# OmniScholar (pypi · luffysolution-omnischolar)

Literature, Zotero, PDF, citation, materials, and scientific image tools for research agents.

- Trust score: 68/100 (medium)
- Change this week: +5
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- pypi · `luffysolution-omnischolar`: 68/100 (this document), [markdown](https://verifymcp.io/servers/luffysolution-svg-omnischolar/luffysolution-omnischolar.md), [page](https://verifymcp.io/servers/luffysolution-svg-omnischolar/luffysolution-omnischolar)

## Channel facts

- Registry: `pypi`
- Package: `luffysolution-omnischolar`
- Version: `0.1.0`
- 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 2026-09-20.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it.
  - 1 of 33 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 35/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: the license (MIT License) isn't a recognized OSI-approved license.
  - Actively maintained (last published 2 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 57/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 2596 tokens (~68/item across 38 items; 38 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 38 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 39 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 OmniScholar MCP server?

OmniScholar runs locally as a PyPI package, launched with uvx luffysolution-omnischolar. 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 luffysolution-svg-omnischolar -- uvx luffysolution-omnischolar
```

### Cursor

```json
{
  "mcpServers": {
    "luffysolution-svg-omnischolar": {
      "command": "uvx",
      "args": [
        "luffysolution-omnischolar"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "luffysolution-svg-omnischolar": {
      "command": "uvx",
      "args": [
        "luffysolution-omnischolar"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add luffysolution-svg-omnischolar -- uvx luffysolution-omnischolar
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "luffysolution-svg-omnischolar": {
      "type": "local",
      "command": [
        "uvx",
        "luffysolution-omnischolar"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add luffysolution-svg-omnischolar --command uvx --arg luffysolution-omnischolar
```

### Hermes

```yaml
mcp_servers:
  luffysolution-svg-omnischolar:
    command: "uvx"
    args: ["luffysolution-omnischolar"]
```

### Netclaw

```json
{
  "McpServers": {
    "luffysolution-svg-omnischolar": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "luffysolution-omnischolar"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add luffysolution-svg-omnischolar -t stdio -c uvx -a luffysolution-omnischolar
```

### Other

```json
{
  "mcpServers": {
    "luffysolution-svg-omnischolar": {
      "command": "uvx",
      "args": [
        "luffysolution-omnischolar"
      ]
    }
  }
}
```

## 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.

### 2026-09-20 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-18 (score 67, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-09-15 (score 63, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-09-14 (score 48, −15)

- [security regression] Malware scan: pass → unverified

### 2026-09-12 (score 63, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-09-10 (score 48)

First indexed and scored.

## MCP tools (38)

### `ai4scholar_author` (~117 tokens)

Search and inspect Semantic Scholar or Google Scholar authors through Ai4Scholar.

Input parameters:

- `action` (string, required)
- `afterAuthor` (string)
- `allowExternalUpload` (boolean)
- `allowPaid` (boolean, required)
- `authorId` (string)
- `fields` (string)
- `limit` (integer)
- `offset` (integer)
- `publicationDateOrYear` (string)
- `query` (string)
- `sort` (string)
- `source` (string, required)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `ai4scholar_batch` (~63 tokens)

Fetch bounded Semantic Scholar/PubMed batch records through Ai4Scholar.

Input parameters:

- `allowExternalUpload` (boolean)
- `allowPaid` (boolean, required)
- `fields` (string)
- `ids` (array, required)
- `source` (string, required)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `ai4scholar_citation_candidates` (~98 tokens)

Find review-required citation candidates for claims; never inserts citations automatically.

Input parameters:

- `allowExternalUpload` (boolean)
- `allowPaid` (boolean, required)
- `candidatesPerClaim` (integer)
- `citationStyle` (string)
- `fieldsOfStudy` (string)
- `maxClaims` (integer)
- `mode` (string)
- `text` (string, required)
- `year` (string)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `ai4scholar_cite` (~57 tokens)

Retrieve citation formats for a Google Scholar result through Ai4Scholar.

Input parameters:

- `allowExternalUpload` (boolean)
- `allowPaid` (boolean, required)
- `language` (string)
- `paperId` (string, required)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `ai4scholar_credits` (~24 tokens)

Check Ai4Scholar credit balance using its documented free endpoint.

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `ai4scholar_dataset` (~83 tokens)

Inspect Semantic Scholar dataset releases/downloads/diffs through Ai4Scholar.

Input parameters:

- `action` (string, required)
- `allowExternalUpload` (boolean)
- `allowPaid` (boolean, required)
- `datasetName` (string)
- `endReleaseId` (string)
- `releaseId` (string)
- `startReleaseId` (string)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `ai4scholar_figure` (~112 tokens)

Generate or revise scientific figure drafts through Ai4Scholar Nano with integrity warning.

Input parameters:

- `action` (string, required)
- `allowExternalUpload` (boolean)
- `allowPaid` (boolean, required)
- `aspectRatio` (string)
- `imageSize` (string)
- `images` (array)
- `lang` (string)
- `model` (string)
- `prompt` (string)
- `stylePreset` (string)
- `vectorizeMode` (string)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `ai4scholar_journal` (~189 tokens)

Search JCR/CAS metrics or recommend journals through Ai4Scholar.

Input parameters:

- `abstract` (string)
- `action` (string, required)
- `allowExternalUpload` (boolean)
- `allowPaid` (boolean, required)
- `casQuartile` (string)
- `categories` (array)
- `category` (string)
- `fieldGroup` (string)
- `fields` (array)
- `filters` (object)
- `id` (string)
- `isOpenAccess` (boolean)
- `jcrQuartile` (string)
- `limit` (integer)
- `maxImpactFactor` (number)
- `minImpactFactor` (number)
- `offset` (integer)
- `query` (string)
- `sort` (string)
- `title` (string)
- `topN` (integer)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `ai4scholar_paper` (~106 tokens)

Read Ai4Scholar paper detail, graph, authors, related records, or recommendations.

Input parameters:

- `action` (string, required)
- `allowExternalUpload` (boolean)
- `allowPaid` (boolean, required)
- `fields` (string)
- `id` (string, required)
- `limit` (integer)
- `offset` (integer)
- `publicationDateOrYear` (string)
- `recommendationPool` (string)
- `source` (string, required)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `ai4scholar_recommend` (~74 tokens)

Recommend papers from positive and negative seed IDs through Ai4Scholar.

Input parameters:

- `allowExternalUpload` (boolean)
- `allowPaid` (boolean, required)
- `fields` (string)
- `limit` (integer)
- `negativePaperIds` (array)
- `positivePaperIds` (array, required)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `ai4scholar_search` (~287 tokens)

Search Semantic Scholar, PubMed, Google Scholar, or Google Patents through explicitly selected paid Ai4Scholar.

Input parameters:

- `after` (string)
- `allowExternalUpload` (boolean)
- `allowPaid` (boolean, required)
- `assignee` (string)
- `before` (string)
- `cites` (string)
