# Scholar RAG MCP (pypi · scholar-rag-mcp)

Academic paper knowledge-base MCP server: PDF ingest, vector search with reranking, KB management.

- Trust score: 57/100 (low)
- Change this week: −12
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- pypi · `scholar-rag-mcp`: 57/100 (this document), [markdown](https://verifymcp.io/servers/notwhiteblank-scholar-rag-mcp/scholar-rag-mcp.md), [page](https://verifymcp.io/servers/notwhiteblank-scholar-rag-mcp/scholar-rag-mcp)

## Channel facts

- Registry: `pypi`
- Package: `scholar-rag-mcp`
- Version: `0.4.0`
- 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**: 50/100
  - Malware scan not yet available for this package.
  - 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.
  - 4 of 48 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 32/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: no license is declared.
  - Actively maintained (last published 16 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 59/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 513 tokens (~46/item across 11 items; 11 tools + 0 resources), lean.
  - 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**: 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**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "remove_document" implies "remove" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 11 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).

## Install

### How do I install the Scholar RAG MCP server?

Scholar RAG MCP runs locally as a PyPI package, launched with uvx scholar-rag-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 notwhiteblank-scholar-rag-mcp -- uvx scholar-rag-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "notwhiteblank-scholar-rag-mcp": {
      "command": "uvx",
      "args": [
        "scholar-rag-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "notwhiteblank-scholar-rag-mcp": {
      "command": "uvx",
      "args": [
        "scholar-rag-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add notwhiteblank-scholar-rag-mcp -- uvx scholar-rag-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add notwhiteblank-scholar-rag-mcp --command uvx --arg scholar-rag-mcp
```

### Hermes

```yaml
mcp_servers:
  notwhiteblank-scholar-rag-mcp:
    command: "uvx"
    args: ["scholar-rag-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "notwhiteblank-scholar-rag-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "scholar-rag-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add notwhiteblank-scholar-rag-mcp -t stdio -c uvx -a scholar-rag-mcp
```

### Other

```json
{
  "mcpServers": {
    "notwhiteblank-scholar-rag-mcp": {
      "command": "uvx",
      "args": [
        "scholar-rag-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.

### 2026-09-20 (score 57, −15)

- [security regression] Malware scan: pass → unverified

### 2026-09-19 (score 72, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-09-17 (score 56, −15)

- [security regression] Malware scan: pass → unverified

### 2026-09-16 (score 71, +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.

### 2026-09-15 (score 70, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-09-14 (score 55, −14)

- [security regression] Malware scan: pass → unverified

### 2026-09-12 (score 69, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-09-11 (score 53, −15)

- [security regression] Malware scan: pass → unverified

## MCP tools (11)

### `search_chunks` (~60 tokens)

Semantic search over chunk bodies of a kb with metadata filters, embedding and rerank scores.

Input parameters:

- `kb` (string, required)
- `metadata_filter`
- `min_score`
- `query` (string, required)
- `top_k` (integer)

### `search_documents` (~77 tokens)

Document-level PubMed-style search with optional FTS query and metadata filters.

Input parameters:

- `authors`
- `journal`
- `kb` (string, required)
- `page` (integer)
- `page_size` (integer)
- `query`
- `title`
- `year_from`
- `year_to`

### `list_documents` (~46 tokens)

Paginated browse of documents in a kb.

Input parameters:

- `kb` (string, required)
- `page` (integer)
- `page_size` (integer)
- `sort` (string)

### `get_document` (~39 tokens)

Overview of a document: metadata, abstract, section outline and total character count.

Input parameters:

- `doc_id` (string, required)
- `kb` (string, required)

### `get_document_text` (~59 tokens)

Paginated reading of the full text or a single section of a document.

Input parameters:

- `doc_id` (string, required)
- `kb` (string, required)
- `page` (integer)
- `page_size` (integer)
- `section`

### `add_document` (~39 tokens)

Asynchronously ingest a single PDF into an existing kb; returns a job_id.

Input parameters:

- `kb` (string, required)
- `pdf_path` (string, required)

### `remove_document` (~37 tokens)

Synchronously delete a document from qdrant, catalog and disk.

Input parameters:

- `doc_id` (string, required)
- `kb` (string, required)

### `create_kb` (~74 tokens)

Asynchronously create a kb from all PDFs in a folder; returns a job_id.

Input parameters:

- `chunk_max` (integer)
- `chunk_min` (integer)
- `chunk_overlap` (integer)
- `folder_path` (string, required)
- `kb_name` (string, required)
- `skip_existing` (boolean)

### `delete_kb` (~36 tokens)

Two-phase kb deletion: preview and confirm token, else full deletion.

Input parameters:

- `confirm_token`
- `kb` (string, required)

### `list_kbs` (~18 tokens)

List all knowledge bases with metadata and status.

### `get_job` (~28 tokens)

Query the status, progress and result of a background job.

Input parameters:

- `job_id` (string, required)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/notwhiteblank-scholar-rag-mcp/scholar-rag-mcp#diagnostics

## Score history

- 2026-09-20: 57
- 2026-09-19: 72
- 2026-09-18: 56
- 2026-09-17: 56
- 2026-09-16: 71
- 2026-09-15: 70
- 2026-09-14: 55
- 2026-09-13: 69
- 2026-09-12: 69
- 2026-09-11: 53
- 2026-09-10: 68
- 2026-09-09: 67
- 2026-09-08: 67
- 2026-09-07: 66
- 2026-09-06: 66
- 2026-09-05: 65
- 2026-09-04: 50
- 2026-09-03: 64
- 2026-09-02: 64
- 2026-09-01: 64
- 2026-08-31: 63
- 2026-08-30: 61
- 2026-08-29: 61
- 2026-08-28: 61
- 2026-08-27: 46

## Common questions

### What is the Scholar RAG MCP server?

Scholar RAG MCP is listed in the public MCP registry as io.github.notwhiteblank/scholar-rag-mcp. Academic paper knowledge-base MCP server: PDF ingest, vector search with reranking, KB management. This page covers its PyPI package (scholar-rag-mcp).

### Is the Scholar RAG MCP server safe to use?

Scholar RAG MCP scores 57 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 Scholar RAG MCP server expose?

Scholar RAG MCP exposes 11 tools: search_chunks, search_documents, list_documents, get_document, get_document_text, and 6 more. Their descriptions and schemas cost roughly 513 tokens of context every time the server is loaded.

### Is the Scholar RAG MCP server still maintained?

Scholar RAG MCP 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/scholar-rag-mcp/
- Socket report: https://socket.dev/pypi/package/scholar-rag-mcp
- Repository: https://github.com/notwhiteblank/scholar-rag-mcp
- Changelog RSS feed: https://verifymcp.io/servers/notwhiteblank-scholar-rag-mcp/scholar-rag-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/notwhiteblank-scholar-rag-mcp/scholar-rag-mcp.json
- HTML version of this page: https://verifymcp.io/servers/notwhiteblank-scholar-rag-mcp/scholar-rag-mcp