Skip to main content
Glama
Sign In
mcp-upstage

mcp-upstage

Official
by UpstageAI
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
UPSTAGE_API_KEYYesYour Upstage API key

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
parse_documentA

Parse a document using Upstage AI's document digitization API.

This tool extracts the structure and content from various document types,
including PDFs, images, and Office files. It preserves the original formatting
and layout while converting the document into a structured format.

Use mode='enhanced' for documents with complex tables, charts, handwriting or
low-quality scans (higher cost, slower), or mode='auto' to let the API decide
per page. The response ends with the model and per-mode page usage reported
by the API, plus a WARNING line if the requested mode was not applied.

Supported file formats include: PDF, JPEG, PNG, TIFF, and other common document formats.
extract_informationC

Extract structured information from documents using Upstage Universal Information Extraction.

This tool can extract key information from any document type without pre-training.
You can either provide a schema defining what information to extract, or let the system
automatically generate an appropriate schema based on the document content.

Supported file formats: JPEG, PNG, BMP, PDF, TIFF, HEIC, DOCX, PPTX, XLSX
Max file size: 50MB
Max pages: 100

Args:
    file_path: Path to the document file to process
    schema_path: Optional path to a JSON file containing the extraction schema
    schema_json: Optional JSON string containing the extraction schema
    auto_generate_schema: Whether to automatically generate a schema if none is provided

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.4/5.0

Scored across 2 tools

Disambiguation4/5

parse_document and extract_information both consume documents, but they target different outputs: layout-preserving digitization versus schema-driven structured extraction. The descriptions make the boundary reasonably clear, though an agent may briefly hesitate because both operate on the same document inputs.

Naming Consistency5/5

Both tool names follow a clear snake_case verb_noun pattern: parse_document and extract_information. The verbs accurately signal the action and the nouns identify the object, with no mixed naming conventions.

Tool Count3/5

Only two tools are exposed, each quite broad. This is borderline thin for a document AI server; while the tools are substantial, the surface does not reach the typical 3-15 well-scoped range.

Completeness4/5

The core document workflows are covered: parsing/digitizing documents and extracting structured information with a provided or auto-generated schema. Minor gaps may remain around batch processing, page-range control, or explicit schema utilities, but agents can likely work around them.

Maintenance

ActivityNo data
ResponsivenessSyncing

Resources