AlphaCitation reference lookup MCP server
com.alphacitation/referencealphacitation.comstreamable-httpv1.0.4Scanned
Is a medicine approved in a market? US, EU/EEA regulators; others not settled. Not medical advice.
4 tools: 1 change things and 3 only read.
- Reads private data · 0
- Reads text others write · 4
- Can send data out · 0
- 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 AlphaCitation reference lookup MCP server can do
The AlphaCitation reference lookup MCP server is published by alphacitation.com, a domain the MCP Registry verified. It has 4 tools. It can create or change data (1 tool: check_drug_approval_fda_eu), but cannot delete data. 3 tools only read.
4 tools bring in text other people can write (check_drug_approval_fda_eu, lookup_medicine_evidence, read_drug_label_fda_eu and 1 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 2 times since Anlyon Radar first saw them.
Last scanned Nov 20, 2026, version 1.0.4.
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.
4 tools
Changes things 1Claude Code: ask
check_drug_approval_fda_euAnswers whether a drug or medicine is approved, authorised, licensed or registered in a country or in the EU (for example, whether it is FDA approved in the US), or approved there …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 Answers whether a drug or medicine is approved, authorised, licensed or registered in a country or in the EU (for example, whether it is FDA approved in the US), or approved there for a condition, today or on a past date, and which official record settles that. Records are held for the US (the FDA's approval record on Drugs@FDA for whether a medicine is approved, and the prescribing information on DailyMed, as submitted to the FDA, for what it is approved for) and, for centrally authorised medicines, for the EU and EEA (the European Commission's product information), and each answer resting on one carries its pointer URL. For any other market, the answer names that market's competent authority and where its registration record is published, each where it is identified, and says which is not; the claim is unresolved there, or supported, never settled, by the authorisation holder's own label. For one medicine, one market and one date, the answer gives which source settles whether the medicine is registered (P1) or authorised for an indication (P2), what that source says about the claim where its content has been checked, where this market's label differs from the US and EU labels, and what is unresolved. supported_attested means the authorisation holder's own approved label, read under the attestation conditions, states the claim; it never settles it. Where that label does not state the indication, or its content has not been checked, the answer is unresolved. An unresolved answer means AlphaCitation cannot currently verify the claim from a held record; it is not evidence about the medicine's status. Every answer that does not settle carries abstention, one reason code (insufficient_evidence, authority_inaccessible, conflicting_records, stale_evidence, unsupported_claim_type, snapshot_only) with its meaning.
Annotations the server declares
- title: Is a drug FDA or EU approved?
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 3Show 3 read-only tools
lookup_medicine_evidenceAnswers whether a drug or medicine is approved, authorised, licensed or registered in a country or in the EU (for example, whether it is FDA approved in the US), or approved there …Reads text others writeNo findings
Why it is in this group
- The name "lookup_medicine_evidence" says "lookup": a word for reading.
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 Answers whether a drug or medicine is approved, authorised, licensed or registered in a country or in the EU (for example, whether it is FDA approved in the US), or approved there for a condition, today or on a past date, and which official record settles that. Records are held for the US (the FDA's approval record on Drugs@FDA for whether a medicine is approved, and the prescribing information on DailyMed, as submitted to the FDA, for what it is approved for) and, for centrally authorised medicines, for the EU and EEA (the European Commission's product information), and each answer resting on one carries its pointer URL. For any other market, the answer names that market's competent authority and where its registration record is published, each where it is identified, and says which is not; the claim is unresolved there, or supported, never settled, by the authorisation holder's own label. For one medicine, one market and one date, the answer gives which source settles whether the medicine is registered (P1) or authorised for an indication (P2), what that source says about the claim where its content has been checked, where this market's label differs from the US and EU labels, and what is unresolved. supported_attested means the authorisation holder's own approved label, read under the attestation conditions, states the claim; it never settles it. Where that label does not state the indication, or its content has not been checked, the answer is unresolved. An unresolved answer means AlphaCitation cannot currently verify the claim from a held record; it is not evidence about the medicine's status. Every answer that does not settle carries abstention, one reason code (insufficient_evidence, authority_inaccessible, conflicting_records, stale_evidence, unsupported_claim_type, snapshot_only) with its meaning.
Annotations the server declares
- title: Is a medicine approved in a market?
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
lookup_precedent_rulingFor one ruling identifier (ACPREC-YYYY-NNNN): what was decided about an evidence conflict, why, on which records, its status now (settled, unresolved or superseded) and its RFC 316…Reads text others writeNo findings
Why it is in this group
- The name "lookup_precedent_ruling" says "lookup": a word for reading.
