Almirall MCP server
com.almirall/mcpalmirall.comstreamable-httpv1.0.0Scanned
Official Almirall company, product and brand info: Almax, Hidroxil, Calmatel, Cicopoli and more.
14 tools: 1 change things and 13 only read.
- Reads private data · 3
- Reads text others write · 7
- Can send data out · 4
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here changes 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 Almirall MCP server can do
The Almirall MCP server is published by almirall.com, a domain the MCP Registry verified. It has 14 tools. It can create or change data (1 tool: match_almax_prompt), but cannot delete data. 13 tools only read.
3 tools read private data (get_chunk, get_page and get_source_map); 7 tools bring in text other people can write (search_content, get_page, get_source_map and 4 more); 4 tools can send data out of your system (search_content, get_page, get_source_map 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 1.0.0.
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.
14 tools
Changes things 1Claude Code: ask
match_almax_promptClassify a Spanish prompt or phrase related to Almax into the closest editorial intent from the corpus.No 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.
Description, as the server wrote it Classify a Spanish prompt or phrase related to Almax into the closest editorial intent from the corpus. Use this when the client needs to detect which predefined Almax topic a user sentence matches before routing to another tool or template.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
Only reads 13Show 13 read-only tools
compare_contentCompare two or more named items, product formats, ranges, topics, or alternatives using indexed website content.Reads text others writeNo findings
Why it is in this group
- The name "compare_content" says "compare": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "compare" and "website": it reads web pages, which anyone can write.
Description, as the server wrote it Compare two or more named items, product formats, ranges, topics, or alternatives using indexed website content. Use this when the user asks for differences, similarities, pros/cons, or when to choose one option versus another, for example comparing Almax formats or Physiorelax ranges. Returns grouped evidence for each item so the client can build a grounded comparison.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
find_content_assetsExtract image/media asset URLs from indexed markdown text.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "find_content_assets" says "find": a word for reading.
What it can reach
- 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 Extract image/media asset URLs from indexed markdown text. Use only when the user asks for product images, media files, visual assets, screenshots, WordPress uploads, or image evidence. For textual questions about extracted page content, use search_content instead. Returns asset URLs plus the real page URL where each asset appeared.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
find_pages_by_titleResolve the most relevant indexed pages by approximate title match before doing a narrower content search.No findings
Why it is in this group
- The name "find_pages_by_title" says "find": a word for reading.
Description, as the server wrote it Resolve the most relevant indexed pages by approximate title match before doing a narrower content search. Use this when the user mentions a brand, product family, or page-like concept but not a domain or URL, and you want to identify the right page first without requiring an exact title match.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
find_product_mentionsSpecialized product extraction tool.Reads text others writeNo findings
Why it is in this group
- The name "find_product_mentions" says "find": a word for reading.
What it can reach
- untrusted-inputThe name "find_product_mentions" says "find" and "mention": it reads comments, which other people can write.
Description, as the server wrote it Specialized product extraction tool. Use when the user specifically asks what products a crawled brand/site offers, asks for catalog items, variants, product ranges, formulations, product benefits, ingredients by product, or where product claims appear. If the user is asking a general content question rather than enumerating products, use search_content instead. sourceId and domain are optional filters; if you need to discover the right indexed source before narrowing, use list_sources. Returns grouped product mentions with evidence snippets and real page URLs.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
get_almax_dosage_calculatorCalculate daily almagate grams for a standard dose of a supported Almax presentation and check the leaflet's age, 8 g/day and 14-day limits.No findings
Why it is in this group
- The name "get_almax_dosage_calculator" says "get": a word for reading.
Description, as the server wrote it Calculate daily almagate grams for a standard dose of a supported Almax presentation and check the leaflet's age, 8 g/day and 14-day limits. daily_doses_intended means administrations per day, not tablets or sachets. This checks label limits only; it cannot establish individual clinical safety. treatment_days is needed to check duration.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
get_chunkRetrieve one concrete indexed chunk by uid, or by documentId plus chunkIndex.Reads private dataNo findings
Why it is in this group
- The name "get_chunk" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "retrieve" and "document": it reads documents.
