MCP Tools Directory
← Browse integrations

Search and research

Scholar RAG MCP

Free account · sign-in required

Contact Scholar RAG MCP

Loading secure sign-in…

Tools for autonomous AI agents

About this integration

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

Transport
stdio
Authentication
none
Initial setup
none
Runtime
unattended
Evidence
documented
Version
0.4.0
Package
scholar-rag-mcp
Last compatibility test
Not independently tested

Connect your agent

scholar-rag-mcp

Publisher README and Python manifest reviewed offline. The package, model services, Qdrant, MinerU, downloads, and MCP tools were not executed or independently security-audited. First-use model and binary downloads and destructive knowledge-base operations require operator review.

Capabilities: Ingest academic PDFs into knowledge bases, Search documents and semantic chunks, Read document text by section and page, Add and remove papers, Monitor background ingestion jobs

Connected profiles

Additional details

Registry identifier

io.github.notwhiteblank/scholar-rag-mcp

Source ↗ · Checked 2026-09-17
Published version

0.4.0

Source ↗ · Checked 2026-09-17
Metadata license

CC0-1.0; package licenses are separate

Source ↗ · Checked 2026-09-17
Package ecosystem

pypi

Source ↗ · Checked 2026-09-17
Required configuration names

SCHOLAR_RAG_CHAT_BASE_URL, SCHOLAR_RAG_EMBED_BASE_URL, SCHOLAR_RAG_RERANK_BASE_URL

Source ↗ · Checked 2026-09-17
Source artifact

scholar-rag-mcp

Source ↗ · Checked 2026-09-19
Source manifest version

0.4.0

Source ↗ · Checked 2026-09-19
Unattended configuration

The MCP host launches uvx scholar-rag-mcp with fixed model-service endpoint and model-name environment variables; the process waits for its client on stdio and ingestion runs as queryable background jobs.

Source ↗ · Checked 2026-09-19
Authentication and prerequisites

The documented minimal local configuration uses loopback OpenAI-compatible model-service base URLs and model names and does not specify a credential or authorization step. External model services may impose requirements outside this reviewed configuration.

Source ↗ · Checked 2026-09-19
Connection configuration

The package exposes its MCP tools over stdio. Model inference uses separately configured OpenAI-compatible HTTP endpoints, and Qdrant is auto-launched or separately connected.

Source ↗ · Checked 2026-09-19
Review scope

Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.

Source ↗ · Checked 2026-09-19