Patchwell MCP server
io.patchwell/patchwellpatchwell.iostreamable-httpv1.3.0Scanned
Cited web research, transcription with word timestamps, and CSV/Excel cleaning with a change log.
5 tools: 4 change things and 1 only read.
- Reads private data · 0
- Reads text others write · 4
- Can send data out · 3
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
4 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Patchwell MCP server can do
The Patchwell MCP server is published by patchwell.io, a domain the MCP Registry verified. It has 5 tools. It can create or change data (4 tools: transcribe, research, listen_clip and clean_data), but cannot delete data. 1 tool only reads.
4 tools bring in text other people can write (transcribe, research, listen_clip and 1 more); 3 tools can send data out of your system (transcribe, listen_clip and clean_data).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 9, 2026, version 1.3.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
5 tools
Changes things 4Claude Code: ask
clean_dataClean a messy spreadsheet or JSON export into typed, deduplicated records with a log of each change.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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 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.
Annotations the server declares
- title: Clean a CSV or Excel file
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
listen_clipUsed by the transcript card to play a spot the speaker labels are unsure of.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Used by the transcript card to play a spot the speaker labels are unsure of. Free.
Annotations the server declares
- title: Play part of a recording
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
researchResearch a question on the live web and get an answer in which each sentence cites the page it came from.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- title: Research a question with cited sources
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
transcribeTranscribe speech in an audio or video file.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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, minimum $0.02 a file; failed downloads are free.
Annotations the server declares
- title: Transcribe audio or video
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Only reads 1Show 1 read-only tool
get_job_resultFetch the result of a long call that returned {"status": "running", "job_id"}.No findings
Why it is in this group
- The name "get_job_result" says "get": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- title: Get a research result
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write4
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out3
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 21, 2026, 19:22 UTC, unchanged since Nov 14, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 4
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://patchwell.io/.well-known/oauth-protected-resource
- Authorization servers
- https://patchwell.io
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 4 tools that change things (3 destructive, 1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://patchwell.io/mcp/: tools/list returned 5 tools to an anonymous client, including transcribe (destructive), research (destructive), clean_data (destructive), listen_clip (write)
Posture changes
- Nov 14, 2026
- Tools that change things, listed without credentials: 3 to 4
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Tools that change things, listed without credentials: 3 -> 4.View diff
- Tools that change things, listed without credentials: 3 to 4
Tools1 added, 2 changed.+1 added~2 changedView diff
- Added:listen_clipChanges things
- Changed:clean_dataChanges thingsdescriptioninputSchema
- Changed:transcribeChanges thingsdescription
Install
Pinned to version 1.3.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http patchwell https://patchwell.io/mcp/ --header 'Authorization: <your-authorization>'claude mcp add --transport http patchwell https://patchwell.io/mcp/ --header 'Authorization: <your-authorization>'Run in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__patchwell__get_job_result"
],
"ask": [
"mcp__patchwell__transcribe",
"mcp__patchwell__research",
"mcp__patchwell__listen_clip",
"mcp__patchwell__clean_data"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as patchwell. Review it before you use it.
Capability tags behind 4 rules
- mcp__patchwell__transcribe untrusted-input, outbound
- mcp__patchwell__research untrusted-input
- mcp__patchwell__listen_clip untrusted-input, outbound
- mcp__patchwell__clean_data untrusted-input, outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.patchwell/patchwell/verify?hash=bcfc16cfba5c3f9b641c66c198049c6e48de8100e08ba083bf2e5b3f551917fc" | jq -e '.changed == false'Pinned hash bcfc16cfba5c, from Nov 9, 2026, 00:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.patchwell/patchwell/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.patchwell/patchwell)Source: MCP Registry · repository. Synced Nov 9, 2026, 00:18 UTC.
Patchwell MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Patchwell MCP server safe?
- No scan can promise that. What its definitions show: 5 tools, 4 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Patchwell MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Patchwell MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Patchwell MCP server have?
- 5 tools: 4 write, 1 read. transcribe, research, listen_clip, clean_data and get_job_result.
Does the Patchwell MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Patchwell MCP server send data to outside services?
- 3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): transcribe, listen_clip and clean_data.
Has the Patchwell MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 8, 2026. Every change is on this page and in its Atom feed.