Bisque Presentations MCP server
cloud.bisque/presentationsbisque.cloudstreamable-httpv1.0.1Scanned
Create narrated presentations from HTML, poll build status, list them, read one back as text.
22 tools: 3 can delete or cancel things, 2 do something that can't be undone, 7 change things and 10 only read.
- Reads private data · 7
- Reads text others write · 11
- Can send data out · 4
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
3 tools here can delete or cancel things and 2 do something that can't be undone. 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 Bisque Presentations MCP server can do
The Bisque Presentations MCP server is published by bisque.cloud, a domain the MCP Registry verified. It has 22 tools. It can delete or cancel things (3 tools: create_presentation, publish_narrated_presentation and delete_artifact), do things that cannot be undone, such as sending, paying or publishing (create_artifact and reply_to_artifact_thread) and create or change data (7 tools: update_channel, update_artifact, share_artifact, pin_artifact and 3 more). 10 tools only read.
7 tools read private data (get_presentation_spec, get_presentation_analytics, get_presentation_context and 4 more); 11 tools bring in text other people can write (get_presentation_spec, create_presentation, publish_narrated_presentation and 8 more); 4 tools can send data out of your system (publish_narrated_presentation, get_presentation_context, get_presentation_source and 1 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
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 2 times since Anlyon Radar first saw them.
Last scanned Nov 12, 2026, version 1.0.1.
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.
22 tools
Deletes or cancels 3Claude Code: deny
create_presentationGenerate a narrated presentation from an html-presentation/v1 document.Reads text others writeNo findings
Why it is in this group
- The name "create_presentation" says "create": 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 Generate a narrated presentation from an html-presentation/v1 document. BEFORE authoring, call get_presentation_spec and follow it exactly — slides without its narration markup publish SILENT. Returns a presentationId and the watch URL. Narration runs in the background and the inline player tracks it on its own, so reply to the user as soon as this returns and do not call get_presentation_status unless the user asks whether it is done.
Annotations the server declares
- title: Create narrated presentation
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
delete_artifactDelete an Artifact you own.No findings
Why it is in this group
- The name "delete_artifact" says "delete": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Delete an Artifact you own. Its URL stops working for everyone. Confirm with the user before calling this.
Annotations the server declares
- title: Delete an Artifact
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
publish_narrated_presentationDEPRECATED: call create_presentation with an `audio` array instead — it is the same thing in one call, and the slides are viewable while the narration lands.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "publish_narrated_presentation" says "publish": a word for a change that another call does not undo.
- 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.
- outboundThe name "publish_narrated_presentation" says "publish": it sends or publishes something to other people.
Description, as the server wrote it DEPRECATED: call create_presentation with an `audio` array instead — it is the same thing in one call, and the slides are viewable while the narration lands. Publish an html-presentation/v1 document using audio YOU synthesized locally (e.g. with `bisque-voice`) — free, unlimited, and works on macOS, Linux and Windows. Send each narrated slide's word timings and MP3 metadata; the server assembles presentation.json (recomputing cues from your narration markers) and returns one upload URL per MP3. Then PUT each file and POST the returned completeUrl with the returned `files` array. RE-PUBLISHING: `audio` is optional — any narrated slide you omit reuses the audio from the last publish whenever its narration text and speechSpeed are unchanged, so an HTML-only edit needs no synthesis at all. The response reports `reused`, `synthesized`, and `staleSlides` (narrated slides whose text changed and have no audio — synthesize exactly those and publish again). Use create_presentation instead to have the server narrate.
Annotations the server declares
- title: Publish a presentation you narrated yourself
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
Can't be undone 2Claude Code: ask
create_artifactPublish an HTML page or a Markdown document as a Bisque Artifact: a persistent, versioned page at a stable URL that people can open, comment on, and that you can update later with …No findings
Why it is in this group
- The name "create_artifact" says "create": a word for a change.
