AgingResearch.News

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Search aging research papers, evidence, trials and grants; follow topics through Sign in with ARN.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "AgingResearch.News": {
      "url": "https://agingresearch.news/api/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (26)

• search_papers read-only

  Use this when the user asks what research has found on a question in the biology of aging or an age-related disease, often without the word aging: senescence and senolytics, epigenetic clocks, partial reprogramming, mitochondrial dysfunction, NAD+, inflammaging and immune aging, ovarian aging and menopause, neurodegeneration, cardiovascular and metabolic decline, sarcopenia, regeneration, and long-lived species such as naked mole rats and whales. Searches the titles and abstracts of every paper AgingResearch.News has read, best match first. Supports "quoted phrases", OR and -exclusions; narrow by study type, category, body system, link to aging, preprint status, author or the date it was added. By default only papers about aging. Each result gives its study type, how it bears on aging, its subjects and its story if one was published. The record is not all of PubMed: no match does not mean no study exists. Not for personal medical advice, symptoms or product recommendations. Read one in full with get_paper.

  Parameters:

  • q (required) — string — Search terms. Supports "quoted phrases", OR and -exclusions.
  • limit — integer — Results per page, 1 to 25.
  • since — string — Only papers added on or after this UTC date (YYYY-MM-DD; a full ISO timestamp is cut to its date).
  • until — string — Only papers added on or before this UTC date (YYYY-MM-DD).
  • author — string — Papers by an author. A name matches every author who answers to it: the words in any order, with or without accents, an initial standing for any name it begins (`sinclair d`). An `author_id` from a paper's `authors_full` (an OpenAlex author id such as `A5022713595`, or an ORCID iD) matches that one person.
  • cursor — string — Opaque cursor from `pagination.next_cursor` of the previous page. Keep the other parameters the same.
  • system — array — Body system key (see `systems`). A paper matches when it involves any of them. Only papers that have been analyzed have systems.
  • age_link — array — How the work itself connects to aging.
  • category — array — Category slug. A paper matches when its category or its secondary category is listed.
  • preprint — boolean — `true` for preprints only, `false` for peer-reviewed papers only. Omit for both.
  • study_type — array — Main source of evidence.
  • min_relevance — number — How closely papers must bear on aging, 0 to 3. Leave out for papers about aging; 1 adds adjacent papers; 0 returns every paper read, most of them not about aging.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• list_papers read-only

  Use this when the user asks what is new: the latest papers in a field (mitochondrial dysfunction, immune aging, senolytics), of a study type such as randomized trials, on a body system, or by one author (author takes a name, or an author_id from get_paper), for example to shortlist a lab's journal club. Lists the newest papers AgingResearch.News has read, by the date they were added, with the same filters as search_papers and an optional words filter. For the papers that best answer a question, use search_papers.

  Parameters:

  • q — string — Full-text filter over title and abstract. Supports "quoted phrases", OR and -exclusions. Results stay in date order; use search_papers for ranked results.
  • limit — integer — Results per page, 1 to 25.
  • since — string — Only papers added on or after this UTC date (YYYY-MM-DD; a full ISO timestamp is cut to its date).
  • until — string — Only papers added on or before this UTC date (YYYY-MM-DD).
  • author — string — Papers by an author. A name matches every author who answers to it: the words in any order, with or without accents, an initial standing for any name it begins (`sinclair d`). An `author_id` from a paper's `authors_full` (an OpenAlex author id such as `A5022713595`, or an ORCID iD) matches that one person.
  • cursor — string — Opaque cursor from `pagination.next_cursor` of the previous page. Keep the other parameters the same.
  • system — array — Body system key (see `systems`). A paper matches when it involves any of them. Only papers that have been analyzed have systems.
  • age_link — array — How the work itself connects to aging.
  • category — array — Category slug. A paper matches when its category or its secondary category is listed.
  • preprint — boolean — `true` for preprints only, `false` for peer-reviewed papers only. Omit for both.
  • study_type — array — Main source of evidence.
  • min_relevance — number — How closely papers must bear on aging, 0 to 3. Leave out for papers about aging; 1 adds adjacent papers; 0 returns every paper read, most of them not about aging.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_paper read-only

  Use this when the user wants one paper in depth: what it did and found, in which species and how many subjects, its caveats, who wrote it and where they work. Takes a paper id such as MED-42823970 from another tool's results. Returns how it bears on aging, the language it was published in with its own-language title when that is not English, every author with ORCID iD and institutions, its full story (headline, body, why it matters, caveats) when published, the drugs, genes and processes it studies and its findings, and a link to the paper at its source. It does not replace the paper.

