What is backlog_mcp AGENTS.md?

Repository instructions for backlog-mcp, a TypeScript MCP server that gives agents read access to a Nulab Backlog workspace through its API.

Use them when changing the server, its configuration, API client, tools, or validation code.

They keep authentication, request validation, server creation, and Backlog API access consistent across the project.

How cuongph-dev-work/backlog_mcp configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to cuongph-dev-work/backlog_mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/cuongph-dev-work/backlog_mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/cuongph-dev-work/backlog_mcp

Made for: Claude Code, Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/cuongph-dev-work/backlog_mcp/agents-md/github.svg)](https://agentmods.dev/instructions/cuongph-dev-work/backlog_mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/cuongph-dev-work/backlog_mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/cuongph-dev-work/backlog_mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/cuongph-dev-work/backlog_mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/cuongph-dev-work/backlog_mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,920 This file is loaded in full into every session.

When invoked 2,920 The same file — it is already loaded in full.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.02920	$0.02920
Opus 5.5	$0.01168	$0.01168
Sonnet 5.5	$0.00584	$0.00584
Haiku 4.5	$0.00292	$0.00292

Measured 2mo ago against content hash 1c37395a42e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

backlog_mcp AGENTS.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

3. **HTTP-first for Backlog access.** All Backlog REST API calls go through `src/backlog/http-client.ts` using Axios. The API Key is injected automatically via `axios.create({ params: { apiKey } })`.

AGENTS.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Agent Instructions for backlog-mcp

This file is the canonical instruction set for any AI agent working on this project. Read this file in full before starting any task.

What Is This Project?

backlog-mcp is a TypeScript MCP (Model Context Protocol) server that provides AI agents with read access to a Backlog (Nulab) space. Authentication uses a static API Key stored in .env — no browser or Playwright session required.

Architecture Rules

Server uses factory pattern. Each incoming MCP request gets a new McpServer + StreamableHTTPServerTransport pair. Never reuse a server instance across requests.
Auth is a config concern, not a tool concern. The BacklogHttpClient receives apiKey from config at construction time. Tool handlers never touch auth directly.
HTTP-first for Backlog access. All Backlog REST API calls go through src/backlog/http-client.ts using Axios. The API Key is injected automatically via axios.create({ params: { apiKey } }).
Zod validates everything. Environment variables (src/config.ts) and tool inputs (each tool's schema) are all validated with Zod before use.
Two-layer type system. Raw Backlog API response types live in src/types/backlog-api.ts. Normalized domain types used by handlers live in src/types.ts. Mappers in src/backlog/mappers.ts bridge the two. Never use raw types outside of http-client.ts and mappers.ts.

Coding Standards

TypeScript strict mode. No any. No implicit types.
ESM with .js extensions. All imports must end in .js (NodeNext module resolution).
Errors use McpError. Every business error must use the McpError class with a typed code. Use factory helpers from src/errors.ts.
Tool errors set isError: true. MCP clients rely on this flag. Never return an error as normal content.
401/403 from Backlog = invalid API key. assertOk() in the HTTP client handles this — tool handlers just catch McpError.
Utility functions in src/utils.ts. Shared helpers (e.g. date formatting, string manipulation) must live in src/utils.ts, not inline in tool or handler files.
Prefer libraries over hand-rolled code. For common tasks (date formatting, etc.), use well-known npm packages instead of writing custom implementations.
Raw API response types in src/types/backlog-api.ts. Types that mirror the exact shape of Backlog REST API responses must live there, separate from the normalized application interfaces in src/types.ts.

Read the full file on GitHub · 196 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 196 lines · 2,920 tokens per session scan A 1c37395a42e2

Subscribe to this mod's changes

backlog_mcp AGENTS.md is an instructions file published in the GitHub repository cuongph-dev-work/backlog_mcp (0 stars, last pushed 6mo ago), licensed MIT. It adds 2,920 tokens to every session, about $0.0117 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

backlog_mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
backlog_mcp AGENTS.mdcuongph-dev-work/backlog_mcp	Instructions file	0	6mo ago	MIT	A	2,920	Claude Code, Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

backlog_mcp: Instructions file for Claude Code