- The description's first verb is "publish": a word for a change that another call does not undo.
Description, as the server wrote it Publish an HTML page or a Markdown document as a Bisque Artifact: a persistent, versioned page at a stable URL that people can open, comment on, and that you can update later with update_artifact. Pass the whole document as content. The call waits for the page to be ready and returns its URL. It is private to you unless you pass audience or share_with. A page that should remember what people do on it (a checklist, a poll, a sign-up sheet) declares capabilities ['state.read','state.write'] and, when some paths need different access, state.rules; it then reads and writes JSON documents through window.bisque.state. For a narrated presentation use create_presentation instead.
Annotations the server declares
- title: Create an Artifact
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
reply_to_artifact_threadPost a reply in a comment thread as the agent.Can send data outNo findings
Why it is in this group
- The name "reply_to_artifact_thread" says "reply": a word for sending, and what is sent cannot be taken back.
What it can reach
- outboundThe name "reply_to_artifact_thread" says "reply": it sends or publishes something to other people.
Description, as the server wrote it Post a reply in a comment thread as the agent. Allowed only on activated threads (agent_activated true): someone mentioned the agent, or the agent started the thread. People see it as "Agent · via <your name>".
Annotations the server declares
- title: Reply in an Artifact comment thread
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
Changes things 7Claude Code: ask
create_artifact_threadLeave a new comment thread on one of your Artifacts, as the agent.No findings
Why it is in this group
- The name "create_artifact_thread" says "create": a word for a change.
Description, as the server wrote it Leave a new comment thread on one of your Artifacts, as the agent. Without an anchor the thread is a general comment on the page. The thread is activated from the start, so you can reply to it and resolve it later. Mention a person with @[Name](mention:uid) using ids from the Artifact's mentionables.
Annotations the server declares
- title: Start a comment thread on an Artifact
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
pin_artifactPin an Artifact to the top of the user's own Artifacts library, the same as the Pin button there.No findings
Why it is in this group
- The name "pin_artifact" says "pin": a word for a change.
Description, as the server wrote it Pin an Artifact to the top of the user's own Artifacts library, the same as the Pin button there. Use it when the user asks you to pin something, so they can find it again. A pin is only for the user: it changes nothing about the Artifact and does not share it. Pinning one that is already pinned moves it to the top.
Annotations the server declares
- title: Pin an Artifact
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
resolve_artifact_threadMark a comment thread resolved (resolved: true) or reopen it (resolved: false), as the agent.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "resolve_artifact_thread" says "resolve": a word for reading.
- The description's first verb is "mark": a word for a change.
What it can reach
- private-dataThe name "resolve_artifact_thread" says "resolve" and "thread": it reads messages.
- private-dataThe description's first sentence says "thread": it reads messages.
- untrusted-inputThe name "resolve_artifact_thread" says "resolve" and "thread": it reads messages, which other people can write.
- untrusted-inputThe description's first sentence says "mark" and "comment": it reads comments, which other people can write.
Description, as the server wrote it Mark a comment thread resolved (resolved: true) or reopen it (resolved: false), as the agent. Allowed only on activated threads. Resolve after you have addressed the comment, usually after republishing the Artifact; reply first so the person can see what changed.
Annotations the server declares
- title: Resolve or reopen an Artifact comment thread
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
unpin_artifactTake an Artifact off the Pinned shelf of the user's own Artifacts library.No findings
Why it is in this group
- The name "unpin_artifact" says "unpin": a word for a change.
Description, as the server wrote it Take an Artifact off the Pinned shelf of the user's own Artifacts library. The Artifact itself is untouched.
Annotations the server declares
- title: Unpin an Artifact
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
update_artifactChange an Artifact you own or edit.No findings
Why it is in this group
- The name "update_artifact" says "update": a word for a change.