  Parameters:

  • id (required) — string — Paper id, e.g. MED-42823970.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• list_stories read-only

  Use this when the user wants a readable round-up of recent findings: what happened this week in aging research, the notable results in a field, or a short list for a journal club. Lists the stories AgingResearch.News wrote about new papers, newest first, each checked against its paper: a plain-language headline, body, why it matters and caveats, with the paper. Narrow by category, body system, study type or publication date. Only the papers chosen for a story; for every paper on a question use search_papers.

  Parameters:

  • limit — integer — Results per page, 1 to 25.
  • since — string — Only stories published on or after this UTC date (YYYY-MM-DD).
  • until — string — Only stories published on or before this UTC date (YYYY-MM-DD).
  • cursor — string — Opaque cursor from `pagination.next_cursor` of the previous page. Keep the other parameters the same.
  • system — array — Body system key (see `systems`). A paper matches when it involves any of them. Only papers that have been analyzed have systems.
  • category — array — Category slug. A paper matches when its category or its secondary category is listed.
  • study_type — array — Main source of evidence.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• find_entities read-only

  Use this to find the type and key of what a question names (a drug, supplement or diet, a gene or protein, a biological process, a disease, a biomarker, an organism, a method or a hallmark of aging) before get_entity, list_claims or list_grants. Matches part of a name, a key or a known synonym, case-insensitive, most-studied first, with how many papers involve each. Pass a result's type and key to get_entity.

  Parameters:

  • q — string — Match on name or key, case-insensitive substring.
  • type — string — Entity type, e.g. intervention, gene, pathway, component, system, method, hallmark, phenotype, organism, tissue, disease, biomarker, mesh.
  • limit — integer — Results per page, 1 to 25.
  • cursor — string — Opaque cursor from `pagination.next_cursor` of the previous page. Keep the other parameters the same.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_entity read-only

  Use this for questions about one drug, supplement, gene, process or disease, such as: is there human evidence for this intervention; has the finding been replicated by independent labs; in which species; what trials test it and how many have posted no results; who funds the work and which companies are tied to it; what the newest papers on it report. Takes a type and key from find_entities (intervention rapamycin, disease sarcopenia). Returns the entity with the papers that involve it, newest first, and the role it plays in each. For an intervention, a gene or a process, `evidence` gives its evidence as structure, never as a grade: the species its findings reach and whether independent labs found the same there, the labs and countries behind them, the findings against, its trials and those with no results posted, its funders and its company ties. The counts are of the papers AgingResearch.News has read, not of all the literature. Not for personal medical advice or doses.

  Parameters:

  • type (required) — string — Entity type.
  • key (required) — string — Entity key within its type.
  • limit — integer — Results per page, 1 to 25.
  • cursor — string — Opaque cursor from `pagination.next_cursor` of the previous page. Keep the other parameters the same.
  • min_relevance — number — Lowest aging-relevance score for the papers listed. Default: no filter.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• list_claims read-only

  Use this when the user asks what has been found about a relation: does an intervention extend lifespan, and in which organisms; what lowers a biomarker; what acts on a process. Lists findings extracted from papers as subject, relation and object (for example rapamycin extends_lifespan in Mus musculus), with organism, conditions, effect size and the paper, newest first. Narrow by subject, object, relation, organism or paper. Check a finding that matters against its paper with get_paper. Not for personal medical advice.

  Parameters:

  • limit — integer — Results per page, 1 to 25.
  • cursor — string — Opaque cursor from `pagination.next_cursor` of the previous page. Keep the other parameters the same.
  • object — string — Object text, entity name or entity key (case-insensitive substring).
  • subject — string — Subject text, entity name or entity key (case-insensitive substring).
  • organism — string — Organism, e.g. Homo sapiens, Mus musculus (case-insensitive substring).
  • paper_id — string — Only claims from this paper.
  • relation — string — Exact relation, e.g. increases, decreases, associated_with, extends_lifespan.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• list_trials read-only

  Use this when the user asks about clinical trials on aging or an age-related condition: what is recruiting, what changed lately (a new status, a completion, results posted), which trials test a drug, or which companies run them. Lists trials from ClinicalTrials.gov that bear on human aging, newest registry update first: phase, status, sponsor, size, conditions, interventions and the latest change. Narrow by words, phase, recruitment status, focus, industry sponsor or update date. Only trials about aging, not every registered trial. Read one with get_trial.