- `cluster` (string)
- `country` (string)
- `fields` (string)
- `fieldsOfStudy` (string)
- `inventor` (string)
- `language` (string)
- `limit` (integer)
- `maxDate` (string)
- `minCitationCount` (integer)
- `minDate` (string)
- `offset` (integer)
- `openAccessOnly` (boolean)
- `page` (integer)
- `patentType` (string)
- `publicationDateOrYear` (string)
- `publicationTypes` (string)
- `query` (string, required)
- `reviewOnly` (boolean)
- `semanticMode` (string)
- `sort` (string)
- `sortByDate` (boolean)
- `source` (string, required)
- `status` (string)
- `token` (string)
- `venue` (string)
- `yearFrom` (integer)
- `yearTo` (integer)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `ai4scholar_snippets` (~118 tokens)

Search Semantic Scholar full-text snippets through Ai4Scholar.

Input parameters:

- `allowExternalUpload` (boolean)
- `allowPaid` (boolean, required)
- `authors` (string)
- `fields` (string)
- `fieldsOfStudy` (string)
- `limit` (integer)
- `minCitationCount` (integer)
- `paperIds` (string)
- `publicationDateOrYear` (string)
- `query` (string, required)
- `venue` (string)
- `year` (string)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `chemical_get` (~27 tokens)

Fetch a CAS substance only under an explicit provider-issued contract.

Input parameters:

- `id` (string, required)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `chemical_search` (~37 tokens)

Search CAS only when a provider-issued contract is configured; otherwise fail closed.

Input parameters:

- `limit` (integer)
- `query` (string, required)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `chemical_sources` (~21 tokens)

Report CAS Common Chemistry contract/credential/license status without guessing endpoints.

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `journal_metrics` (~34 tokens)

Retrieve journal metrics only from a provider with a verified contract.

Input parameters:

- `provider` (string, required)
- `query` (string, required)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `literature_fulltext` (~44 tokens)

Resolve or fetch legally available full text without bypassing provider entitlements.

Input parameters:

- `fetch` (boolean)
- `id` (string, required)
- `provider` (string, required)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `literature_get` (~33 tokens)

Fetch one normalized literature record from an explicitly selected provider.

Input parameters:

- `id` (string, required)
- `provider` (string, required)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `literature_graph` (~56 tokens)

Fetch bounded references, citations, or recommendations from a selected provider.

Input parameters:

- `cursor` (string)
- `id` (string, required)
- `kind` (string, required)
- `limit` (integer)
- `provider` (string, required)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `literature_search` (~103 tokens)

Search selected official literature APIs with bounded pagination and ordered retryable fallback.

Input parameters:

- `cursor` (string)
- `fallback` (boolean)
- `fields` (array)
- `limit` (integer)
- `openAccessOnly` (boolean)
- `page` (integer)
- `provider` (string)
- `providers` (array)
- `query` (string, required)
- `yearFrom` (integer)
- `yearTo` (integer)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `materials_advanced` (~52 tokens)

Retrieve consistently-defined phase data or invoke explicit optional local calculations.

Input parameters:

- `action` (string, required)
- `chemsys` (string)
- `limit` (integer)
- `materialId` (string)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `materials_capabilities` (~21 tokens)

Report implemented Materials Project routes, fields and local derived limitations.

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `materials_export` (~40 tokens)

Write Materials records atomically beneath the configured output root.

Input parameters:

- `format` (string, required)
- `path` (string, required)
- `records` (array, required)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `materials_get` (~39 tokens)

Fetch one material record by Materials Project ID.

Input parameters:

- `fields` (array)
- `materialId` (string, required)
- `route` (string)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `materials_route_search` (~52 tokens)

Search one verified Materials Project REST route.

Input parameters:

- `fields` (array)
- `filters` (object)
- `limit` (integer)
- `page` (integer)
- `route` (string, required)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `materials_search` (~49 tokens)

Search Materials Project summary records with bounded filters and explicit field status.

Input parameters:

- `fields` (array)
- `filters` (object)
- `limit` (integer)
- `page` (integer)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `omnischolar_capabilities` (~26 tokens)

List available tools with their capabilities, effects, credentials, and cost classes.

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `omnischolar_image_edit` (~73 tokens)

