Skip to main content

A Model Context Protocol (MCP) server for Backlog project management integration

Project description

Backlog MCP Server

Introduction

Backlog MCP Server is a remote server designed to integrate the Backlog project management tool with AI assistants via the Model Context Protocol (MCP).

The server uses API key authentication for secure and simple access, allowing AI assistants such as Claude AI and Geniai Assistant to access and manage tasks, projects, and issues in Backlog efficiently.

This server is truly stateless, meaning it does not store session state between requests, which enhances both security and scalability.


Architecture Highlights

  • Simple API key authentication with Backlog
  • MCP-compliant design based on [MCP Specification (2025-06-18)]
  • Stateless architecture for simplicity and scalability
  • Single workspace configuration for personal use
  • Supports stdio protocol for direct communication

MCP Tools

The server provides a set of MCP tools that allow AI assistants to interact with Backlog via API. Below is the list of supported tools:


get_issue_details

Get detailed information about a Backlog issue by its issue key.

Parameters:

  • issue_key (str): The issue key in Backlog.
  • issue_title (str, optional): The title of the Backlog issue, used for logging or reference purposes.
  • timezone (str, default "UTC"): Timezone for datetime formatting.

get_user_issue_list

Retrieve a filtered list of issues based on project, assignees, milestones, and other criteria.

Parameters:

  • project_ids (List[int], optional): List of project IDs.
  • assignee_ids (List[int], optional): List of assignee IDs (defaults to current user).
  • status_ids (List[int], optional): List of status IDs (defaults to non-closed).
  • milestone_ids (List[int], optional): List of milestone IDs.
  • parent_issue_ids (List[int], optional): List of parent issue IDs.
  • created_since (str, optional): Created since (YYYY-MM-DD).
  • created_until (str, optional): Created until (YYYY-MM-DD).
  • updated_since (str, optional): Updated since (YYYY-MM-DD).
  • updated_until (str, optional): Updated until (YYYY-MM-DD).
  • start_date_since (str, optional): Start Date since (YYYY-MM-DD).
  • start_date_until (str, optional): Start Date until (YYYY-MM-DD).
  • due_date_since (str, optional): Due Date since (YYYY-MM-DD).
  • due_date_until (str, optional): Due Date until (YYYY-MM-DD).

Running the Server Locally

1. Get your Backlog API key

  1. Log in to your Backlog workspace
  2. Go to Personal SettingsAPI
  3. Generate a new API key
  4. Copy the API key for use in configuration

2. Create and configure the .env file

Create a .env file in the root directory and add the following environment variables:

# Backlog API Settings
BACKLOG_API_KEY=your_backlog_api_key_here
BACKLOG_DOMAIN=your-space.backlog.com
USER_ID=your_user_id

Important:

  • Replace your_backlog_api_key_here with your actual Backlog API key
  • Replace your-space.backlog.com with your actual Backlog domain
  • Replace your_user_id with your actual Backlog user ID

3. Start the server

After configuring .env, run:

mise mcp

The server will run using stdio transport and communicate directly with MCP clients.


Benefits of API Key Authentication

  1. Simplified Setup: No OAuth flow required - just use your API key
  2. Better Performance: Direct API calls without token introspection overhead
  3. Easier Debugging: Clear error messages and straightforward authentication
  4. Reduced Dependencies: No JWT libraries or OAuth server needed
  5. Personal Use Optimized: Perfect for individual developers and personal projects

Migration from OAuth Version

If you're migrating from the OAuth version:

  1. Backup your current setup
  2. Get your Backlog API key (see step 1 above)
  3. Update your .env file with new format (see step 2 above)
  4. Remove OAuth-related files (if any)
  5. Test the connection with your Backlog workspace

The migration preserves all existing MCP tools and functionality while simplifying the authentication process.

Tag for deployment

  1. MCP Resource only: mcp.v2.0.0-dev

  2. Both of Resource + Auth: v2.0.0-dev

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

backlog_mcp-1.0.1.tar.gz (47.9 kB view details)

Uploaded Source

Built Distribution

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

backlog_mcp-1.0.1-py3-none-any.whl (12.1 kB view details)

Uploaded Python 3

File details

Details for the file backlog_mcp-1.0.1.tar.gz.

File metadata

  • Download URL: backlog_mcp-1.0.1.tar.gz
  • Upload date:
  • Size: 47.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.7.18

File hashes

Hashes for backlog_mcp-1.0.1.tar.gz
Algorithm Hash digest
SHA256 979a1bd8f708b63955586cecd4defdb729f26e2f75167d431ccd8eba25a4ccf1
MD5 375d496386d11507c85184dc680963dd
BLAKE2b-256 e52431ba1402a1051d039d2e03fa846f7cbb20a8f579782e80c0395c6054dd38

See more details on using hashes here.

File details

Details for the file backlog_mcp-1.0.1-py3-none-any.whl.

File metadata

File hashes

Hashes for backlog_mcp-1.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 0918ca2b90f309003f3fd46d6895af4f70fe991fd57f425864ff150a48dadd3b
MD5 243dab9643a2422668d80c19e755d7a8
BLAKE2b-256 c74c3070d966b4cbb74afc4d2c70348feec52b20ab4bd65268fde889053b9fbc

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