How to Connect Backlog MCP to an AI Agent
Auth setup
1. Log into Backlog > Personal Settings > API. 2. Generate API key. 3. Append ?apiKey={key} to every request URL. No header needed.
Key facts
| Base URL | https://{space}.backlog.com/api/v2/ |
|---|
| API version | v2 |
|---|
| Auth | Two methods: 1) API Key — generate at Backlog settings, pass as ?apiKey= query param. 2) OAuth 2.0 — register at developer.nulab.com. API key is simpler for agents. |
|---|
| Token URL | https://{space}.backlog.com/api/v2/oauth2/token |
|---|
| Request body | application/x-www-form-urlencoded |
|---|
| Pagination | offset: 'offset' and 'count' params (max 100). No total count in response — fetch until empty. |
|---|
| Rate limit | Varies by plan. Typically no strict rate limit for API key access, but heavy use may be throttled. |
|---|
| Error format | JSON: {"errors":[{"message":"No such issue.","code":6,"moreInfo":""}]} |
|---|
Key endpoints
| Method | Path | Description |
|---|
GET | /issues | List issues with filters (project, status, assignee) |
POST | /issues | Create a new issue |
PATCH | /issues/{issueIdOrKey} | Update an issue (status, assignee, etc.) |
GET | /projects | List all projects |
GET | /wikis | List wiki pages in a project |
Quickstart
GET /api/v2/issues?projectId[]=1&statusId[]=1&apiKey={key} HTTP/1.1
Host: myspace.backlog.com
Response: [{"id":1,"issueKey":"PROJ-1","summary":"バグ修正","status":{"id":1,"name":"Open"}}]
Agent pitfalls & tips
- POST/PATCH use application/x-www-form-urlencoded, not JSON. Common source of 400 errors.
- Issue keys like 'PROJ-1' can be used instead of numeric IDs in most endpoints.
- Array params use bracket notation: projectId[]=1&projectId[]=2.
- Base URL requires space name: https://{space}.backlog.com. Ask user for their Backlog space name.
- Webhook support: POST /projects/{projectId}/webhooks for real-time issue updates.
Source: curated by KanseiLink from official documentation (docs) and registry checks. Last reviewed: 2026-04-04. Specs change — verify against the official docs before production use.
Frequently Asked Questions
What is Backlog MCP's AEO score?
▼
Backlog MCP has an AEO score of 1.00 and is rated AAA (Best-in-class agent integration). AEO (Agent Engine Optimization) measures how well a SaaS service works with AI agents. Scores range from 0.00 to 1.00, with grades from AAA (best) to D (not agent-ready).
Is Backlog MCP AI-agent-ready?
▼
Backlog MCP is currently ✓ verified for AI agent use. It offers an official MCP (Model Context Protocol) server, which means AI agents can connect directly. For detailed connection guides, auth setup, and known pitfalls, use the KanseiLink MCP tool.
How does Backlog MCP compare to other Project Management services?
▼
In the Project Management category, Backlog MCP is rated AAA. KanseiLink evaluates services based on MCP availability, API quality, documentation, auth-guide clarity, and integration recipe availability (methodology published). Visit the full rankings at kansei-link.com to see how Backlog MCP compares.
How can I integrate Backlog MCP with an AI agent?
▼
The fastest way to integrate Backlog MCP with an AI agent is through KanseiLink MCP. Install it with: npx @kansei-link/mcp-server — then use the search_services and get_service_detail tools to get the current auth setup, endpoints, rate limits, and agent-specific tips. This data is kept fresh from registry checks, curated official-doc guides, and agent reports.
How do I authenticate with Backlog MCP?
▼
Two methods: 1) API Key — generate at Backlog settings, pass as ?apiKey= query param. 2) OAuth 2.0 — register at developer.nulab.com. API key is simpler for agents. Setup: 1. Log into Backlog > Personal Settings > API. 2. Generate API key. 3. Append ?apiKey={key} to every request URL. No header needed.
What are Backlog MCP's API rate limits?
▼
Varies by plan. Typically no strict rate limit for API key access, but heavy use may be throttled.