Advertise
MCP.so
Sign In

Unstructured API MCP Server for Research Paper Data Processing

@HeetVekariya

Repository

Basic information

Category

Data & Analytics

Transports

stdio

Author

HeetVekariya

About Unstructured API MCP Server for Research Paper Data Processing

GitHub repository for Unstructured MCP Hackathon.

#mcp#unstructured#mcp-server

Unstructured API MCP Server for Research Paper Data Processing config

No standard config provided

This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.

Repository

Unstructured API MCP Server for Research Paper Data Processing tools

18

Lists available sources from the Unstructured API.

Get detailed information about a specific source connector.

Update an existing google source connector by params.

Delete a source connector by source id.

Lists available destinations from the Unstructured API.

Get detailed info about a specific destination connector. Currently, we have s3/weaviate/astra/neo4j/mongo DB (more to come!)

Create a mongodb destination connector by params.

Update an existing mongodb destination connector by destination id.

Delete a mongodb destination connector by destination id.

Lists workflows from the Unstructured API.

Get detailed information about a specific workflow.

Create a new workflow with source, destination id, etc.

Run a specific workflow with workflow id

Update an existing workflow by params.

Delete a specific workflow by id.

Lists jobs for a specific workflow from the Unstructured API.

Get detailed information about a specific job by job id.

Delete a specific job by id.

Overview

What is Unstructured API MCP Server for Research Paper Data Processing?

The Unstructured API MCP Server for Research Paper Data Processing is an MCP server that uses the Unstructured API to extract meaningful information from research paper PDFs. It converts unstructured documents into structured JSON data, which can then be used to fine‑tune language models and reduce literature review time for researchers.

How to use Unstructured API MCP Server for Research Paper Data Processing?

Install dependencies (uv add "mcp[cli]", uv pip install --upgrade unstructured-client python-dotenv) and set up environment variables (UNSTRUCTURED_API_KEY, GOOGLEDRIVE_SERVICE_ACCOUNT_KEY, MONGO_DB_CONNECTION_STRING). The server provides 18 tools for managing sources, destinations, workflows, and jobs. Integrate with Claude Desktop by adding the server configuration to claude_desktop_config.json. For local development, run the server over SSE and a minimal client.

Key features of Unstructured API MCP Server for Research Paper Data Processing

  • Connects to Google Drive to fetch research paper PDFs.
  • Sends structured data to a MongoDB destination connector.
  • Offers 18 tools for source, destination, workflow, and job management.
  • Supports auto partitioning, chunking, NER enrichment, and embedding.
  • Integrates directly with Claude Desktop via MCP configuration.

Use cases of Unstructured API MCP Server for Research Paper Data Processing

  • Researchers automatically extracting key information from many PDFs.
  • Building a pipeline to feed structured research data into a fine‑tuning workflow.
  • Creating, running, and monitoring document processing workflows end‑to‑end.
  • Reducing manual literature review time by converting papers into analyzable JSON.

Frequently asked questions

1

What environment variables are required?

`UNSTRUCTURED_API_KEY`, `GOOGLEDRIVE_SERVICE_ACCOUNT_KEY`, and `MONGO_DB_CONNECTION_STRING`. A `.env.template` file is provided.

2

How do I integrate this server with Claude Desktop?

Add the server configuration to `claude_desktop_config.json` under `mcpServers.UNS_MCP`, specifying the `uv` command and environment variables. Restart Claude Desktop afterward.

3

How can I test the server during development?

Use Anthropic’s MCP Inspector by running `mcp dev uns_mcp/server.py`. You can set environment variables and test all tools interactively.

4

Can I run the server locally without Claude Desktop?

Yes. Run the server with `uv run python uns_mcp/server.py --host 127.0.0.1 --port 8080` and connect a minimal client via SSE at `http://127.0.0.1:8080/sse`.

Comments

More Data & Analytics MCP servers

Manifold MCP

Jesse Sibley

An MCP for marketers that gives agents tools for SEO, AEO, socials and ads data. Generous free tier; works in Claude, ChatGPT, Cursor and other MCP clients.

442ball

442ball

Football club Power Ratings for AI assistants: weekly 442ball ratings, league strength, the 442 League Index, unbeaten and winning runs, and the greatest sides in a league's history. Every answer links to its 442ball.com

B

BidSkim - UK Tenders & Contract Renewals

BidSkim

UK procurement intelligence for AI assistants: search live UK government tenders, find contract renewals with expiry dates and incumbent suppliers, and profile public-sector buyers and suppliers. Covers Find a Tender, Co

Kyrodata — Brazil Trade, Crop & Commodity Data

Kyrodata

Brazilian foreign-trade data from MDIC/ComexStat (exports and imports, 2000 to 2026, by HS code, NCM, partner country and bloc) plus crop production, supply-and-demand balances, growing-season climate and commodity forec

Sugra API MCP

Sugra Systems, Inc.

Official MCP server for the Sugra API, giving AI agents source-attributed access to 1,500+ endpoints across 36 data domains from 160+ primary sources. Covers markets, economics, company fundamentals, government, news, cl

1
Advertise