Edit scientific image references using an explicitly capable model.

Input parameters:

- `allowExternalUpload` (boolean, required)
- `allowPaid` (boolean, required)
- `model` (string)
- `options` (object)
- `prompt` (string, required)
- `provider` (string)
- `references` (array, required)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `omnischolar_image_generate` (~77 tokens)

Generate a scientific image draft using capability routing and explicit paid/upload authorization.

Input parameters:

- `allowExternalUpload` (boolean)
- `allowPaid` (boolean, required)
- `model` (string)
- `options` (object)
- `prompt` (string, required)
- `provider` (string)
- `references` (array)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `omnischolar_image_models` (~40 tokens)

Discover image models and return only catalog/pin/curated capability declarations.

Input parameters:

- `discover` (boolean)
- `provider` (string)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `omnischolar_image_service` (~43 tokens)

Inspect provider status or a configured asynchronous image job.

Input parameters:

- `action` (string, required)
- `jobId` (string)
- `provider` (string, required)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `omnischolar_parse` (~91 tokens)

Parse a Zotero PDF through MinerU v4 with deterministic cache and transactional local publication.

Input parameters:

- `allowExternalUpload` (boolean, required)
- `attachmentKey` (string)
- `enableFormula` (boolean)
- `enableTable` (boolean)
- `force` (boolean)
- `isOcr` (boolean)
- `key` (string, required)
- `language` (string)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `omnischolar_status` (~33 tokens)

Report configuration source, enabled groups, provider and credential presence, local services, defaults, and runtime without revealing secrets.

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `omnischolar_sync` (~76 tokens)

Plan and control conservative incremental sync, conflict, recovery, exclude, restore, repair and reparse actions.

Input parameters:

- `action` (string, required)
- `allowExternalUpload` (boolean)
- `attachmentKey` (string)
- `force` (boolean)
- `key` (string)
- `reason` (string)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `research_sources` (~21 tokens)

List first-party literature providers and verified capability status without network access.

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `zotero_collections` (~47 tokens)

List/read local Zotero collections and collection items through GET-only loopback API.

Input parameters:

- `action` (string)
- `key` (string)
- `limit` (integer)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `zotero_item` (~52 tokens)

Read one Zotero item or aggregate paper with notes, annotations, attachments, indexed text and PDF location.

Input parameters:

- `attachmentKey` (string)
- `key` (string, required)
- `mode` (string)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

### `zotero_search` (~68 tokens)

Search or browse top-level Zotero items through the read-only Local API.

Input parameters:

- `collectionKey` (string)
- `direction` (string)
- `itemType` (string)
- `limit` (integer)
- `query` (string)
- `sort` (string)

Output parameters:

- `data`
- `error`
- `ok` (boolean)
- `output`

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/luffysolution-svg-omnischolar/luffysolution-omnischolar#diagnostics

## Score history

- 2026-09-20: 68
- 2026-09-19: 67
- 2026-09-18: 67
- 2026-09-17: 63
- 2026-09-16: 63
- 2026-09-15: 63
- 2026-09-14: 48
- 2026-09-13: 63
- 2026-09-12: 63
- 2026-09-11: 48
- 2026-09-10: 48

## Common questions

### What is the OmniScholar MCP server?

OmniScholar is an MCP server listed in the public MCP registry as io.github.luffysolution-svg/omnischolar. Literature, Zotero, PDF, citation, materials, and scientific image tools for research agents. This page covers its PyPI package (luffysolution-omnischolar).

### Is the OmniScholar MCP server safe to use?

OmniScholar scores 68 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. 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 OmniScholar MCP server expose?

OmniScholar exposes 38 tools: ai4scholar_author, ai4scholar_batch, ai4scholar_citation_candidates, ai4scholar_cite, ai4scholar_credits, and 33 more. Their descriptions and schemas cost roughly 2,583 tokens of context every time the server is loaded.

### Is the OmniScholar MCP server still maintained?

OmniScholar is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- PyPI project: https://pypi.org/project/luffysolution-omnischolar/
- Socket report: https://socket.dev/pypi/package/luffysolution-omnischolar
- Repository: https://github.com/luffysolution-svg/omnischolar
- Changelog RSS feed: https://verifymcp.io/servers/luffysolution-svg-omnischolar/luffysolution-omnischolar.xml
- Changelog JSON feed: https://verifymcp.io/servers/luffysolution-svg-omnischolar/luffysolution-omnischolar.json
- HTML version of this page: https://verifymcp.io/servers/luffysolution-svg-omnischolar/luffysolution-omnischolar