# AgingResearch.News (remote · agingresearch.news)

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

- Trust score: 70/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

## Components

- remote · `agingresearch.news`: 70/100 (this document), [markdown](https://verifymcp.io/servers/news-agingresearch-agingresearch-news/api-mcp.md), [page](https://verifymcp.io/servers/news-agingresearch-agingresearch-news/api-mcp)

## Channel facts

- Endpoint: `https://agingresearch.news/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.3.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-18.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (unfollow).
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 76/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 6067 tokens (~209/item across 29 items; 26 tools + 3 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 99/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 98% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 26 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 28 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).
  - Supports UI / widget rendering.

## Install

### How do I install the AgingResearch.News MCP server?

AgingResearch.News is a hosted endpoint at https://agingresearch.news/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http news-agingresearch-agingresearch-news 'https://agingresearch.news/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "news-agingresearch-agingresearch-news": {
      "url": "https://agingresearch.news/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "news-agingresearch-agingresearch-news": {
      "type": "http",
      "url": "https://agingresearch.news/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.news-agingresearch-agingresearch-news]
url = "https://agingresearch.news/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "news-agingresearch-agingresearch-news": {
      "type": "remote",
      "url": "https://agingresearch.news/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add news-agingresearch-agingresearch-news --url 'https://agingresearch.news/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  news-agingresearch-agingresearch-news:
    url: "https://agingresearch.news/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "news-agingresearch-agingresearch-news": {
      "Transport": "http",
      "Url": "https://agingresearch.news/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add news-agingresearch-agingresearch-news -t streamable-http -u 'https://agingresearch.news/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "news-agingresearch-agingresearch-news": {
      "type": "http",
      "url": "https://agingresearch.news/api/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-18 (score 70, +1)

- [security] Tool “count_pipeline” rewrote its description, which is the text the model reads
- [security] Tool “get_asset” rewrote its description, which is the text the model reads
- [security] Tool “get_conference” rewrote its description, which is the text the model reads
- [security] Tool “list_assets” rewrote its description, which is the text the model reads
- [security] Tool “list_papers” rewrote its description, which is the text the model reads
- [cosmetic] “count_pipeline” reworded the description of “organisation”
- [cosmetic] “list_assets” reworded the description of “organisation”
- [cosmetic] “list_grants” reworded the description of “funder”
- [cosmetic] “list_grants” reworded the description of “holder”
- [cosmetic] “list_papers” reworded the description of “system”
- [cosmetic] “list_stories” reworded the description of “system”
- [cosmetic] “search_papers” reworded the description of “system”
- [cosmetic] Tool “get_asset” changed its title: Get a drug or therapy programme → Get a drug or therapy program
- [cosmetic] Tool “list_assets” changed its title: List drug and therapy programmes → List drug and therapy programs

### 2026-10-17 (score 69, 0)

- [security] Tool “get_asset” rewrote its description, which is the text the model reads

### 2026-10-16 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-15 (score 68, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “ask_arn” rewrote its description, which is the text the model reads
- [security] Tool “count_pipeline” rewrote its description, which is the text the model reads
- [security] Tool “find_entities” rewrote its description, which is the text the model reads
- [security] Tool “follow” rewrote its description, which is the text the model reads
- [security] Tool “get_ask_answer” rewrote its description, which is the text the model reads
- [security] Tool “get_asset” rewrote its description, which is the text the model reads
- [security] Tool “get_entity” rewrote its description, which is the text the model reads
- [security] Tool “get_paper” rewrote its description, which is the text the model reads
- [security] Tool “get_trial” rewrote its description, which is the text the model reads
- [security] Tool “list_assets” rewrote its description, which is the text the model reads
- [security] Tool “list_claims” rewrote its description, which is the text the model reads
- [security] Tool “list_conferences” rewrote its description, which is the text the model reads
- [security] Tool “list_follows” rewrote its description, which is the text the model reads
- [security] Tool “list_grants” rewrote its description, which is the text the model reads
- [security] Tool “list_news” rewrote its description, which is the text the model reads
- [security] Tool “list_papers” rewrote its description, which is the text the model reads
- [security] Tool “list_questions” rewrote its description, which is the text the model reads
- [security] Tool “list_stories” rewrote its description, which is the text the model reads
- [security] Tool “list_trials” rewrote its description, which is the text the model reads
- [security] Tool “open_arn” rewrote its description, which is the text the model reads
- [security] Tool “search_arn” rewrote its description, which is the text the model reads
- [security] Tool “search_papers” rewrote its description, which is the text the model reads
- [security] Tool “start_ultradeep” rewrote its description, which is the text the model reads
- [security] Tool “unfollow” rewrote its description, which is the text the model reads
- [functional] Schema quality: good → excellent
- [cosmetic] “get_conference” reworded the description of “min_visibility”
- [cosmetic] “get_paper” reworded the description of “id”
- [cosmetic] “list_papers” reworded the description of “age_link”
- [cosmetic] “list_papers” reworded the description of “min_relevance”
- [cosmetic] “list_papers” reworded the description of “since”
- [cosmetic] “list_papers” reworded the description of “system”
- [cosmetic] “list_papers” reworded the description of “until”
- [cosmetic] “list_stories” reworded the description of “system”
- [cosmetic] “list_trials” reworded the description of “min_relevance”
- [cosmetic] “search_papers” reworded the description of “age_link”
- [cosmetic] “search_papers” reworded the description of “min_relevance”
- [cosmetic] “search_papers” reworded the description of “since”
- [cosmetic] “search_papers” reworded the description of “system”
- [cosmetic] “search_papers” reworded the description of “until”
- [cosmetic] Tool “find_entities” changed its title: Find entities → Find a drug, gene or topic
- [cosmetic] Tool “get_entity” changed its title: Get an entity and its papers → Get a drug, gene or topic and its papers
- [cosmetic] Tool “list_questions” changed its title: List the user's questions to ARN → List the user's questions to AgingResearch.News
- [cosmetic] Tool “list_stories” changed its title: List ARN's stories → List stories

### 2026-10-14 (score 68, +1)

- [security] Tool “ask_arn” rewrote its description, which is the text the model reads
- [cosmetic] Tool “start_ultradeep” changed its title: Start an Ultradeep review → Start a full evidence review

### 2026-10-13 (score 67, 0)

- [security] Resource “agingresearch_news” now points somewhere else: ui://agingresearch-news/sidebar-v2.html → ui://agingresearch-news/sidebar-v3.html
- [security] Resource “evidence_card” now points somewhere else: ui://agingresearch-news/evidence-card-v2.html → ui://agingresearch-news/evidence-card-v3.html
- [security] Resource “story_card” now points somewhere else: ui://agingresearch-news/story-card-v2.html → ui://agingresearch-news/story-card-v3.html
- [security] Tool “list_conferences” rewrote its description, which is the text the model reads
- [security] Tool “list_grants” rewrote its description, which is the text the model reads
- [security] Tool “list_news” rewrote its description, which is the text the model reads
- [security] Tool “list_papers” rewrote its description, which is the text the model reads
- [security] Tool “list_stories” rewrote its description, which is the text the model reads
- [security] Tool “list_trials” rewrote its description, which is the text the model reads
- [security] Tool “search_papers” rewrote its description, which is the text the model reads
- [security] Tool “count_pipeline” rewrote its description, which is the text the model reads
- [security] Tool “find_entities” rewrote its description, which is the text the model reads
- [security] Tool “get_asset” rewrote its description, which is the text the model reads
- [security] Tool “get_conference” rewrote its description, which is the text the model reads
- [security] Tool “get_entity” rewrote its description, which is the text the model reads
- [security] Tool “get_paper” rewrote its description, which is the text the model reads
- [security] Tool “get_trial” rewrote its description, which is the text the model reads
- [security] Tool “list_assets” rewrote its description, which is the text the model reads
- [security] Tool “list_claims” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 180 → 211
- [functional improvement] Stability: unverified → 0.03
- [functional] New tool “ask_arn”
- [functional] New tool “get_ask_answer”
- [functional] New tool “start_ultradeep”

### 2026-10-12 (score 67)

First indexed and scored.

## MCP tools (26)

### `search_papers` (~581 tokens)

Search papers

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.

Input parameters:

- `age_link` (array): How the work itself connects to aging.
- `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 p…
- `category` (array): Category slug. A paper matches when its category or its secondary category is listed.
- `cursor` (string): Opaque cursor from `pagination.next_cursor` of the previous page. Keep the other parameters the same.
- `limit` (integer): Results per page, 1 to 25.
- `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.
- `preprint` (boolean): `true` for preprints only, `false` for peer-reviewed papers only. Omit for both.
- `q` (string, required): Search terms. Supports "quoted phrases", OR and -exclusions.
- `since` (string): Only papers added on or after this UTC date (YYYY-MM-DD; a full ISO timestamp is cut to its date).
- `study_type` (array): Main source of evidence.
- `system` (array): Body system key (see `systems`). A paper matches when it involves any of them. Only papers that have been analyzed have systems.
- `until` (string): Only papers added on or before this UTC date (YYYY-MM-DD).

### `list_papers` (~503 tokens)

List new papers

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.

Input parameters:

- `age_link` (array): How the work itself connects to aging.
- `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 p…
- `category` (array): Category slug. A paper matches when its category or its secondary category is listed.
- `cursor` (string): Opaque cursor from `pagination.next_cursor` of the previous page. Keep the other parameters the same.
- `limit` (integer): Results per page, 1 to 25.
- `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.
- `preprint` (boolean): `true` for preprints only, `false` for peer-reviewed papers only. Omit for both.
- `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.
- `since` (string): Only papers added on or after this UTC date (YYYY-MM-DD; a full ISO timestamp is cut to its date).
- `study_type` (array): Main source of evidence.
- `system` (array): Body system key (see `systems`). A paper matches when it involves any of them. Only papers that have been analyzed have systems.
- `until` (string): Only papers added on or before this UTC date (YYYY-MM-DD).

### `get_paper` (~162 tokens)

Get a paper

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.

Input parameters:

- `id` (string, required): Paper id, e.g. MED-42823970.

### `list_stories` (~267 tokens)

List stories

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.

Input parameters:

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

### `find_entities` (~208 tokens)

Find a drug, gene or topic

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.

Input parameters:

- `cursor` (string): Opaque cursor from `pagination.next_cursor` of the previous page. Keep the other parameters the same.
- `limit` (integer): Results per page, 1 to 25.
- `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.

### `get_entity` (~302 tokens)

Get a drug, gene or topic and its papers

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.

Input parameters:

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

### `list_claims` (~262 tokens)

List findings

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.

Input parameters:

- `cursor` (string): Opaque cursor from `pagination.next_cursor` of the previous page. Keep the other parameters the same.
- `limit` (integer): Results per page, 1 to 25.
- `object` (string): Object 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.
- `subject` (string): Subject text, entity name or entity key (case-insensitive substring).

### `list_trials` (~390 tokens)

List clinical trials

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.

Input parameters:

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

### `get_trial` (~132 tokens)

Get a clinical trial

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.

Input parameters:

- `nct_id` (string, required): The trial's registry number, e.g. NCT04488601 or ISRCTN12345678.

### `list_news` (~187 tokens)

List news

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.

Input parameters:

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

### `list_grants` (~361 tokens)

List research grants

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.

Input parameters:

- `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`.
- `limit` (integer): Results per page, 1 to 25.
- `q` (string): Words of the grant's title ("quoted phrases", OR and -exclusions work).
- `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).

### `list_conferences` (~84 tokens)

List conferences

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.

### `get_conference` (~223 tokens)

Get a conference and its abstracts

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.

Input parameters:

- `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.
- `id` (string, required): Conference id from list_conferences, e.g. gsa.
- `limit` (integer): Results per page, 1 to 25.
- `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.

### `list_assets` (~449 tokens)

List drug and therapy programs

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.

Input parameters:

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

### `get_asset` (~229 tokens)

Get a drug or therapy program

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.

Input parameters:

- `key` (string, required): The asset's key or a code name.

### `count_pipeline` (~369 tokens)

Count the development pipeline

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.

Input parameters:

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

### `follow` (~113 tokens)

Follow a topic

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.

Input parameters:

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

### `unfollow` (~96 tokens)

Stop following a topic

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.

Input parameters:

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

### `list_follows` (~58 tokens)

List what the user follows

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.

### `list_questions` (~66 tokens)

List the user's questions to AgingResearch.News

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.

Input parameters:

- `limit` (integer): How many, 1 to 25.

### `open_arn` (~74 tokens)

AgingResearch.News

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.

Input parameters:

- `tab` (string): Which feed to open on.

### `list_feed` (~29 tokens)

Feed

The sidebar's feed: For you or Top, as story cards.

Input parameters:

- `tab` (string)

### `search_arn` (~30 tokens)

Search

The sidebar's search: topics and papers matching words, as cards.

Input parameters:

- `q` (string, required)

### `ask_arn` (~259 tokens)

Ask AgingResearch.News

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.

Input parameters:

- `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.
- `question` (string, required): The research question in the user's words, in any language; the answer is written in the question's language.

### `start_ultradeep` (~211 tokens)

Start a full evidence review

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.

Input parameters:

- `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.
- `question` (string, required): The research question in the user's words, in any language; the answer is written in the question's language.

### `get_ask_answer` (~114 tokens)

Read an Ask answer

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.

Input parameters:

- `question_id` (integer, required): The question_id ask_arn or start_ultradeep gave.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/news-agingresearch-agingresearch-news/api-mcp#diagnostics

## Score history

- 2026-10-18: 70
- 2026-10-17: 69
- 2026-10-16: 69
- 2026-10-15: 68
- 2026-10-14: 68
- 2026-10-13: 67
- 2026-10-12: 67

## Common questions

### What is the AgingResearch.News MCP server?

AgingResearch.News is an MCP server listed in the public MCP registry as news.agingresearch/agingresearch-news. Search aging research papers, evidence, trials and grants; follow topics through Sign in with ARN. This page covers its hosted endpoint (https://agingresearch.news/api/mcp).

### Is the AgingResearch.News MCP server safe to use?

AgingResearch.News scores 70 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the AgingResearch.News MCP server expose?

AgingResearch.News exposes 26 tools: search_papers, list_papers, get_paper, list_stories, find_entities, and 21 more. Their descriptions and schemas cost roughly 5,759 tokens of context every time the server is loaded.

### Does the AgingResearch.News MCP server require authentication?

No. We connected to AgingResearch.News without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the AgingResearch.News MCP server still maintained?

AgingResearch.News is still listed as active in the MCP registry. We last reached this channel on 18 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://agingresearch.news/api/mcp
- Website: https://agingresearch.news/connect
- Changelog RSS feed: https://verifymcp.io/servers/news-agingresearch-agingresearch-news/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/news-agingresearch-agingresearch-news/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/news-agingresearch-agingresearch-news/api-mcp