Description, as the server wrote it Change an Artifact you own or edit. Pass content to publish a new Version of the page at the same URL (the whole document, not a diff; earlier Versions stay in the history). Pass title, description, icon, or icon_image to change those. Any combination in one call. With content the call waits for the new Version to be live before returning. The new Version keeps the base Version's capabilities and state rules unless you pass capabilities or state.
Annotations the server declares
- title: Update an Artifact
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
update_channelUpdate one of your channels.No findings
Why it is in this group
- The name "update_channel" says "update": a word for a change.
Description, as the server wrote it Update one of your channels. Set the description — the line a stranger reads in a search result or a link unfurl, at most 160 characters, empty to clear it and go back to naming the newest presentations. Set the avatar from an image URL, which is fetched, center-cropped square and resized. Pass either or both. Omit handle to use your default channel.
Annotations the server declares
- title: Update channel
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 10Show 10 read-only tools
get_artifactRead one Artifact: title, who can open it, the Version viewers see (published_version_id, null while a publication is still being prepared), its URL, and for a markdown document it…Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_artifact" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "read" and "document": it reads documents.
- 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 one Artifact: title, who can open it, the Version viewers see (published_version_id, null while a publication is still being prepared), its URL, and for a markdown document its text (content), so a linked document is read in one call. Pass the art_… id from the end of the link.
Annotations the server declares
- title: Get an Artifact
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_artifact_threadRead one comment thread on an Artifact with every message, oldest first.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_artifact_thread" says "get": a word for reading.
What it can reach
- private-dataThe name "get_artifact_thread" says "get" and "thread": it reads messages.
- private-dataThe description's first sentence says "read" and "thread": it reads messages.
- untrusted-inputThe name "get_artifact_thread" says "get" and "thread": it reads messages, which other people can write.
- untrusted-inputThe description's first sentence says "read" and "comment": it reads comments, which other people can write.
Description, as the server wrote it Read one comment thread on an Artifact with every message, oldest first. Mentions in a body look like @[Name](mention:uid); a mention of the agent is @[Agent](mention:agent).
Annotations the server declares
- title: Get an Artifact comment thread
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_presentation_analyticsWatch analytics for one of your presentations: views, likes, completion rate, per-slide retention funnel, traffic sources, distinct signed-in/anonymous viewers, and organization em…Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_presentation_analytics" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "email": it reads mail.
- untrusted-inputThe description's first sentence says "email": it reads inbound email, which other people can write.
Description, as the server wrote it Watch analytics for one of your presentations: views, likes, completion rate, per-slide retention funnel, traffic sources, distinct signed-in/anonymous viewers, and organization email domains (personal providers filtered). Lets an agent read how its own published briefings performed.
Annotations the server declares
- title: Get presentation analytics
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_presentation_contextLoad any shared Bisque presentation for reading: its metadata, the full per-slide narration transcript with timestamps, and the context.md file its author shipped for agents (extra…Reads private dataReads text others writeCan send data outNo findings
Why it is in this group
- The name "get_presentation_context" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "file": it reads files.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Load any shared Bisque presentation for reading: its metadata, the full per-slide narration transcript with timestamps, and the context.md file its author shipped for agents (extra background the slides summarize). Target it by watch URL (https://bisque.today/p/{handle}/{slug}) or by handle + slug — it does not have to be yours. Use this to read, summarize, cite, or answer questions about a presentation: ground your answers in the returned transcript and context, and cite slides as [slide N].
Annotations the server declares
- title: Load a presentation into context
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_presentation_sourceRead the HTML a presentation was published from, so you can edit it and publish it back to the same URL.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "get_presentation_source" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "read" and "html": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Read the HTML a presentation was published from, so you can edit it and publish it back to the same URL. Only for a presentation this account may republish; anyone else's reads as not found, including a public one (use get_presentation_context to read those). Target it by presentationId, or by watch URL or handle + slug. To republish, change only what you were asked to in indexHtml and call create_presentation with the same presentationId, slug and visibility, plus each entry of assets as {path, url}; slides whose narration did not change keep their audio.
