Skip to main content
Glama
Sign In
mcp-upstage

mcp-upstage

Official
by UpstageAI
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Related Servers

Alternatives to mcp-upstage

No user-submitted related servers found.

    Related Servers

    • Claude RAG MCP Pipeline

      kenjisekino
      A
      license
      Not graded
      quality
      D
      maintenance
      Enables Claude Desktop to search and query personal document collections (PDF, Word, Markdown, text) using semantic search and conversational AI with full context preservation across exchanges.
      MIT
    • MCP-Upstage-Server

      MCP-Upstage-Serverofficial

      UpstageAI
      A
      license
      A
      quality
      D
      maintenance
      Enables document processing through Upstage AI services including parsing various document formats, extracting structured information with custom schemas, auto-generating extraction schemas, and classifying documents into categories.
      4
      96 npm
      3
      MIT

    • Enterprise Knowledge MCP

      j84077200345-dotcom
      A
      license
      Not graded
      quality
      D
      maintenance
      Enables querying enterprise documents (DOCX, PDF, PPTX) using natural language, with hybrid search and MCP integration for Claude Desktop and other agents.
      MIT

    • CoreRag

      TJ-Neary
      A
      license
      Not graded
      quality
      D
      maintenance
      Enables Claude Desktop to perform local-first semantic search, ingest documents, and manage a private knowledge base with hybrid search, PII redaction, and multi-format support.
      1
      MIT
    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