  Parameters:

  • q — string — Words that must all appear in the trial's titles, conditions, interventions, keywords or sponsor (case-insensitive).
  • focus — array — The trial's main connection to aging (see `focus`).
  • limit — integer — Results per page, 1 to 25.
  • phase — array — Phase: `1` (early phase 1 and phase 1), `2`, `3`, `4`, or `none` for studies with no phase.
  • since — string — Only trials the registry updated on or after this date (YYYY-MM-DD).
  • cursor — string — Opaque cursor from `pagination.next_cursor` of the previous page. Keep the other parameters the same.
  • status — array — Recruitment status: `recruiting` (recruiting, not yet recruiting or by invitation), `active` (active, not recruiting), `completed`, or `stopped` (terminated, withdrawn or suspended).
  • industry — boolean — `true` for trials whose lead sponsor is a company, `false` for the rest. Omit for both.
  • min_relevance — number — Lowest aging-relevance score to include (0 to 3, see `relevance`). Default 1.8, the trials about aging.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_trial read-only

  Use this when the user asks about one clinical trial by its registry number (NCT, ISRCTN, ChiCTR, CTRI, CTIS and the rest): its design, outcomes and dates, what changed and when, and which papers cite it. Returns the registry's summary, outcomes and dates, every change recorded and the papers that cite it. A record from the WHO ICTRP carries its attribution and the day WHO processed it, to show with it.

  Parameters:

  • nct_id (required) — string — The trial's registry number, e.g. NCT04488601 or ISRCTN12345678.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• list_news read-only

  Use this when the user asks about events in aging research and the longevity industry: company financings and deals, trial readouts, approvals and regulators, policy, conferences. One story per event, newest first, written by AgingResearch.News with a link to every outlet that covered it. Narrow by words, kind or date. Only news of this field; not for general, political or market news.

  Parameters:

  • q — string — Words that must all appear in the story's headline or summary (case-insensitive).
  • kind — string — Only stories of this kind.
  • limit — integer — Results per page, 1 to 25.
  • since — string — Only stories with coverage on or after this UTC date (YYYY-MM-DD).
  • cursor — string — Opaque cursor from `pagination.next_cursor` of the previous page. Keep the other parameters the same.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• list_grants read-only

  Use this when the user asks who funds work on a target, a drug, a process or a lab, how much and since when, or what a funder pays for in aging research. Lists research grants from NIH, the EU (CORDIS), UKRI and Wellcome that bear on aging, newest award first: title, funder, holder, investigators, amount, funded period, scheme and a link to the record. Narrow by an entity the title names (type:key, as find_entities gives), a funder or holder key, title words or award date. Other funders and private money are not here; for company financings use list_news.

  Parameters:

  • q — string — Words of the grant's title ("quoted phrases", OR and -exclusions work).
  • limit — integer — Results per page, 1 to 25.
  • since — string — Only grants awarded on or after this date (YYYY-MM-DD).
  • until — string — Only grants awarded on or before this date (YYYY-MM-DD).
  • cursor — string — Opaque cursor from `pagination.next_cursor` of the previous page. Keep the other parameters the same.
  • entity — string — Only grants whose titles name this entity, as `type:key` (see /entities), e.g. `intervention:rapamycin` or `disease:sarcopenia`.
  • funder — string — Only grants from this funder, by its organization key or name, e.g. `nia` or `wellcome`.
  • holder — string — Only grants held by this organization (its key) or investigator (`person:` and their key), e.g. `buck-institute-for-research-on-aging`.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• list_conferences read-only

  Use this when the user asks which meetings on aging research and age-related disease are coming up, or which have just been held. The conference calendar: meetings still to come or on, soonest first, then recent ones, each edition with its dates, place and how many of its abstracts are held. Read one, and an edition's abstracts, with get_conference.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_conference read-only

  Use this when the user asks about one meeting from list_conferences, or what was presented there. Returns its organizer, site and every edition; with `edition`, that edition's abstracts worth reading, the most relevant first, each with its number, format and the paper it was later published as. An abstract is not a peer-reviewed paper. Read one in full with get_paper.