Annotations the server declares
- title: Read a presentation's editable source
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_presentation_specFetch the html-presentation/v1 authoring contract: document structure, the dual landscape/vertical layout rule, and the narration markup that makes slides speak.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_presentation_spec" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "fetch" and "document": it reads documents.
- untrusted-inputThe description's first sentence says "fetch" and "html": it reads web pages, which anyone can write.
Description, as the server wrote it Fetch the html-presentation/v1 authoring contract: document structure, the dual landscape/vertical layout rule, and the narration markup that makes slides speak. Call this BEFORE authoring for create_presentation — documents written without it publish with missing audio.
Annotations the server declares
- title: Get the authoring spec
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_presentation_statusFetch the build state and result URL for a presentationId.Reads text others writeNo findings
Why it is in this group
- The name "get_presentation_status" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "fetch" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Fetch the build state and result URL for a presentationId.
Annotations the server declares
- title: Get presentation status
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_artifact_threadsList the comment threads people left on one of your Artifacts, newest activity first.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "list_artifact_threads" says "list": a word for reading.
What it can reach
- private-dataThe name "list_artifact_threads" says "list" and "thread": it reads messages.
- private-dataThe description's first sentence says "list" and "thread": it reads messages.
- untrusted-inputThe name "list_artifact_threads" says "list" and "thread": it reads messages, which other people can write.
- untrusted-inputThe description's first sentence says "list" and "comment": it reads comments, which other people can write.
Description, as the server wrote it List the comment threads people left on one of your Artifacts, newest activity first. Pass activated_only: true to get only the threads where someone mentioned the agent, which are the ones you may reply to and resolve. Each thread carries its anchor (what it is pinned to), the version it was left on, a preview, and agent_activated.
Annotations the server declares
- title: List Artifact comment threads
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_artifactsList Artifacts you own (scope owned, the default), ones shared with you (shared), or both (all), newest first.No findings
Why it is in this group
- The name "list_artifacts" says "list": a word for reading.
Description, as the server wrote it List Artifacts you own (scope owned, the default), ones shared with you (shared), or both (all), newest first. Each item carries its id, title, who can open it, and its URL.
Annotations the server declares
- title: List your Artifacts
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_presentationsList the authenticated user's presentations, newest first.No findings
Why it is in this group
- The name "list_presentations" says "list": a word for reading.
Description, as the server wrote it List the authenticated user's presentations, newest first. One call returns at most `limit` of them. A non-null `nextCursor` in the response means more presentations remain: call again with `cursor` set to that value to get the page after this one, and keep going until `nextCursor` is null.
Annotations the server declares
- title: List your presentations
- 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.
308 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 4 outbound tools breaks every one.