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 For one ruling identifier (ACPREC-YYYY-NNNN): what was decided about an evidence conflict, why, on which records, its status now (settled, unresolved or superseded) and its RFC 3161 timestamp where one has been issued, together with a fresh lookup of the current governing record for the ruling's medicine, market and date where the ruling names one. A ruling is not evidence and decides no claim today; the current governing record does, and the ruling records only how the earlier conflict was decided. Where no current record is held, the answer names the competent authority and where its own record is published.
Annotations the server declares
- title: AlphaCitation precedent ruling
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
read_drug_label_fda_euAnswers what a drug's or medicine's official FDA label (the US prescribing information) or EU summary of product characteristics (SmPC) says, and its FDA approval or EU authorisati…Reads text others writeNo findings
Why it is in this group
- The name "read_drug_label_fda_eu" 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.
Description, as the server wrote it Answers what a drug's or medicine's official FDA label (the US prescribing information) or EU summary of product characteristics (SmPC) says, and its FDA approval or EU authorisation facts, today or on a past date: what it is approved or authorised for and in whom, dosage, contraindications, the boxed warning, warnings and precautions, use in pregnancy, breastfeeding, children and older people, adverse reactions, interactions, overdose, pharmacology, storage, and the label's version history. For the US it reads the application holder's label as published on DailyMed and the FDA's approval record on Drugs@FDA; for the EU it reads each SmPC in the European Commission's product information as published by the EMA, and the EMA's medicines data. Each answer gives the record's own words for the section asked, with the section number, the document's version, its effective date, the SHA-256 of the exact document read and its address, and the source to acknowledge. Where a product information holds several SmPCs (strengths or forms), each is given apart. The indications text is the record's statement; whether a particular use falls within it is not decided, except for an indication from the published list, where the reference lookup's own answer is given beside it. Where the record cannot be read, matched or confirmed for the date, no text is given: the answer is unresolved, with one reason code (insufficient_evidence, authority_inaccessible, conflicting_records, stale_evidence, unsupported_claim_type, snapshot_only) and its meaning.
Annotations the server declares
- title: What does a drug's FDA or EU label say?
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: 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 write4
- 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 17, 2026, 15:18 UTC, unchanged since Nov 17, 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
- 0
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://alphacitation.com/.well-known/oauth-protected-resource
- Authorization servers
- https://alphacitation.com
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- 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.
Tools2 added, 2 changed.+2 added~2 changedView diff
- Added:check_drug_approval_fda_euChanges things
- Added:read_drug_label_fda_euOnly reads
- Changed:lookup_medicine_evidenceOnly readsdescriptioninputSchemaannotations
- Changed:lookup_precedent_rulingOnly readsannotations
Tools2 changed.~2 changedView diff
- Changed:lookup_medicine_evidenceOnly readstitledescriptionannotations
- Changed:lookup_precedent_rulingOnly readsdescriptionannotations
Install
Pinned to version 1.0.4. Values in angle brackets are yours to fill in.
claude mcp add --transport http reference https://alphacitation.com/api/v1/reference/mcpclaude mcp add --transport http reference https://alphacitation.com/api/v1/reference/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__reference__lookup_medicine_evidence",
"mcp__reference__read_drug_label_fda_eu",
"mcp__reference__lookup_precedent_ruling"
],
"ask": [
"mcp__reference__check_drug_approval_fda_eu"
],
"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 reference. Review it before you use it.
Capability tags behind 4 rules
- mcp__reference__check_drug_approval_fda_eu untrusted-input
- mcp__reference__lookup_medicine_evidence untrusted-input
- mcp__reference__read_drug_label_fda_eu untrusted-input
- mcp__reference__lookup_precedent_ruling 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.alphacitation/reference/verify?hash=5be5e347a429f27b1ced6e063aaa404f961b57bce29b00d54db4e4ced2cd2e98" | jq -e '.changed == false'Pinned hash 5be5e347a429, from Nov 20, 2026, 05:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.alphacitation/reference/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.alphacitation/reference)Source: MCP Registry · repository. Synced Nov 20, 2026, 05:17 UTC.
AlphaCitation reference lookup MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the AlphaCitation reference lookup MCP server safe?
- No scan can promise that. What its definitions show: 4 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 AlphaCitation reference lookup MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the AlphaCitation reference lookup 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 AlphaCitation reference lookup MCP server have?
- 4 tools: 1 write, 3 read. check_drug_approval_fda_eu, lookup_medicine_evidence, read_drug_label_fda_eu and lookup_precedent_ruling.
Does the AlphaCitation reference lookup MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the AlphaCitation reference lookup MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the AlphaCitation reference lookup MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 20, 2026. Every change is on this page and in its Atom feed.