MCP Server

Let your AI
run the retro

Read boards, create polls, search cards, and generate reports from Claude, Cursor, or VS Code. One command, zero config.

◇ LetRetro MCP CLI v1.2.0
◆ Enter your API Key: ••••••
✔ API key validated
✔ Detecting MCP clients... found 11
Claude Desktop · Cursor · VS Code · Windsurf · +7 more
✔ Config files written
~/.claude/claude_desktop_config.json
1command

npx @letretro/mcp install. No config files to touch.

11clients

Claude, Cursor, VS Code, Windsurf. All auto-detected.

17tools

Boards, cards, polls, teams, reports. Everything at your AI's fingertips.

Proplan

Included with every Pro plan. Get your API key from the dashboard.

Up and running in 30 seconds

One install. Auto-detects every MCP client on your machine. Writes all the config. No manual edits.

01

Get your key

Sign up for a Pro plan and generate a lr_-prefixed API key from your dashboard.

Go to dashboard
02

Run the installer

npx @letretro/mcp install. Paste your key, pick your clients, and the CLI writes every config file.

npx @letretro/mcp install
03

Ask your AI

Restart your MCP clients. Your AI can now read boards, search cards, create polls, and generate reports.

17 tools your AI can use right now

Every action you would take in the dashboard, now available from your coding assistant.

Boards

4 tools
list_boards

Browse every board you own or are a member of

get_board

View full board detail with columns, settings, and members

get_board_stats

Check card counts, poll activity, and who is active

create_board

Create a new retro board with your preferred column template

Cards

4 tools
get_board_cards

Read cards grouped by column with author profiles and comments

search_cards

Search across all card content in seconds

create_card

Drop a rich-text card into any column

add_comment

Jump into conversations with @mentions

Polls & Reports

5 tools
list_polls

See all polls with vote counts and whether they are still open

get_poll

Drill into poll results, who voted and how

create_poll

Run a poll with 2-20 options and priority labels

get_job_status

Check if an async job is done yet

generate_report

Ask your AI to generate a retro trend analysis

Team & Account

4 tools
list_teams

See teams you are in and your role in each

get_activity_summary

Birds-eye view of recent cards, comments, and polls

get_profile

View your profile, subscription tier, and plan details

get_usage

Check your MCP API usage and remaining quota

Works everywhere you code

11 MCP clients supported. The installer finds them all. You do not touch a single config file.

Claude Desktop
Cursor
VS Code
VS Code
OpenCode
Windsurf
Claude Code
C
Continue
Gemini
Gemini
Hermes
Hermes
Codex CLI
Codex CLI
OpenClaw
OpenClaw
Claude Desktop
Cursor
VS Code
VS Code
OpenCode
Windsurf
Claude Code
C
Continue
Gemini
Gemini
Hermes
Hermes
Codex CLI
Codex CLI
OpenClaw
OpenClaw

What to ask your AI

Once LetRetro MCP is connected, try these prompts.

Prompt

Show me the latest 5 cards from our retro board

Frequently asked questions

MCP (Model Context Protocol) is an open standard that lets AI coding assistants communicate directly with tools and services. Instead of manually copying data between apps, your AI can read boards, search cards, and create polls in real time. It is like giving your AI a direct line to LetRetro.

Any assistant that supports the MCP protocol: Claude Desktop, Claude Code, Cursor, VS Code, OpenAI Codex CLI, Windsurf, OpenCode, Gemini, Hermes AI, OpenClaw, Continue, and more. We auto-detect 11 clients on your machine.

Sign up for a Pro plan on the letRetro dashboard. Once subscribed, generate a lr_-prefixed API key from the billing settings page. Then run npx @letretro/mcp install and paste the key when prompted.

MCP access is included with the Pro plan. You get 20,000 requests per month. Check our pricing page for plan details and upgrade options.

Your API key is stored locally in the MCP client config files on your machine. It is sent securely to mcp.letretro.com with every request and is never logged or stored on our servers beyond the request lifecycle.

The server returns a quota exceeded response. Your usage resets at the start of each billing cycle. You can check your remaining quota anytime by calling the get_usage tool from your AI assistant.

Still have questions?

Reach out, we are happy to help.

Contact us