  Parameters:

  • id (required) — string — Conference id from list_conferences, e.g. gsa.
  • limit — integer — Results per page, 1 to 25.
  • cursor — string — Opaque cursor from `pagination.next_cursor` of the previous page. Keep the other parameters the same.
  • edition — string — An edition from `editions`, e.g. 2025: list its abstracts.
  • min_visibility — string — With `edition`: which abstracts to list, from the most to the least worth reading: `core`, `visible`, `searchable`, `matchable`, `out`. Default `visible`, those worth reading.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• list_assets read-only

  Use this when the user asks which drugs or therapies are in development against a target, a mechanism, a hallmark of aging or an age-related disease, who develops them and how far each has got. Lists drug and therapy programs (assets), furthest stage first: each with its developers and partners, code names, modality, targets, mechanism, indications with the stage of each, hallmarks of aging and lifespan evidence. Narrow by target (a gene symbol such as GLP1R, or a process), mechanism words, modality, hallmark, indication, stage, the developer's country, an organization or a name. Read one in full with get_asset; count them with count_pipeline. An account whose plan includes drug and therapy programs reads every record in full; others read an outline, as the site's asset pages show it.

  Parameters:

  • q — string — Letters and digits in any of the asset's names or code names (`UBX1325` matches UBX-1325).
  • limit — integer — Results per page, 1 to 25.
  • stage — string — Stage: with `indication`, the stage for that indication; otherwise the asset's furthest stage.
  • cursor — string — Opaque cursor from `pagination.next_cursor` of the previous page. Keep the other parameters the same.
  • target — string — A target: a gene symbol or key (`GLP1R`, `bcl2l1`) or a process key (`mtor`, `cellular-senescence`).
  • country — string — The developer's country, ISO 3166 alpha-2 (`US`, `GB`, `CH`).
  • hallmark — string — A hallmark of aging the asset acts on.
  • modality — string — The kind of therapy (see `modality`).
  • mechanism — string — Words that must all appear in the asset's mechanism line (case-insensitive).
  • indication — string — A disease, by name or entity key (`idiopathic pulmonary fibrosis`, `alzheimer-disease`).
  • organisation — string — An organization key: the assets it develops, partners on or licensed out.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_asset read-only

  Use this when the user asks about one drug or therapy program by its name or any code name (ubx1325, UBX-1325, BMS-986278). Returns its developers, partners and licensors, targets, mechanism, modality, every indication with its stage and source, lifespan evidence and news; its published research (papers a year and by kind, species reached, the newest papers and abstracts); designations (orphan, breakthrough, fast track, PRIME) by agency; an approved drug's patents and exclusivity; its development status (active, inactive, discontinued or approved) with reasons and stage by country; its next catalyst (a PDUFA date, an advisory committee, an expected readout, with how exactly its day is known); and its newest events from filings and regulators (topline results, complete response letters, clinical holds, programs stopped). An account whose plan includes drug and therapy programs reads every record in full; others read an outline, as the site's asset pages show it.

  Parameters:

  • key (required) — string — The asset's key or a code name.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• count_pipeline read-only

  Use this when the user asks how many drug and therapy programs there are, or how a field's pipeline splits. Counts programs grouped by stage, modality, target, hallmark, indication, the developer's country or the developer, with each group's count at each stage. Takes list_assets' filters: by=target with indication=obesity counts the targets of obesity programs. An account whose plan includes drug and therapy programs reads every record in full; others read an outline, as the site's asset pages show it.

  Parameters:

  • q — string — Letters and digits in any of the asset's names or code names (`UBX1325` matches UBX-1325).
  • by — string — What to group by.
  • limit — integer — Results per page, 1 to 25.
  • stage — string — Stage: with `indication`, the stage for that indication; otherwise the asset's furthest stage.
  • target — string — A target: a gene symbol or key (`GLP1R`, `bcl2l1`) or a process key (`mtor`, `cellular-senescence`).
  • country — string — The developer's country, ISO 3166 alpha-2 (`US`, `GB`, `CH`).
  • hallmark — string — A hallmark of aging the asset acts on.
  • modality — string — The kind of therapy (see `modality`).
  • mechanism — string — Words that must all appear in the asset's mechanism line (case-insensitive).
  • indication — string — A disease, by name or entity key (`idiopathic pulmonary fibrosis`, `alzheimer-disease`).
  • organisation — string — An organization key: the assets it develops, partners on or licensed out.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• follow

  Use this when the user asks to follow a drug, gene, process, disease or other entity on AgingResearch.News, so its new papers reach them. Takes the type and key that find_entities or get_entity give. Following is saved to the user's account: new papers on it appear in For you and the daily follow email.

