PokerAgile
Server Details
Planning poker rooms an AI assistant can join and vote in, its card hidden until the team reveals.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- florianmousseau/pokeragile
- GitHub Stars
- 1
- Server Listing
- pokeragile
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 7 tools
Most tools target a distinct action (add, join, leave, vote, report, read). get_room and get_estimates overlap somewhat since both read the room/story list, but descriptions clarify that get_room is the full room snapshot while get_estimates focuses on kept estimates.
Six of seven tools follow a clear verb_noun pattern (add_stories, get_estimates, get_room, join_room, leave_room, report_actual). Only 'vote' deviates as a bare verb, a minor inconsistency in an otherwise predictable scheme.
Seven tools is well-scoped for a planning poker workflow. Each tool earns its place covering session entry/exit, story setup, voting, reading state, and reporting actuals.
The core lifecycle (join, add stories, vote, estimate, report actuals, leave) is covered. Some gaps exist, such as exposing a reveal-votes action and room creation/story removal, though these may be host-side UI functions the agent can work around.
Available Tools
7 toolsadd_storiesAInspect
Append story titles to the room's list, for instance the sprint's stories read from your user's tracker. Returns how many were added, how many were refused and why, and the room state; refused when the host locked the room.
Inputs: room (required), seat (required), stories (required). Returns: why, added, state, story, +1 more
get_estimatesARead-onlyInspect
Read the story list with the estimate the team kept for each, as data and as a Markdown table. Call it before you vote, to place the story among the estimates already kept, and when the session is over, to write the estimates back to the tracker.
Inputs: room (required). Returns: stories, markdown
get_roomARead-onlyInspect
Read a room: the deck (cards), the round, the title of the story on the table (story), the story list, who voted, and the results once a person has revealed the votes.
Inputs: room (required). Returns: state, story
join_roomAInspect
Join a planning poker room as a participant marked as an AI. Returns the seat token and the room state.
Inputs: name (required), room (required). Returns: seat, state
leave_roomBInspect
Leave the room and give up the seat.
Inputs: room (required), seat (required). Returns: state, story
report_actualAInspect
Report what a story the team estimated cost once delivered: files touched, lines added and removed, tests added, working time. Numbers only. Returns the list with each measure and the card it looks like; refused for a story with no kept estimate, and when the host locked the room.
Inputs: room (required), seat (required), added (required), files (required), +4 more. Returns: stories, markdown
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Planning poker rooms: import stories from Jira or GitHub, run rounds, write the estimates back.
Meetings for people and AI agents: make a room, join as a disclosed agent, read the transcript.
Poker Bots All Stars is a live multiplayer poker room for agents. Every seat at a table is an AI player with a character built by a person and the agent they brought to play. The agents play no-limit Texas Hold'em against each other, and anyone can watch in a browser. Connect your assistant and it takes a seat as your star.
Shared rooms for existing AI assistants, with messages, files and private memory vaults.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceEnables AI agents to join ephemeral collaborative chatrooms, read room context, poll messages, publish findings, and update their status alongside human participants.-
- AlicenseNot gradedqualityBmaintenanceEnables people to open a shared group chat as a card inside their own AI chat, where they and their AIs talk together and post, claim, and confirm tasks on a self-organizing board. Its tools also let any AI read the repository's code and submit a proposed change that becomes a pull request.MIT
- AlicenseAqualityDmaintenanceJoin.cloud gives AI agents a shared workspace — real-time rooms where they message each other, collaborate on tasks, and share files via git.751 npm66AGPL 3.0
- AlicenseNot gradedqualityBmaintenanceEnables people and AI assistants to collaborate in a shared page where agents inspect room state and prepare structured drafts, while humans keep final authority over commitments and confirmations.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.