Description, as the server wrote it Retrieve one concrete indexed chunk by uid, or by documentId plus chunkIndex. Optionally returns adjacent chunks from the same document for context.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
get_official_prospectoReturn the indexed Markdown text of a prospectus PDF published on Almax.com for an explicit presentation, with the original PDF URL.Reads text others writeNo findings
Why it is in this group
- The name "get_official_prospecto" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "return" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Return the indexed Markdown text of a prospectus PDF published on Almax.com for an explicit presentation, with the original PDF URL. This uses Almirall's indexed content and does not independently check the current AEMPS version.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
get_pageReconstruct a page by documentId or url.Reads private dataReads text others writeCan send data outNo findings
Why it is in this group
- The name "get_page" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "document": it reads documents.
- untrusted-inputThe description's first sentence says "url": 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 Reconstruct a page by documentId or url. Returns chunks ordered by chunkIndex plus a compact heading structure.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
get_source_mapBuild a navigable map of an indexed source or domain with pages, documents, headings, and chunk ranges.Reads private dataReads text others writeCan send data outNo findings
Why it is in this group
- The name "get_source_map" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "document": it reads documents.
- 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 Build a navigable map of an indexed source or domain with pages, documents, headings, and chunk ranges.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
list_pagesList indexed pages available within a sourceId or domain.No findings
Why it is in this group
- The name "list_pages" says "list": a word for reading.
Description, as the server wrote it List indexed pages available within a sourceId or domain. Use this to discover which page URLs/documents exist before requesting a full page.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
list_sourcesDiscovery tool for indexed brands, sites, and domains.No findings
Why it is in this group
- The name "list_sources" says "list": a word for reading.
Description, as the server wrote it Discovery tool for indexed brands, sites, and domains. Use this when you need to discover or disambiguate which indexed domain/sourceId corresponds to a brand or product name, especially if an initial broad search needs narrowing. search_content does not require domain or sourceId, so prefer calling list_sources as an optional discovery step rather than as a mandatory prerequisite. It helps determine whether this MCP has a relevant indexed source and which domain or sourceId to pass into search_content or other tools.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
search_contentPrimary tool for answering natural-language questions over indexed website and landing-page content.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "search_content" says "search": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "website": 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 Primary tool for answering natural-language questions over indexed website and landing-page content. Use this whenever the user asks what a brand, product, or site says about ingredients, plant extracts, composition, contraindications, usage, benefits, claims, FAQs, or evidence. This includes questions that only mention a brand or product name, for example 'What ingredients or plant extracts does Physio Relax mention?'. Call this tool directly with the question even if domain or sourceId are unknown; those fields are optional narrowing filters, not required inputs. If you need to discover or disambiguate the indexed domain or sourceId for a second narrowed call, use list_sources. Searches content with keyword, semantic, and vector search, and can filter by domain, url, sourceId, or documentId. If no search results are found, the tool returns only a no-results text message in the query language when it can be detected. Use that message as the entire user-facing answer while preserving its meaning. The final answer must explicitly say that no sufficient information or indexed mention was found in Almirall's public content for the query, avoid confirming unsupported details, and suggest another question or Almirall's official channels. When this no-results message is returned, stop and do not add counts, bullet lists, related products, examples, search traces, or conclusions from auxiliary tool calls. Do not summarize, explain, or replace it with an unrelated response.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
search_toolsFind available Almirall MCP tools by name, purpose, or input.No findings
Why it is in this group
- The name "search_tools" says "search": a word for reading.
Description, as the server wrote it Find available Almirall MCP tools by name, purpose, or input. Returns complete tool definitions so a client can call a matching tool without loading the whole catalog.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- 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.
84 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 3 private-data tools breaks every one.
