Pentasor MCP server
com.pentasor/sensespentasor.comstreamable-httpv1.0.0Scanned
Senses for agents on live sites and media: read, see, hear, drive a flow, verify a claim.
7 tools: 1 can delete or cancel things, 5 change things and 1 only read.
- Reads private data · 0
- Reads text others write · 7
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here can delete or cancel things. Govern it.
- 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 Pentasor MCP server can do
The Pentasor MCP server is published by pentasor.com, a domain the MCP Registry verified. It has 7 tools. It can delete or cancel things (1 tool: drive) and create or change data (5 tools: see, hear, perceive, verify and 1 more). 1 tool only reads.
7 tools bring in text other people can write (read, see, hear and 4 more).
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 19, 2026, version 1.0.0.
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.
7 tools
Deletes or cancels 1Claude Code: deny
driveOpen a URL in a real browser, run up to 20 steps (60 seconds at most), and return what happened: a timeline, screenshots and the final text.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "open": a word for a change.
- The server marks it destructive (destructiveHint: true).
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 Open a URL in a real browser, run up to 20 steps (60 seconds at most), and return what happened: a timeline, screenshots and the final text. This acts on the live site: clicks and form submits are real. Nothing persists between calls, and typed text is not logged. Steps: {do: goto|click|type|press|wait|waitFor|scrollIntoView|mark, testid? | role+name? | selector?, text?, key?, url?, ms?, label?}. Uses 5 perceptions. Free keys get a monthly allowance.
Annotations the server declares
- readOnlyHint: false
- openWorldHint: true
- destructiveHint: true
- idempotentHint: false
Changes things 5Claude Code: ask
hearTranscribe speech from an audio or video URL, up to 20 MB: full text, language and timed segments.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.
- 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.
Description, as the server wrote it Transcribe speech from an audio or video URL, up to 20 MB: full text, language and timed segments. Uses one perception per started minute of audio. Free keys get a monthly allowance of minutes.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
- idempotentHint: true
perceiveHealth check with an explanation: is it up, how fast, its security headers, and an excerpt of what it says.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.
- 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.
Description, as the server wrote it Health check with an explanation: is it up, how fast, its security headers, and an excerpt of what it says. Paid keys also get sight, or hearing for media. Its `ok` covers those readings only and does NOT check any claim about the content: use `verify` for that.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
- idempotentHint: true
seeLoad a URL in a real browser and return a screenshot you can look at plus the rendered text.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.
- 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.
Description, as the server wrote it Load a URL in a real browser and return a screenshot you can look at plus the rendered text. For a video URL, returns frames from it. Free keys get a monthly allowance: call `senses` to see what is left.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
- idempotentHint: true
sensesWhat this key can use right now: its plan, which tools are open, and how many perceptions are left this month.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.
- 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.
Description, as the server wrote it What this key can use right now: its plan, which tools are open, and how many perceptions are left this month. Free to call.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
- idempotentHint: true
verifyCheck a claim about a live page.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.
- 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.
Description, as the server wrote it Check a claim about a live page. `must_contain`, `must_not_contain` and `expect_status` are checked exactly. A free-text `expectation` is judged from the page's text on paid keys; on other keys, or when the text can't settle it (how a page looks, what a click does), the verdict is `unverified` and you get the evidence to decide yourself. `pass` means everything asked was checked and held; `fail` means something checked did not.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
- idempotentHint: true
Only reads 1Show 1 read-only tool
readRead a URL as it is delivered: status, title, text and links, without running JavaScript.Reads text others writeNo findings
Why it is in this group
- The name "read" says "read": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "read" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Read a URL as it is delivered: status, title, text and links, without running JavaScript. Works on every key. If `sparse` is true the page builds itself in the browser: use `see` instead.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
- idempotentHint: true
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 or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write7
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- 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 20, 2026, 18:22 UTC, unchanged since Nov 13, 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
- 6
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://api.pentasor.com/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://api.passvak.com, https://api.pentasor.com
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- yes
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 6 tools that change things (1 destructive, 5 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://api.pentasor.com/mcp: tools/list returned 7 tools to an anonymous client, including drive (destructive), see (write), hear (write), perceive (write), verify (write) and 1 more
Posture changes
- Nov 13, 2026
- Client ID metadata documents: no to yes
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.
Tools1 changed.~1 changedView diff
- Changed:verifyChanges thingsdescription
PostureRemote posture changed. Client ID metadata documents: no -> yes.View diff
- Client ID metadata documents: no to yes
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http senses https://api.pentasor.com/mcpclaude mcp add --transport http senses https://api.pentasor.com/mcpRun 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__senses__read"
],
"ask": [
"mcp__senses__see",
"mcp__senses__hear",
"mcp__senses__perceive",
"mcp__senses__verify",
"mcp__senses__senses"
],
"deny": [
"mcp__senses__drive"
]
}
}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 senses. Review it before you use it.
Capability tags behind 7 rules
- mcp__senses__read untrusted-input
- mcp__senses__see untrusted-input
- mcp__senses__hear untrusted-input
- mcp__senses__perceive untrusted-input
- mcp__senses__verify untrusted-input
- mcp__senses__drive untrusted-input
- mcp__senses__senses untrusted-input
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/com.pentasor/senses/verify?hash=27cc8a4dad8e09eaf175bf18b2b6813aff9c079ad0fb6f1020c22b290f483377" | jq -e '.changed == false'Pinned hash 27cc8a4dad8e, from Nov 19, 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/com.pentasor/senses/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.pentasor/senses)Source: MCP Registry. Synced Nov 5, 2026, 05:17 UTC.
Pentasor MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Pentasor MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, 6 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 Pentasor MCP server delete data?
- Yes. 1 tool can delete, cancel or revoke something: drive.
Can the Pentasor 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 Pentasor MCP server have?
- 7 tools: 1 destructive, 5 write, 1 read. drive, see, hear, perceive, verify, senses and read.
Does the Pentasor MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Pentasor MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Pentasor MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 19, 2026. Every change is on this page and in its Atom feed.