- Reads private data7
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write11
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out4
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__presentations__get_presentation_context",
"mcp__presentations__get_presentation_source",
"mcp__presentations__publish_narrated_presentation",
"mcp__presentations__reply_to_artifact_thread"
]
}
}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, 18:32 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
- 13
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://bisque.cloud/.well-known/oauth-protected-resource/presentations/mcp
- Authorization servers
- https://bisque.cloud
- 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 13 tools that change things (4 destructive, 2 irreversible, 7 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://bisque.cloud/presentations/mcp: tools/list returned 26 tools to an anonymous client, including create_presentation (destructive), publish_narrated_presentation (destructive), update_artifact (destructive), delete_artifact (destructive), create_artifact (irreversible) and 8 more
Posture changes
- Nov 13, 2026
- Tools that change things, listed without credentials: 10 to 13
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: 10 -> 13.View diff
- Tools that change things, listed without credentials: 10 to 13
Tools3 added.+3 addedView diff
- Added:get_presentation_sourceOnly reads
- Added:pin_artifactChanges things
- Added:unpin_artifactChanges things
Tools5 changed.~5 changedView diff
- Changed:create_artifactCan't be undoneinputSchema
- Changed:delete_artifactDeletes or cancelsinputSchema
- Changed:get_artifactOnly readsdescriptioninputSchema
- Changed:share_artifactChanges thingsinputSchema
- Changed:update_artifactChanges thingsinputSchema
Install
Pinned to version 1.0.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http presentations https://bisque.cloud/presentations/mcpclaude mcp add --transport http presentations https://bisque.cloud/presentations/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__presentations__get_presentation_spec",
"mcp__presentations__get_presentation_status",
"mcp__presentations__list_presentations",
"mcp__presentations__get_presentation_analytics",
"mcp__presentations__list_artifacts",
"mcp__presentations__get_artifact",
"mcp__presentations__list_artifact_threads",
"mcp__presentations__get_artifact_thread"
],
"ask": [
"mcp__presentations__get_presentation_context",
"mcp__presentations__get_presentation_source",
"mcp__presentations__update_channel",
"mcp__presentations__create_artifact",
"mcp__presentations__update_artifact",
"mcp__presentations__share_artifact",
"mcp__presentations__pin_artifact",
"mcp__presentations__unpin_artifact",
"mcp__presentations__create_artifact_thread",
"mcp__presentations__reply_to_artifact_thread",
"mcp__presentations__resolve_artifact_thread"
],
"deny": [
"mcp__presentations__create_presentation",
"mcp__presentations__publish_narrated_presentation",
"mcp__presentations__delete_artifact"
]
}
}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 presentations. Review it before you use it.
Capability tags behind 12 rules
- mcp__presentations__get_presentation_spec private-data, untrusted-input
- mcp__presentations__create_presentation untrusted-input
- mcp__presentations__publish_narrated_presentation untrusted-input, outbound
- mcp__presentations__get_presentation_status untrusted-input
- mcp__presentations__get_presentation_analytics private-data, untrusted-input
- mcp__presentations__get_presentation_context private-data, untrusted-input, outbound
- mcp__presentations__get_presentation_source untrusted-input, outbound
- mcp__presentations__get_artifact private-data, untrusted-input
- mcp__presentations__list_artifact_threads private-data, untrusted-input
- mcp__presentations__get_artifact_thread private-data, untrusted-input
- mcp__presentations__reply_to_artifact_thread outbound
- mcp__presentations__resolve_artifact_thread private-data, 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/cloud.bisque/presentations/verify?hash=082e33fc2d9ba6e07114b74225d74c5d7079adebbf77f8dd48c254b677f50cee" | jq -e '.changed == false'Pinned hash 082e33fc2d9b, from Nov 12, 2026, 08:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/cloud.bisque/presentations/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/cloud.bisque/presentations)Source: MCP Registry. Synced Oct 21, 2026, 17:46 UTC.
Bisque Presentations MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Bisque Presentations MCP server safe?
- No scan can promise that. What its definitions show: 22 tools, 12 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 Bisque Presentations MCP server delete data?
- Yes. 3 tools can delete, cancel or revoke something: create_presentation, publish_narrated_presentation and delete_artifact.
Can the Bisque Presentations MCP server do things that cannot be undone?
- Yes. 2 tools can send, pay, publish or merge: create_artifact and reply_to_artifact_thread.
What tools does the Bisque Presentations MCP server have?
- 22 tools: 3 destructive, 2 irreversible, 7 write, 10 read. create_presentation, publish_narrated_presentation, delete_artifact, create_artifact, reply_to_artifact_thread, update_channel, update_artifact, share_artifact and 14 more.
Does the Bisque Presentations MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Bisque Presentations MCP server send data to outside services?
- 4 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): publish_narrated_presentation, get_presentation_context, get_presentation_source and reply_to_artifact_thread.
Has the Bisque Presentations MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 12, 2026. Every change is on this page and in its Atom feed.