — so the key stays out of its config: export it in your shell profile (macOS, Linux), or run setx AUTHORIZATION … and open a new terminal (Windows).

claude mcp add --scope user --transport http patchwell-mcp https://patchwell.io/mcp/ --header 'Authorization: Bearer ${AUTHORIZATION}'

Reconnect, or start a new session, and the tools appear in the model’s tool list.

Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add — but its publisher asks for a key of their own on every call.

What it asks of you

It reaches a system of yours, so it needs your own credential rather than the publisher’s: Authorization header — Bearer <your Patchwell API key>. Free $1 key: POST https://patchwell.io/v1/credits/trial. You set it in your own client’s config, on your machine — this marketplace never holds it.

What it writes

One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.

What you approve

4 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.

Tool surface

What the model actually sees. Descriptions are diffed on every release — see version history.

Only tools that write or reach the network

Transcribe speech in an audio or video file. Use it when you need the words in a recording, quotes with their time, or subtitles. Returns text, sentence segments, each word with start/end seconds and confidence, SRT and VTT, and flags listing any phrase the guards removed (Whisper's invented phrases over silence and repetition loops) with its original text and time. Files

Parameter	Type	Required	Notes
url	string	yes	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.
language		no	Two-letter language code such as en, es or ja. Leave it out to detect the language from the audio.

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":

Parameter	Type	Required	Notes
question	string	yes	The question in plain language, up to 4,000 characters. Ask about topics, markets, products, prices, companies, regulations, places, events or published research.
context	string	no	Optional background: who the answer is for, what you already know, or constraints such as country or date range.

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.

Parameter	Type	Required	Notes
job_id	string	yes	The job_id from a transcribe, research or clean_data call that returned status 'running'.

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

Parameter	Type	Required	Notes
url	string	no	Public http(s) link to a CSV, TSV, XLSX or JSON file, up to 100 MB. Use this or content_base64.
filename	string	no	File name with extension (e.g. customers.csv). Required with content_base64 so the format is known.
content_base64	string	no	The file itself, base64-encoded, for small files you hold locally. Use this or url.
dedupe_on		no	Columns that identify a record; rows matching on them merge into one. Default: the email column, else the whole row.
required		no	Columns a row must have; rows missing one go to the review list.
hints		no	Force a column's type, e.g. {"Joined": "date"}. Types: email, phone, date, money, number, us_state, name, boolean, text.
recipe		no	The recipe from an earlier run. Pass it to clean a new file with the same column types and rules.
phone_region	string	no	Two-letter country for phone numbers written without a country code, e.g. US, GB, DE.
phone_format	string	no	'national' like (415) 555-0100, or 'e164' like +14155550100.

Free

$0 forever

Every tool — any call limit is its publisher’s, not ours
No card, and mcprush charges nothing for it
Runs at its publisher’s own address — this marketplace is not in the path
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install Patchwell or to call it, at any volume.

ATool-list grade · score 93 / 100

Release 1.1.0 · scanned 7 Nov 2026

Graded from the tools this server lists, not from its source code.

Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.

Threat score100

Client score93

Findings0 threat · 3 capability

Capabilitymoderate

Coveragemanifest

Verificationnot in this report

Surface digestbab3e2e20760a8a43fd9c2c3a8ccc8475354834e8ed46d0c69d2df5bd6284394

Score vectorthreat 100 → client 93

Term	Level	What it prices	Points
capability-exposure	moderate	capability blast radius (moderate) — client exposure if the model is manipulated	−3
coverage-honesty	manifest	inspection depth (manifest) — how much of the target the scan could see	−4

score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.

What the scan could actually read

A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.

The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.

Tool surfaceread

Implementation sourcenot available

Package metadatanot available

Live transportnot available

The implementation source was not read — this reflects the declared tool metadata only.

Capability — what it could do if the model were manipulated

Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.

Tool	Capability tags	Why the tag was assigned
transcribe	external-sink	external-sink: declares readOnlyHint: false, openWorldHint: true
research	external-sink	external-sink: declares readOnlyHint: false, openWorldHint: true
get_job_result	untrusted-input	untrusted-input: keyword "fetch"
clean_data	external-sink	external-sink: declares readOnlyHint: false, openWorldHint: true

Toxic-flow graph

The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.

flow-1

Untrusted input can drive an external action even though no sensitive source is exposed.

Supply chain and provenance

Integrityfirst-seen

Surface digestbab3e2e20760a8a4

Scanned2026-11-07

This is the first scan of this surface here, so there is nothing yet to compare it against.

Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.