Name: Backlog MCP Server
Author: nulab

LABSCO SUMMARY

One space's issues, wiki, documents and pull requests answer to the same session.

The reach is unusual for a tracker binding: Backlog's Git repositories are in scope, so a pull request can be opened, updated and commented next to the issue it closes. count_issues is the tool that changes how the rest get used — ask for the number first, fetch bodies only when the number justifies it. It is not a read-only surface either: project, issue, version and watch deletions sit in the same set as the reads, and the way to bound that is the toolset flag, which is also how you keep the catalogue small enough for a client to handle.

What it is

A server over the Backlog API, covering projects, issues, comments, wikis, documents, Git repositories and pull requests, watches and notifications.

What you get

count_issues taking the same filter set as get_issues — assignee, status, milestone, category, custom fields, and created, updated, start and due windows — so a distribution question is answered without fetching issue bodies
Issue relations maintained in both directions through get_related_issues, add_related_issue and remove_related_issue
Pull requests in the project's own repositories: listed, counted, opened, updated and commented on, addressed by repoName or repoId
Two generations of documentation side by side — wiki pages with add_wiki and update_wiki, and the newer document tree through get_document_tree and addDocument
Watches and notifications as objects rather than UI state: a watch carries a note, can be marked read, and the unread counter can be counted or reset
Toolsets switched on individually — space, project, issue, wiki, git, notifications, document — so a client with a tight tool budget carries only what it uses
Responses kept in bounds: a fields parameter on the list tools returns only the columns you name, and a token ceiling truncates anything past 50,000 tokens by default
Several Backlog organizations reachable from one server, each call routed by an organization argument that defaults to the one you nominate

Requirements

BACKLOG_DOMAIN naming the space and BACKLOG_API_KEY for a user inside it; every call runs as that user, which get_myself will confirm. It runs from npx or the published Docker image, and for multiple spaces the domain and key are supplied per organization instead. Exposed over HTTP it binds to 127.0.0.1 by default and validates Host and Origin — anything wider needs an allowed-hosts list, and the port must not reach an untrusted network, since it hands out full use of the API key. Remote deployments can use OAuth instead, so each person authenticates as themselves. MIT.

Setup effort

One command plus a key — docker pull ghcr.io/nulab/backlog-mcp-server:latest, then supply credentials

See installation options

USE CASES

01

Filing the bug you just reproduced

Create the issue against the right project with its type, priority and milestone, add the reproduction as a comment, and link it to the issue it is a regression of.

add_issueadd_issue_commentadd_related_issue

02

Answering how much is left before the release

Ask for the count under the milestone and status you care about before pulling anything, then list only the issues that survive the filter and check the milestone's release date.

count_issuesget_issuesget_version_milestone_list

03

Reviewing the pull request that closes an issue

Find the open pull requests on the project's repository, read the one linked to the issue, and leave the review comment or update its status without switching tools.

get_pull_requestsget_pull_requestadd_pull_request_commentupdate_pull_request

04

Writing up a decision where the team will find it

Look at where documents already sit in the project tree, add the write-up in the right place, and update the wiki page that people actually navigate to.

get_document_treeaddDocumentget_wiki_pagesupdate_wiki

05

Clearing a week of Backlog notifications

Count what is unread before reading any of it, walk the list in order, mark the ones that matter as read, and reset the counter once the rest have been triaged.

count_notificationsget_notificationsmark_notification_as_readreset_unread_notification_count

06

Setting up a new project's issue fields

Create the project, then read back the issue types, categories and custom fields it starts with so the first issues are filed against the right vocabulary rather than corrected later.

add_projectget_issue_typesget_categoriesget_custom_fields

62 tools

Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.

`add_issue`

Creates a new issue in the specified project.

BEFORE YOU INSTALL

What to know first

Tools you get

62 tools when we connected. Two tools answer to different names than documented: count_notifications, not get_notifications_count, and delete_version, not delete_version_milestone. ENABLE_TOOLSETS or --enable-toolsets limits the list to chosen toolsets; the default is all.

Requires

npx on PATH
BACKLOG_DOMAIN in your environment
BACKLOG_API_KEY in your environment

CONTEXT COST

Moderate Standing cost

Rated by the size of the 62 tool definitions that ride along on every turn, not by how many there are

INSTALLATION

Connect your client

Server setup

TERMINAL

docker pull ghcr.io/nulab/backlog-mcp-server:latest

MCP Clients

Any MCP client — Docker

ANY MCP CLIENT — DOCKER · JSON

{
  "mcpServers": {
    "backlog": {
      "command": "docker",
      "args": [
        "run",
        "--pull",
        "always",
        "-i",
        "--rm",
        "-e",
        "BACKLOG_DOMAIN",
        "-e",
        "BACKLOG_API_KEY",
        "ghcr.io/nulab/backlog-mcp-server"
      ],
      "env": {
        "BACKLOG_DOMAIN": "<YOUR_DOMAIN>.backlog.com",
        "BACKLOG_API_KEY": "<YOUR_BACKLOG_API_KEY>"
      }
    }
  }
}

Any MCP client — npx

ANY MCP CLIENT — NPX · JSON

{
  "mcpServers": {
    "backlog": {
      "command": "npx",
      "args": [
        "backlog-mcp-server"
      ],
      "env": {
        "BACKLOG_DOMAIN": "<YOUR_DOMAIN>.backlog.com",
        "BACKLOG_API_KEY": "<YOUR_BACKLOG_API_KEY>"
      }
    }
  }
}

Self-hosted server — OAuth

SELF-HOSTED SERVER — OAUTH · TERMINAL

git clone https://github.com/nulab/backlog-mcp-server.git
cd backlog-mcp-server
pnpm install
pnpm run build

In your Backlog space, Personal Settings → Register Application: set the Redirect URI to <YOUR_MCP_SERVER_BASE_URL>/callback and note the Client ID and Client Secret

SELF-HOSTED SERVER — OAUTH · TERMINAL

BACKLOG_DOMAIN=<YOUR_SPACE>.backlog.com \
BACKLOG_OAUTH_CLIENT_ID=<YOUR_BACKLOG_OAUTH_CLIENT_ID> \
BACKLOG_OAUTH_CLIENT_SECRET=<YOUR_BACKLOG_OAUTH_CLIENT_SECRET> \
MCP_SERVER_BASE_URL=<YOUR_MCP_SERVER_BASE_URL> \
node build/index.js --transport http --http-host 0.0.0.0 --http-port 3333 \
  --http-allowed-hosts <YOUR_HTTP_ALLOWED_HOSTS>

Run it from the clone. <YOUR_HTTP_ALLOWED_HOSTS> is the public hostname your server is reached at, and <YOUR_MCP_SERVER_BASE_URL> is the same hostname as an https:// address. Clients connect to <YOUR_MCP_SERVER_BASE_URL>/mcp and sign in with their own Backlog account; no BACKLOG_API_KEY is needed in this mode.

Backlog MCP Server

One space's issues, wiki, documents and pull requests answer to the same session.

What it is

What you get

Requirements

Setup effort

Filing the bug you just reproduced

Answering how much is left before the release

Reviewing the pull request that closes an issue

Writing up a decision where the team will find it

Clearing a week of Backlog notifications

Setting up a new project's issue fields

62 tools

add_issue

add_issue_comment

add_project

add_pull_request

add_pull_request_comment

add_related_issue

add_version_milestone

add_watching

add_wiki

addDocument

count_issues

count_notifications

delete_issue

delete_project

delete_version

delete_watching

get_categories

get_custom_fields

get_document

get_document_tree

get_documents

get_git_repositories

get_git_repository

get_issue

get_issue_comments

get_issue_types

get_issues

get_myself

get_notifications

get_priorities

get_project

get_project_list

get_project_users

get_pull_request

get_pull_request_comments

get_pull_requests

get_pull_requests_count

get_related_issues

get_resolutions

get_space

get_space_activities

get_user_recent_updates

get_user_stars_count

get_users

get_version_milestone_list

get_watching_list_count

get_watching_list_items

get_wiki

get_wiki_pages

get_wikis_count

mark_notification_as_read

mark_watching_as_read

remove_related_issue

reset_unread_notification_count

update_issue

update_issue_comment

update_project

update_pull_request

update_pull_request_comment

update_version_milestone

update_watching

update_wiki

What to know first

Tools you get

Requires

Moderate Standing cost

Connect your client

`add_issue`

`add_issue_comment`

`add_project`

`add_pull_request`

`add_pull_request_comment`

`add_related_issue`

`add_version_milestone`

`add_watching`

`add_wiki`

`addDocument`

`count_issues`

`count_notifications`

`delete_issue`

`delete_project`

`delete_version`

`delete_watching`

`get_categories`

`get_custom_fields`

`get_document`

`get_document_tree`

`get_documents`

`get_git_repositories`

`get_git_repository`

`get_issue`

`get_issue_comments`

`get_issue_types`

`get_issues`

`get_myself`

`get_notifications`

`get_priorities`

`get_project`

`get_project_list`

`get_project_users`

`get_pull_request`

`get_pull_request_comments`

`get_pull_requests`

`get_pull_requests_count`

`get_related_issues`

`get_resolutions`

`get_space`

`get_space_activities`

`get_user_recent_updates`

`get_user_stars_count`

`get_users`

`get_version_milestone_list`

`get_watching_list_count`

`get_watching_list_items`

`get_wiki`

`get_wiki_pages`

`get_wikis_count`

`mark_notification_as_read`

`mark_watching_as_read`

`remove_related_issue`

`reset_unread_notification_count`

`update_issue`

`update_issue_comment`

`update_project`

`update_pull_request`

`update_pull_request_comment`

`update_version_milestone`

`update_watching`

`update_wiki`