productboard-mcp: Instructions file for Claude Code

CLAUDE.md

productboard-mcp CLAUDE.md is an instructions file for Claude Code from drmaxbdc/productboard-mcp. It costs 3,899 tokens per session, scanned A, original, MIT.

Project instructions for developing an MCP server that connects coding agents to the Productboard API. Productboard is a product-management service for organizing customer feedback, features, and product decisions.

In plain words
What is it for?
Use them when building, running, publishing, or updating this TypeScript server and its Productboard integrations.
Why use it?
They give developers the project’s setup, architecture, build process, and API-migration requirements in one place.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is drmaxbdc/productboard-mcp's own configuration. It tells Claude Code how to work on productboard-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything productboard-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to drmaxbdc/productboard-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/drmaxbdc/productboard-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/drmaxbdc/productboard-mcp

Made for: Claude Code.

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.

agentmods badge for productboard-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/drmaxbdc/productboard-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/drmaxbdc/productboard-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/drmaxbdc/productboard-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/drmaxbdc/productboard-mcp/claude-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.

agentmods 80×15 button for productboard-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/drmaxbdc/productboard-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/drmaxbdc/productboard-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,899 This file is loaded in full into every session.
When invoked 3,899 The same file — it is already loaded in full.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.03899 $0.03899
Opus 5.5 $0.01560 $0.01560
Sonnet 5.5 $0.00780 $0.00780
Haiku 4.5 $0.00390 $0.00390

Measured 2mo ago against content hash df15f08ff66a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

productboard-mcp CLAUDE.md scanned grade A with 0 findings 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@drmaxbdc/productboard-mcp

Project Overview

MCP (Model Context Protocol) server for the Productboard API. Exposes ~30 tools covering entities, notes, relationships, configurations, members, and analytics. Today the server is hybrid V1 + V2: V2 for CRUD, V1 retained for rich note search (displayUrl, followers, features, fulltext, comments).

Active migration: Productboard API v1 is deprecated and will be sunset on 2026-07-08. Every v1 call must be moved to v2 (or explicitly accepted as a parity gap) before then. See Productboard v2 migration below.

Stack

  • Language: TypeScript (ESM, "type": "module")
  • Runtime: Node.js >= 18
  • SDK: @modelcontextprotocol/sdk ^1.12.1
  • Validation: zod ^3.24.2
  • Build: tsc → build/
  • Distribution: npm package @drmaxbdc/productboard-mcp, run via npx -y @drmaxbdc/productboard-mcp

No test framework, linter, or CI workflow is configured.

Development

Build

npm run build      # tsc → build/

Run locally

PRODUCTBOARD_ACCESS_TOKEN=... npm start

Publish

npm publish        # prepublishOnly → build

Architecture

Entry point src/index.ts bootstraps the MCP server from src/server.ts over stdio.

src/
  index.ts                       # npm bin entry (#!/usr/bin/env node)
  server.ts                      # creates McpServer, registers tool groups
  types.ts                       # shared types: V1Note, PaginatedResponse, etc.
  utils.ts                       # toolResult / toolError / ProductboardApiError
  api/
    client.ts                    # HTTP layer — both V2 and V1 callers live here
  tools/
    configuration-tools.ts       # /entities/configurations, /notes/configurations
    entity-tools.ts              # /entities CRUD + search
    relationship-tools.ts        # /entities/{id}/relationships, set_entity_parent
    note-tools.ts                # /notes CRUD (V2) + rich search/comments (V1)
    member-tools.ts              # /members, /teams

Read the full file on GitHub · 180 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.

  1. 2mo ago Changed · +127 tokens per session df15f08ff66a
  2. 2mo ago First seen · 180 lines · 3,772 tokens per session scan A 630b3c5fbeaf

Subscribe to this mod's changes

productboard-mcp CLAUDE.md is an instructions file published in the GitHub repository drmaxbdc/productboard-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 3,899 tokens to every session, about $0.0156 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

productboard-mcp CLAUDE.md compared with instructions from other repositories

productboard-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
productboard-mcp CLAUDE.mddrmaxbdc/productboard-mcpInstructions file02mo agoMITA3,899Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode