Backlog MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BACKLOG_API_KEY | Yes | Your Backlog API key | |
| BACKLOG_BASE_URL | Yes | Your Backlog space URL (e.g., https://your-space.backlog.com) | |
| BACKLOG_TIMEOUT_MS | No | Timeout for Backlog API requests in milliseconds | 10000 |
| BACKLOG_MAX_PAGE_SIZE | No | Maximum page size for Backlog API responses | 100 |
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
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_notificationsC | Get recent Backlog notifications. |
| read_notificationC | Read full notification details. |
| list_projectsC | List accessible Backlog projects. |
| list_repositoriesC | List repositories in a Backlog project. |
| list_pull_requestsC | List pull requests in a Backlog git repository. |
| get_pull_requestC | Get Backlog pull request details. |
| get_pull_request_commentsC | Get comments for a Backlog pull request. |
| list_issuesC | List Backlog issues in accessible projects. |
| get_issueC | Get Backlog issue details. |
| get_issue_commentsC | Get comments for a Backlog issue. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 10 tools
Every tool has a clearly distinct purpose targeting specific resources and actions, such as get_issue vs. get_issue_comments or list_issues vs. list_pull_requests. There is no overlap or ambiguity that would cause misselection by an agent.
All tool names follow a consistent verb_noun pattern with snake_case, such as get_issue, list_projects, and read_notification. This predictability makes the set easy to navigate and understand.
With 10 tools, the server is well-scoped for managing Backlog resources like issues, pull requests, projects, and notifications. Each tool earns its place without feeling excessive or insufficient for the domain.
The toolset covers read operations comprehensively but lacks create, update, or delete actions for issues, pull requests, or comments, which are common in project management workflows. This creates notable gaps that agents might struggle with for full lifecycle management.