miro-mcp-server: Instructions file for Claude Code

CLAUDE.md

miro-mcp-server CLAUDE.md is an instructions file for Claude Code from olgasafonova/miro-mcp-server. It costs 1,598 tokens per session, scanned A, original, MIT.

A Go MCP server that connects AI agents to Miro, a collaborative online whiteboard. It exposes Miro's boards, diagrams, mind maps, comments, canvas content, tags, exports, and audit functions through its tool interface.

In plain words
What is it for?
Use it when building or maintaining an agent integration with Miro, including board editing, diagram generation, comments, exports, authentication, or audit logging.
Why use it?
It gives an agent a defined way to work with Miro data and actions instead of requiring separate manual API calls. It also documents how the server is structured and authenticated.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: names the TodoWrite tool.

This is olgasafonova/miro-mcp-server's own configuration. It tells Claude Code how to work on miro-mcp-server 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 miro-mcp-server configures →

Reuse

Borrowing it

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

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 miro-mcp-server CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/olgasafonova/miro-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/olgasafonova/miro-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,598 This file is loaded in full into every session.
When invoked 1,598 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 $0.01598 $0.01598
Opus 5 $0.00799 $0.00799
Sonnet 5 $0.00320 $0.00320
Haiku 4.5 $0.00160 $0.00160

Measured 10d ago against content hash 7ac4339a2d94, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

miro-mcp-server 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 10d 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 · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Miro MCP Server

Project

Go MCP server for Miro REST API v2. 110 tools across boards, items, diagrams, mindmaps, code widgets, comments, canvas SVG, tags, groups, connectors, export, and audit. OAuth2 + token auth. Single binary with stdio + HTTP transport.

Architecture

  • main.go — entry point, dual stdio/HTTP transport, health/metrics endpoints, token validation
  • miro/client.go — HTTP client with connection pooling (100 max idle, 10 per host)
  • miro/cache.go — LRU cache with 2-minute TTL
  • miro/circuitbreaker.go — circuit breaker isolating failing endpoints
  • miro/ratelimit.go — adaptive rate limiting using Miro response headers
  • miro/errors.go — structured errors with retryable flag
  • miro/diagrams/ — Mermaid parser for flowchart/sequence diagram generation
  • miro/audit/ — local execution audit log (JSON file-based)
  • miro/oauth/ — OAuth2 authentication flow
  • tools/definitions.go — ToolSpec declarations with annotations (ReadOnly, Destructive, Idempotent)
  • tools/handlers.go — HandlerRegistry with generic makeHandler[Args, Result] + panic recovery + audit logging
  • prompts/prompts.go — MCP workflow prompts (sprint board, retro, brainstorm, story map, kanban)
  • resources/resources.go — MCP resource URIs (board summary, items, frames)
  • evals/ — tool selection + argument correctness benchmarks

Key Patterns

  • makeHandler[Args, Result] generic wraps every tool handler with: panic recovery, timing, audit event creation
  • HandlerRegistry.buildHandlerMap() maps Method name -> registration function; adding a tool = one map entry
  • ToolSpec annotations drive MCP tool hints (ReadOnly, Destructive, Idempotent, OpenWorld)
  • All API methods live on the MiroClient interface for testability (mock in tools/mock_client_test.go)
  • Mermaid diagrams parsed locally (no external service), supporting flowchart + sequenceDiagram

Tool Categories (110 total)

  • Board Management (9): list, find, get, create, copy, update, delete, summary, content
  • Board Members (5): list, get, share, update, remove
  • Create Items (15): sticky, shape, flowchart shape, text, connector, frame, card, app card, image, document, embed, bulk create/update/delete, sticky grid
  • Read Items (8): list, list all (paginated), get, search, get image/document/app card, who am i (token introspection)
  • Update/Delete (9): update/delete for sticky, shape, text, card, image, document, embed, generic item
  • Tags (9): create, list, get, attach, detach, get item tags, get items by tag, update, delete
  • Connectors (4): list, get, update, delete
  • Groups (6): create, list, get, get items, update, delete
  • Mindmaps (4): create, get, list, delete
  • Code Widgets (6, v2-experimental): create, get, list, update, move, delete
  • Comments (5, v2-experimental): create, list, get, reply, resolve
  • Canvas SVG (3, local transform): read board as SVG (whole board or one frame), create items from SVG, update items from SVG (data-miro-id diff)
  • Frames (4): get, update, delete, get items
  • Doc Formats (4): create, get, update, delete (Markdown input)
  • Tables (2): list, get (data_table_format metadata)
  • Upload (4): upload image, upload document, update image from file, update document from file (multipart)
  • App Cards (2): update, delete (create and get counted above)
  • Export (4): board picture, create job, status, results
  • Diagrams (3): generate from Mermaid, list native diagrams, get native diagram
  • Audit (2): query local execution log, query Miro org audit log (Enterprise)
  • Desire Paths (1): report tool usage patterns

Read the full file on GitHub · 118 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. 10d ago First seen · 118 lines · 1,598 tokens per session scan A 7ac4339a2d94

Subscribe to this mod's changes

miro-mcp-server CLAUDE.md is an instructions file published in the GitHub repository olgasafonova/miro-mcp-server (26 stars, last pushed today), licensed MIT. It adds 1,598 tokens to every session, about $0.0080 per session on Opus 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 2026-08-30.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens