# Oliver's mTOR Atlas (npm · mtor-atlas-mcp)

Evidence-labelled mTOR research: studies, entities, pathway claims, contradictions, open questions.

- Trust score: 79/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-25

## Components

- remote · `mtor-atlas-mcp.mtor-atlas.workers.dev`: 75/100, [markdown](https://verifymcp.io/servers/open-mtor-atlas-mtor-atlas/mtor-atlas-mcp-2.md), [page](https://verifymcp.io/servers/open-mtor-atlas-mtor-atlas/mtor-atlas-mcp-2)
- npm · `mtor-atlas-mcp`: 79/100 (this document), [markdown](https://verifymcp.io/servers/open-mtor-atlas-mtor-atlas/mtor-atlas-mcp.md), [page](https://verifymcp.io/servers/open-mtor-atlas-mtor-atlas/mtor-atlas-mcp)

## Channel facts

- Registry: `npm`
- Package: `mtor-atlas-mcp`
- Version: `1.3.3`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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 2026-10-25.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 30 of 92 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 7 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 65/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1917 tokens (~147/item across 13 items; 13 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 80/100
  - Stability observed for 24 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 92/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 77% 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 13 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Oliver's mTOR Atlas MCP server?

Oliver's mTOR Atlas runs locally as an npm package, launched with npx -y mtor-atlas-mcp. 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 open-mtor-atlas-mtor-atlas -- npx -y mtor-atlas-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "open-mtor-atlas-mtor-atlas": {
      "command": "npx",
      "args": [
        "-y",
        "mtor-atlas-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "open-mtor-atlas-mtor-atlas": {
      "command": "npx",
      "args": [
        "-y",
        "mtor-atlas-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add open-mtor-atlas-mtor-atlas -- npx -y mtor-atlas-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "open-mtor-atlas-mtor-atlas": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "mtor-atlas-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add open-mtor-atlas-mtor-atlas --command npx --arg -y --arg mtor-atlas-mcp
```

### Hermes

```yaml
mcp_servers:
  open-mtor-atlas-mtor-atlas:
    command: "npx"
    args: ["-y", "mtor-atlas-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "open-mtor-atlas-mtor-atlas": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "mtor-atlas-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add open-mtor-atlas-mtor-atlas -t stdio -c npx -a -y mtor-atlas-mcp
```

### Other

```json
{
  "mcpServers": {
    "open-mtor-atlas-mtor-atlas": {
      "command": "npx",
      "args": [
        "-y",
        "mtor-atlas-mcp"
      ]
    }
  }
}
```

## 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.

### 2026-10-25 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-23 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-21 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-19 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-17 (score 75, 0)

- [functional regression] Schema quality: 128 → 147
- [functional improvement] Tool coverage: 55% → 77%
- [functional] Package version: 1.3.0 → 1.3.3

### 2026-10-16 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-14 (score 74, +36)

- [security improvement] Injection markers: unverified → pass
- [functional regression] Schema quality: pass → fail
- [functional improvement] Tool coverage: 43% → 55%
- [functional improvement] Stability: unverified → 0.43
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass

### 2026-10-13 (score 38, −35)

- [security regression] Stability: 0.37 → unverified
- [security regression] Tool safety: pass → unverified
- [functional regression] Security disclosure: unverified → fail
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Capabilities: pass → unverified
- [functional] First check of Schema quality: unverified
- [functional] Package version: 1.2.2 → 1.3.0

## MCP tools (13)

### `atlas_about` (~61 tokens)

About the Atlas

Dataset version, corpus snapshot date, counts, evidence-code legend and how to cite the dataset. When the Atlas does not report the contested and conflicting counts itself, derived_counts adds them, computed from the relations, so they can be compared with find_contradictions.

### `search_studies` (~249 tokens)

Search studies

Search the curated studies by keywords, optionally filtered by evidence code, a linked entity (gene, drug, disease...) and year range. Searches title, finding, authors (author-list form "Sabatini DM" and full names of profiled authors), PMID, DOI, PMCID, linked entities and their synonyms, journal, model system and the abstract excerpt. A query that is a PMID or DOI returns that study. Returns summary records with evidence codes and URLs.

Input parameters:

- `entity` (string): Only studies linked to this entity (name, synonym or id), e.g. "Rheb".
- `evidence_code` (array): Keep only these evidence codes, e.g. ["H","S"] for human evidence.
- `limit` (integer): Maximum 50; a larger value is capped at 50.
- `offset` (integer): For the next page: pass next_offset from the previous answer.
- `query` (string): Keywords, e.g. "rapamycin lifespan mice", a person ("Claudio De Virgilio"), a PMID or a DOI. Omit to list by filters only.
- `year_from` (integer)
- `year_to` (integer)

### `get_study` (~102 tokens)

Get one study

Full record for one study by Atlas ID (e.g. "SAB1994"), PMID, DOI or PMCID: abstract excerpt, extracted findings, linked entities, the relations it supports or contradicts, related open questions.

Input parameters:

- `id` (string): Alias of sid.
- `sid` (string): Atlas study ID ("SAB1994"), PMID ("23716719"), DOI or PMCID
- `study_id` (string): Alias of sid.

### `search_entities` (~164 tokens)

Search entities

Find genes/proteins, complexes, drugs, diseases, processes, nutrients and outcomes by name or synonym. Each result says where it matched (match_field: name, synonym or description); use match="name" to leave out description-only hits.

Input parameters:

- `limit` (integer): Maximum 100; a larger value is capped at 100.
- `match` (string): "any" also searches descriptions; "name" searches names and synonyms only.
- `offset` (integer): For the next page: pass next_offset from the previous answer.
- `query` (string, required): Name or synonym, e.g. "raptor", "sirolimus"
- `type` (string): Optional type filter, e.g. "Drug", "Gene/Protein", "Disease"

### `get_entity` (~114 tokens)

Get one entity

One entity (gene/protein, complex, drug, disease, process...) with its linked studies as short cards (first studies_limit) and every pathway relation it takes part in as a one-line claim. Accepts an id, a name or a synonym.

Input parameters:

- `entity` (string): e.g. "mTORC1", "Rheb", "rapamycin"
- `id` (string): Alias of entity.
- `studies_limit` (integer): Maximum 50; a larger value is capped at 50.

### `find_relations` (~174 tokens)

Find pathway relations

Signed, evidence-linked pathway relations (claims such as "Rheb activates mTORC1"). Filter by an entity on either end, by source/target, effect, contested status or minimum strength of the best supporting evidence.

Input parameters:

- `contested_only` (boolean): Only relations marked contested or with conflicting studies
- `effect` (string)
- `entity` (string): Entity on either end of the relation
- `limit` (integer): Maximum 50; a larger value is capped at 50.
- `offset` (integer): For the next page: pass next_offset from the previous answer.
- `source` (string)
- `strongest_at_least` (string): Keep relations whose best supporting study is at least this code in the order S > H > A > M
- `target` (string)

### `get_relation` (~45 tokens)

Get one relation

One pathway relation by ID (e.g. "RHEB-MTORC1"): mechanism, boundary conditions, confidence, supporting and conflicting studies.

Input parameters:

- `id` (string, required)

### `evidence_between` (~105 tokens)

Evidence between two entities

Direct curated relations between two entities (either direction) with full cards for the supporting and conflicting studies. Answers questions such as "what is the evidence that A acts on B?". A study that repeats within the answer is sent in full once and afterwards as a short card with full_card_in.

Input parameters:

- `a` (string, required)
- `b` (string, required)
- `dedupe` (boolean): Send a repeated study in full only once. Pass false for a full card every time.

### `find_contradictions` (~214 tokens)

Find contested claims

Relations the Atlas marks as contested or that carry conflicting studies, with both sides of the evidence. status says which; breakdown splits the total. A contested relation with no conflicting study listed is flagged conflicting_studies_missing; relations named in its note or boundary are shown in named_in_text (a mention is not evidence). Paged: pass next_offset as offset for the rest. Optionally limited to one entity.

Input parameters:

- `brief` (boolean): Shorten the long boundary and note text (text_truncated is set); get_relation has the full text.
- `dedupe` (boolean): Send a repeated study in full only once. Pass false for a full card every time.
- `entity` (string)
- `limit` (integer): Maximum 50; a larger value is capped at 50.
- `offset` (integer): For the next page: pass next_offset from the previous answer.
- `only_contested` (boolean): Keep only relations the Atlas flags contested, not those that merely carry conflicting studies.

### `list_questions` (~151 tokens)

List open questions

The Atlas's open questions (evidence gaps with testable hypotheses) and frontier questions. Paged. By default still_open is shortened at a sentence boundary (still_open_truncated); get_question has the full text, or pass brief=false.

Input parameters:

- `brief` (boolean): Shorten still_open; false returns the full text.
- `kind` (string)
- `limit` (integer): Maximum 50; a larger value is capped at 50.
- `offset` (integer): For the next page: pass next_offset from the previous answer.
- `query` (string): Keywords to find questions by their title, gap, hypothesis or what is still open, e.g. "rapamycin immune".

### `get_question` (~54 tokens)

Get one question

One open or frontier question by ID (e.g. "H1", "F2"): the gap, what changed, what is still open, how it could be tested, linked studies.

Input parameters:

- `id` (string, required)

### `search_authors` (~143 tokens)

Search authors

People in the Atlas by full name ("Claudio De Virgilio"), author-list form ("De Virgilio C"), ORCID or lab. results are authors with a profile page (full name, ORCID, lab, their study IDs); in_author_lists are matching names in study author lists without a profile.

Input parameters:

- `limit` (integer): Maximum 50; a larger value is capped at 50.
- `offset` (integer): For the next page: pass next_offset from the previous answer.
- `query` (string, required): A name, ORCID or lab, e.g. "Sabatini", "Claudio De Virgilio", "Fribourg"

### `get_author` (~91 tokens)

Get one author

One profiled author by profile id ("claudio-de-virgilio"), full name, author-list form or ORCID: lab, role, profile URL and short cards of their studies in the Atlas.

Input parameters:

- `author` (string): e.g. "Claudio De Virgilio", "De Virgilio C", "claudio-de-virgilio"
- `id` (string): Alias of author.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/open-mtor-atlas-mtor-atlas/mtor-atlas-mcp#diagnostics

## Score history

- 2026-10-25: 79
- 2026-10-24: 78
- 2026-10-23: 78
- 2026-10-22: 77
- 2026-10-21: 77
- 2026-10-20: 76
- 2026-10-19: 76
- 2026-10-18: 75
- 2026-10-17: 75
- 2026-10-16: 75
- 2026-10-15: 74
- 2026-10-14: 74
- 2026-10-13: 38
- 2026-10-12: 73
- 2026-10-11: 73
- 2026-10-07: 71
- 2026-10-04: 70
- 2026-10-03: 54
- 2026-10-02: 68
- 2026-10-01: 53

## Common questions

### What is the Oliver's mTOR Atlas MCP server?

Oliver's mTOR Atlas is an MCP server listed in the public MCP registry as io.github.open-mtor-atlas/mtor-atlas. Evidence-labelled mTOR research: studies, entities, pathway claims, contradictions, open questions. This page covers its npm package (mtor-atlas-mcp).

### Is the Oliver's mTOR Atlas MCP server safe to use?

Oliver's mTOR Atlas scores 79 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 25 October 2026. It declares no install or post-install scripts. 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 Oliver's mTOR Atlas MCP server expose?

Oliver's mTOR Atlas exposes 13 tools: atlas_about, search_studies, get_study, search_entities, get_entity, and 8 more. Their descriptions and schemas cost roughly 1,667 tokens of context every time the server is loaded.

### Is the Oliver's mTOR Atlas MCP server still maintained?

Oliver's mTOR Atlas is still listed as active in the MCP registry. We last reached this channel on 25 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Oliver's mTOR Atlas MCP server under?

Oliver's mTOR Atlas declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/mtor-atlas-mcp
- Socket report: https://socket.dev/npm/package/mtor-atlas-mcp
- Repository: https://github.com/open-mtor-atlas/atlas
- Website: https://mtor-atlas.org/api/
- Changelog RSS feed: https://verifymcp.io/servers/open-mtor-atlas-mtor-atlas/mtor-atlas-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/open-mtor-atlas-mtor-atlas/mtor-atlas-mcp.json
- HTML version of this page: https://verifymcp.io/servers/open-mtor-atlas-mtor-atlas/mtor-atlas-mcp