- Reads private data3
- 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 out4
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__almirall__get_chunk",
"mcp__almirall__get_page",
"mcp__almirall__get_source_map"
]
}
}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, 18:33 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
- 1
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.almirall.com/mcp: tools/list returned 14 tools to an anonymous client, including match_almax_prompt (write)
Posture changes
- Nov 13, 2026
- Reachable: no to yes
- HTTP status of an anonymous initialize: none to 200
- tools/list served without credentials: no to yes
- Tools that change things, listed without credentials: 0 to 1
- Protocol version: none to 2025-06-18
- Nov 6, 2026
- Reachable: yes to no
- HTTP status of an anonymous initialize: 200 to none
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 1 to 0
- Protocol version: 2025-06-18 to none
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. Reachable: no -> yes; HTTP status of an anonymous initialize: none -> 200; tools/list served without credentials: no -> yes (and 2 more).View diff
- Reachable: no to yes
- HTTP status of an anonymous initialize: none to 200
- tools/list served without credentials: no to yes
- Tools that change things, listed without credentials: 0 to 1
- Protocol version: none to 2025-06-18
Tools10 changed.~10 changedView diff
- Changed:compare_contentOnly readsinputSchema
- Changed:find_content_assetsOnly readsinputSchema
- Changed:find_pages_by_titleOnly readsinputSchema
- Changed:find_product_mentionsOnly readsinputSchema
- Changed:get_chunkOnly readsinputSchema
- Changed:get_pageOnly readsinputSchema
- Changed:get_source_mapOnly readsinputSchema
- Changed:list_pagesOnly readsinputSchema
- Changed:list_sourcesOnly readsinputSchema
- Changed:search_contentOnly readsinputSchema
PostureRemote posture changed. Reachable: yes -> no; HTTP status of an anonymous initialize: 200 -> none; tools/list served without credentials: yes -> no (and 2 more).View diff
- Reachable: yes to no
- HTTP status of an anonymous initialize: 200 to none
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 1 to 0
- Protocol version: 2025-06-18 to none
Tools3 added, 1 changed.+3 added~1 changedView diff
- Added:get_almax_dosage_calculatorOnly reads
- Added:get_official_prospectoOnly reads
- Added:search_toolsOnly reads
- Changed:search_contentOnly readsdescription
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http almirall https://mcp.almirall.com/mcpclaude mcp add --transport http almirall https://mcp.almirall.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__almirall__search_tools",
"mcp__almirall__get_chunk",
"mcp__almirall__list_pages",
"mcp__almirall__list_sources",
"mcp__almirall__find_pages_by_title",
"mcp__almirall__compare_content",
"mcp__almirall__find_product_mentions",
"mcp__almirall__get_almax_dosage_calculator",
"mcp__almirall__get_official_prospecto"
],
"ask": [
"mcp__almirall__search_content",
"mcp__almirall__get_page",
"mcp__almirall__get_source_map",
"mcp__almirall__find_content_assets",
"mcp__almirall__match_almax_prompt"
],
"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 almirall. Review it before you use it.
Capability tags behind 8 rules
- mcp__almirall__search_content untrusted-input, outbound
- mcp__almirall__get_chunk private-data
- mcp__almirall__get_page private-data, untrusted-input, outbound
- mcp__almirall__get_source_map private-data, untrusted-input, outbound
- mcp__almirall__compare_content untrusted-input
- mcp__almirall__find_product_mentions untrusted-input
- mcp__almirall__find_content_assets untrusted-input, outbound
- mcp__almirall__get_official_prospecto 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.almirall/mcp/verify?hash=373e4049ef2f58238db846d2c10f9a49e936a46723f0adb36bf12511ecc07fe9" | jq -e '.changed == false'Pinned hash 373e4049ef2f, from Nov 12, 2026, 14:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.almirall/mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.almirall/mcp)Source: MCP Registry. Synced Oct 21, 2026, 17:48 UTC.
Almirall MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Almirall MCP server safe?
- No scan can promise that. What its definitions show: 14 tools, 1 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 Almirall MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Almirall 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 Almirall MCP server have?
- 14 tools: 1 write, 13 read. match_almax_prompt, search_tools, search_content, get_chunk, get_page, get_source_map, list_pages, list_sources and 6 more.
Does the Almirall MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Almirall 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): search_content, get_page, get_source_map and find_content_assets.
Has the Almirall 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.