Skip to main content

MCP server for the 1up knowledge management platform — connect AI assistants to your 1up workspace

Project description

1up MCP Server

MCP (Model Context Protocol) server for the 1up knowledge management platform. Enables AI coding assistants to interact with your 1up workspace — manage questionnaires, Q&A libraries, knowledge bases, and more — directly from the terminal.

Installation

# With pip
pip install 1up-mcp

# With pipx (isolated install, recommended for CLI tools)
pipx install 1up-mcp

# With uvx (zero-install, runs directly)
uvx 1up-mcp auth login

Requires Python 3.10+

Authentication

1up-mcp auth login       # Opens browser for SSO login
1up-mcp auth status      # Show current auth status
1up-mcp auth logout      # Remove cached credentials

Credentials are cached locally in ~/.1up/credentials.json and automatically refreshed.

Configuration

Claude Code

Add to your .claude.json or ~/.claude.json:

{
  "mcpServers": {
    "1up": {
      "command": "1up-mcp"
    }
  }
}

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "1up": {
      "command": "uvx",
      "args": ["1up-mcp"]
    }
  }
}

Cursor / Windsurf

Add to your MCP configuration:

{
  "mcpServers": {
    "1up": {
      "command": "1up-mcp"
    }
  }
}

Environment Variables

These are optional — credentials from 1up-mcp auth login are used by default.

Variable Description
ONEUP_AUTH_TOKEN Bearer token (overrides cached credentials)
ONEUP_API_URL API base URL
ONEUP_WORKSPACE_ID Workspace ID to use

Available Tools

Q&A Library (6 tools)
Tool Description
ask_question Query the knowledge base with optional filters
search_qa_library Search Q&A pairs with pagination
get_qa_pair Get a specific Q&A pair by ID
create_qa_pair Create a new Q&A pair
update_qa_pair Update an existing Q&A pair
delete_qa_pair Archive a Q&A pair
Questionnaires (11 tools)
Tool Description
upload_questionnaire Upload XLSX/DOCX/PDF/CSV questionnaire files
list_questionnaires List questionnaires with status/search filters
get_questionnaire Get full questionnaire details
get_questionnaire_questions Get questions with answers
update_questionnaire_answer Edit a specific answer
approve_question Mark an answer as approved
bulk_approve_questions Approve multiple questions at once
regenerate_answer Regenerate AI answer for a question
assign_question Assign a question to a team member
add_question_comment Add a comment to a question
request_questionnaire_export Export as XLSX/DOCX/CSV
Knowledge Base (4 tools)
Tool Description
list_kb_items List items with search/source filters
get_kb_item Get KB item details
upload_kb_document Upload PDF/DOCX/XLSX/CSV documents
delete_kb_item Delete a KB item
Knowledge Groups (5 tools)
Tool Description
list_knowledge_groups List all groups
get_knowledge_group Get group with its documents and Q&A pairs
create_knowledge_group Create a new group
add_items_to_knowledge_group Add documents/Q&A pairs to a group
remove_items_from_knowledge_group Remove items from a group
delete_knowledge_group Delete a group (items are ungrouped, not deleted)
Workspace (4 tools)
Tool Description
list_workspaces List accessible workspaces
get_workspace_info Get workspace details, plan, limits, usage
switch_workspace Switch active workspace
get_audit_events Get audit events with pagination

Available Resources

16 read-only resources for workspace context, questionnaire data, Q&A library, knowledge base items (with source text tracing), and knowledge groups.

Development

# Clone and install in dev mode
git clone https://gitlab.com/1upai/mcp_server.git
cd mcp_server
python3.10 -m venv .venv
source .venv/bin/activate
pip install -e .

# Run directly
python -m oneup_mcp

License

Proprietary. Copyright (c) 2025-2026 1up.ai. All rights reserved. See LICENSE for details.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

1up_mcp-0.1.0.tar.gz (42.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

1up_mcp-0.1.0-py3-none-any.whl (21.8 kB view details)

Uploaded Python 3

File details

Details for the file 1up_mcp-0.1.0.tar.gz.

File metadata

  • Download URL: 1up_mcp-0.1.0.tar.gz
  • Upload date:
  • Size: 42.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.14

File hashes

Hashes for 1up_mcp-0.1.0.tar.gz
Algorithm Hash digest
SHA256 659a69612bec82a58f16e8cead4440591b46628c45e1704f4a50d26cb9c3a125
MD5 5f5e5c51cced693793ae0ada39073420
BLAKE2b-256 c94094f20cff92a2a6ce79d8ca5ca6d115db4517468f0984d6b131a076ef3607

See more details on using hashes here.

File details

Details for the file 1up_mcp-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: 1up_mcp-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 21.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.14

File hashes

Hashes for 1up_mcp-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 a3cb379b06e9b4215a4daab301902f4d0fe9a494fc80777b5bf9a9dfacd5720c
MD5 43ab568f97faecf7ab3e9f3ff6e3ebb4
BLAKE2b-256 8c9fc08d5988ac150e25f3ec298b8be0ed60f71be4ef14453fdfea94099e9967

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page