  Parameters:

  • type (required) — string — The entity's type, as find_entities or get_entity gives it.
  • key (required) — string — The entity's key within its type, such as rapamycin.

  Hints: read-only no · destructive no · idempotent yes · open-world no

• unfollow destructive

  Use this when the user asks to stop following a drug, gene, process or other entity on AgingResearch.News. Takes the type and key that list_follows, find_entities or get_entity give. Removes the follow from the user's account.

  Parameters:

  • type (required) — string — The entity's type, as find_entities or get_entity gives it.
  • key (required) — string — The entity's key within its type, such as rapamycin.

  Hints: read-only no · destructive yes · idempotent yes · open-world no

• list_follows read-only

  Use this when the user asks what they follow on AgingResearch.News. Lists the drugs, genes, processes and saved searches their account follows, newest first, each with its page; an entity's id is the type:key that unfollow takes.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• list_questions read-only

  Use this when the user asks about questions they asked AgingResearch.News (Ask) before. Lists their most recent conversations, newest first, each with its title and its address, where the answer and its sources are.

  Parameters:

  • limit — integer — How many, 1 to 25.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• open_arn read-only

  Use this when the user asks to open AgingResearch.News or to see their feed, follows and recent questions in one place. Shows the newest stories (For you when the user is signed in, else Top), what they follow and their recent questions, with search.

  Parameters:

  • tab — string — Which feed to open on.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• list_feed read-only

  Only for the AgingResearch.News sidebar app: returns the reader's For you or Top feed as story cards for the sidebar to show. To answer what is new in aging research, use list_stories or list_papers.

  Parameters:

  • tab — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• search_arn read-only

  Only for the AgingResearch.News sidebar app: the sidebar search box's results, the topics a query names (to open or follow) and the papers that match it most closely, as cards. To answer a research question, use search_papers; to find a drug, gene or topic, use find_entities.

  Parameters:

  • q (required) — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• ask_arn

  Use this when the user asks a research question on the biology of aging, longevity interventions, age-related disease, or the people and companies of the field (for example: does rapamycin extend lifespan in people, what is known about senolytics for frailty, who works on epigenetic clocks). Not for personal medical advice, doses or symptoms. It answers from AgingResearch.News's own record of papers, trials, approvals, mouse lifespan results, human genetics, researchers and companies, and says when that record is thin. Returns an answer of at most about 350 words with numbered sources, each linked to its page, and the conversation's address. It spends one of the user's Ask questions for the day on their AgingResearch.News account. Pass conversation_id for a follow-up. If the answer takes longer than a call allows, the result says so: read it with get_ask_answer and its question_id.

  Parameters:

  • question (required) — string — The research question in the user's words, in any language; the answer is written in the question's language.
  • conversation_id — string — To ask a follow-up in a conversation this tool or ask_arn started: its `conversation.id`. Leave out to start a new conversation.

  Hints: read-only no · destructive no · idempotent no · open-world yes

• start_ultradeep

  Use this when the user asks for a full review of the evidence on a research question in aging or longevity, beyond a short answer. Not for personal medical advice, doses or symptoms. It writes, over several minutes, a review in five sections: the bottom line, the evidence by kind of study, contradictions and gaps, how far it has got toward patients, and what would change the answer. It is started on the user's own AgingResearch.News account and counts against their plan's Ultradeep reviews. Returns at once with the address of the conversation where the review appears and a question_id: get_ask_answer says where it stands and gives the review once it is in.

  Parameters:

  • question (required) — string — The research question in the user's words, in any language; the answer is written in the question's language.
  • conversation_id — string — To ask a follow-up in a conversation this tool or ask_arn started: its `conversation.id`. Leave out to start a new conversation.

  Hints: read-only no · destructive no · idempotent no · open-world yes

• get_ask_answer read-only

  Use this when ask_arn or start_ultradeep said an answer is still being written, or the user wants it again: it reads that question's answer by the question_id they gave: the answer with its numbered sources once it is written, or where it stands while it is written. Waits up to 20 seconds for a short answer that is nearly done; an Ultradeep review takes several minutes.

  Parameters:

  • question_id (required) — integer — The question_id ask_arn or start_ultradeep gave.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

Publisher website

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.