Amass is now in Claude's connector directory. Connect it in one click

Amass

Model Context Protocol

Cited biomedical evidence, inside

Pull papers, trials, sponsors, and targets straight into Claude — citations attached, no copy-pasting, no leaving the chat. Also works in ChatGPT, Codex, Claude Code, and any MCP-compatible assistant.
Get started with:
APIBuilding with the API instead? One REST API across five cores — cross-linked and cited.

Works with

Claude
Claude Code
ChatGPT
Codex
Microsoft 365 CopilotOn request

Why MCP for evidence

Three things you get that you don't from web search.

Better than web search for evidence questions.

Structured filters — date, journal quality, retraction status, identifiers — consistently surface higher-signal results than open-web retrieval.

Agentic, not one-shot.

Assistants chain searches together — broad scan, filter, deep-dive on specific records — without the user having to drive each step.

Citations back to sources.

Every result links to its underlying record, so claims are auditable end-to-end.

How it works

Just sign in with your existing Amass account.

Connect Amass MCP from any supported assistant and sign in once with your existing Amass account. That's the whole setup — nothing else to configure. The assistant then queries Amass on your behalf, with the same access your plan already gives you.

See what you can create with the Amass MCP

Install

Connect Amass to your assistant.

Same connector, same one-time Amass sign-in everywhere — pick your tool.

Amass is listed in Claude's connector directory as Amass Connector — find it in the app and connect in one click. Available on Claude Pro, Max, Team, and Enterprise.

Open Amass Connector in Claude

Press Connect on the listing and sign in once with your existing Amass account — that's the whole install. Your plan's access applies.

See the step-by-step walkthrough (with screenshots)
  1. Find Amass in Claude's connector directory.

    Use the button above — or in Claude, open Settings → Connectors → Browse connectors and search for Amass.

    Claude's directory overlay on the Connectors tab with 'amass' in the search field and the Amass Connector listing in the results
  2. Open the listing, press Connect, and sign in with your Amass account.

    No URLs to paste, nothing to configure — the listing carries the setup. One-time sign-in, and your Amass plan's access applies.

    The Amass Connector listing page in Claude's directory — life sciences intelligence description, the *Cores it exposes, and the Connect button top-right

You'll be redirected to sign in with your Amass account. That's it — your existing plan's access applies through the MCP.

The skill

Install the Biomedical Evidence Scout skill to get more out of Amass.

The skill is a small instruction pack that teaches the assistant how to use Amass well — when to filter by journal quality, how to structure landscape scans, when to drill into a specific record. Works in any assistant that supports the open SKILL.md format: Claude, Codex, GitHub Copilot, Gemini CLI.

See it in action — the Biomedical Evidence Scout in the Skills & Prompts library, with a real KRAS G12C landscape briefing built from live Amass data.

How do I install the skill?

Install every Amass skill in one step with npx skills add amass-technologies/public-skills. Or grab a file from the amass-technologies/public-skills repo: double-click the .skill on Mac to install it into Claude, or unzip the .zipinto the tool's skills directory:

  • Claude Code: ~/.claude/skills/
  • Codex: ~/.codex/skills/
  • Gemini CLI: ~/.gemini/skills/

Try it

Once it's connected, start asking.

Switch between baseline MCP queries the connector handles well, and the harder asks the skill is built to make easier.

Clinical / translational

Lp(a)HORIZON deep dive

Can you pull up Lp(a)HORIZON and tell me the key trial details, whether results are available, and any papers linked to it?

Returns: NCT ID, phase, sponsor, status, enrollment, countries, endpoints, posted results, and linked publications.

Target / mechanism

Recent TREM2 mechanisms

What are the most important recent TREM2 mechanism papers, and what do they suggest about TREM2 as an Alzheimer's target?

Returns: Ranked papers with journal, year, citations, PMID/DOI, model system, and core mechanistic claims.

Competitive / BD

RayzeBio active trials

Which RayzeBio radiopharmaceutical trials are currently active, and what are the main assets, indications, and timelines?

Returns: Active or recruiting trials, assets such as RYZ101/RYZ801/RYZ811/RYZ401, indications, phase, NCT IDs, enrollment, and completion dates.

See it in action

A real query, in Claude, with citations.

Our CTO Alex shows how it works, in about 90 seconds.

Enterprise

Deploying to a Microsoft 365 environment?

Amass can be deployed inside Microsoft 365 Copilot as a declarative agent, sideloaded by your IT admin and surfaced across Teams, Outlook, Word, and Excel. The same Amass MCP runs underneath, with the same Amass-plan-based auth — no separate licenses, no new API keys.

Talk to us

Changelog

What we've shipped so far.

Here's what changed for the tools and filters you call, newest first.

  1. v5

    International trials and PatentCore

    July 2026

    TrialCore now spans non-US trials from the WHO ICTRP, and PatentCore adds patents as a new linked core.

    • TrialCore search and lookup now cover 1.2M+ trials — ClinicalTrials.gov plus non-US national registries via the WHO ICTRP (EUCTR, ChiCTR, JPRN, ISRCTN, and more).
    • Every trial record carries its source: a native registry ID (populated even for non-US trials, which have no NCT Id), the source registry, and a link to the trial on that registry.
    • The get_amass_trialcore_record tool now accepts a registry ID (not just an Amass Id or NCT Id), so you can fetch non-US trials by their native registry id.
    • PatentCore search and lookup (preview) — patent publications with bibliographic metadata, full text (title, abstract, claims, description), CPC/IPC classifications, inventors/assignees, key dates, and citation lineage. Search the full text with filters for jurisdiction, classification, assignee/inventor, dates, and citation count.
    • PatentCore search collapses each patent family to one result, so an invention filed across many jurisdictions takes a single slot — the collapsed siblings' Amass IDs ride along on the kept record.
    • Patent records cross-link to DrugCore (the drugs disclosed in or linked to a patent) and BioMedCore (via references), and you can look a patent up directly by its publication number or Amass Id.
  2. v4

    GeneCore, target intelligence, and drug targets

    June 2026

    GeneCore brings human genes into the linked cores with a full target-intelligence layer and DrugCore now carries the gene targets each drug acts on.

    • GeneCore search and lookup — harmonized gene records with approved symbols, names, synonyms, gene families, gene type (biotype), RefSeq functional summary, genomic location, external identifiers, and UniProt protein annotations.
    • Search filters for gene type/biotype, druggability, DepMap essentiality, ChEMBL target class, clinical-precedent tractability (by modality and stage), curated safety liabilities, and gnomAD LOEUF constraint.
    • DrugCore records now return each drug's mechanisms of action — how it acts on each pharmacological target, its mode of action, and the target genes it hits.
    • Records link both ways: gene records point to the drugs (DrugCore) that target them, and drug records now carry their gene targets.
  3. v3

    RegulatoryCore and DrugCore

    June 2026

    Coverage extends past papers and trials into the regulatory record and the drugs themselves — each core cross-linked to the rest.

    • RegulatoryCore search and lookup — FDA and EMA on one schema, from NDA/BLA approvals to EMA marketing authorizations. Filter by agency, molecule type, authorization status, authorization date, and orphan designation; cross-agency by default.
    • DrugCore search and lookup — harmonized drugs and molecules with trade names, synonyms, modality, clinical stage, and chemical structure. Filter by modality and clinical stage.
    • A new tool pulls the full text of a single regulatory document section — FDA labels and reviews, EMA SmPCs and EPARs.
    • Records now link across all four cores: a drug connects to its trials, its literature, and its regulatory authorizations.
  4. v2

    Better search, richer records

    May 2026

    The two launch cores grew filters, optional full text, and the cross-links that tie papers and trials together.

    • BioMedCore search gained filters for publication date, journal quality (JuFo tier), retraction status, and author or institution — by name, ORCID, or ROR.
    • TrialCore search gained filters for phase, recruitment status, study type, intervention type, start date, and whether results have posted.
    • Fetching a publication can now return its full text on request, not just the abstract.
    • Records carry their cross-references — publication-to-trial links, plus what each record cites and what cites it.
  5. v1

    Launch — BioMedCore and TrialCore

    April 2026

    The first release: two cores, each with a search tool and a direct-lookup tool.

    • BioMedCore — search and fetch across 39M+ PubMed and PMC publications, abstracts included.
    • TrialCore — search and fetch across 575K+ ClinicalTrials.gov trials, with protocols, sponsors, and endpoints.
    • Look any record up directly by identifier — PMID or DOI for papers, NCT Id for trials.

FAQ

Honest answers.

Which assistants is the Amass MCP available in?

Claude (Pro/Max/Team/Enterprise — listed in the connector directory), ChatGPT (Plus/Business/Enterprise/Edu — listed in the plugin directory), Claude Code, Codex CLI. Microsoft 365 Copilot via enterprise deployment. Perplexity, Gemini CLI, and other MCP-compatible clients should also work — let us know if you try one of these.

Is the connector approved by Anthropic, OpenAI, or others?

Amass is listed in Claude's connector directory (as a community connector) and in ChatGPT's plugin directory, the former app store — one-click installs in both, no custom setup. Other MCP-compatible assistants install it as a custom connector, which works the same way functionally.

Do I need an API key?

No. The MCP authenticates via your existing Amass plan. You'll sign in once when you connect.

Does this work on ChatGPT Plus?

Yes. Amass MCP is available on ChatGPT Plus, Business, Enterprise, and Edu — install in one click from ChatGPT's plugin directory (the former app store). If your tenant restricts third-party app installs, a developer-mode fallback is available on the install page.

What data does Amass have access to?

Only the queries the assistant sends and the responses we return. The assistant runs on your provider's infrastructure, not ours.

My company uses Microsoft 365 — what are my options?

We can ship a declarative agent backed by the same Amass MCP for sideload by your IT admin. See the Enterprise section above and get in touch.