MCP HeartbeatTHE MCP OBSERVATORY
Public workspace

Explore

Evidence for your next connection.

Independent measurements of remote MCP servers. Every observation has a timestamp.

Read-only probes

MCP server · Other

com.qretro/retro

QRetro retrospectives and planning poker over MCP: boards, action items, poker games, estimates.

Checks passed
12 / 22

2 failed · 8 not measured

Median response
368 ms

Median of successful probes over 7 days

30-day uptime
Not measured

Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.

Discovered tools
29

Tool definitions returned by this server

Independent monitoring

Health & checks

Status history

Responded

The server completed its last measured handshake. This is an observation, not a guarantee.

Last checked
Check summary by test group
Test areaPassedFailedUnmeasured
ConnectionCan a client connect and discover tools?
500
Reliability & speedDoes it respond consistently and quickly?
004
Access & authenticationWhat is required to use this server?
102
Tool qualityAre the tool definitions usable by an agent?
310
Publisher identityCan the publisher be traced to its source?
312

Unmeasured means there is not enough evidence to decide. How these checks work

Inspect individual checks 22 recorded

Core

  • Pass
    Reachable

    Latest probe returned HTTP 200 in 368 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-11-25, serverInfo.name QRetro.com.

  • Pass
    Lists tools

    tools/list returned 29 tools.

  • Pass
    Current protocol

    Negotiated 2025-11-25. The bar is 2025-06-18 or newer.

  • Pass
    HTTPS

    The endpoint URL is https.

Performance

  • Not measured
    Fast (p50)

    Median latency 368 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 368 ms over 1 samples in 7 days. The bar is 3000 ms. Need at least 20 samples.

  • Not measured
    Reliable (uptime)

    1 of 1 attempts returned a tool list in 30 days (100%). The bar is 99%. Need at least 30 samples.

  • Not measured
    Stable tool list

    Fewer than two successful probes in 30 days, so tool-list stability is not measured.

Access

  • Pass
    Open access

    tools/list succeeded with no credential, and the record declares none.

  • Not measured
    Standard auth

    Auth is not required, so the OAuth metadata check does not apply.

  • Not measured
    Free tier cited

    No publisher quote has been checked.

Tools

  • Pass
    Tools described

    Every tool description is at least 20 characters.

  • Pass
    Valid input schemas

    Every inputSchema is a JSON Schema object.

  • Pass
    Parameters documented

    66 of 66 parameters have a description (100%). The bar is 80%.

  • Fail
    Safety hints

    3 tools set neither readOnlyHint nor destructiveHint.

Publisher

  • Pass
    Verified namespace

    Listed in the Official MCP Registry.

  • Pass
    Website matches publisher

    The website host matches the reverse-domain namespace.

  • Fail
    Source repo linked

    No repository URL is on file.

  • Not measured
    Repo owner matches

    This namespace is not an io.github login, so the owner comparison does not apply.

  • Pass
    Recently updated

    Updated 2026-11-02T19:56:02.902742Z, within 180 days.

  • Not measured
    Open-source licence

    No GitHub repository to ask about a licence.

Start using com.qretro/retro

Connect to this server

Choose your client, copy the configuration, then enable the server in your client’s MCP settings.

Run this command in your terminal, then restart Claude Code.

Claude Code

claude mcp add --transport http com-qretro-retro https://mcp.qretro.com

Capabilities

Tools 29

poker.game.get

Returns one planning poker game: its estimation scale, progress, the task currently on the table and the link participants use to join. Use poker.game.tasks.list for the tasks themselves.

Discovered
poker.game.task.reveal

Reveals the cards of a task and computes its estimate from the votes cast — this is the only way an estimate appears, there is no way to set a number directly. Pass reveal=false to hide the cards again and drop the estimate, which also clears the votes for a re-vote. Only the team owner or an admin can change a game. Requires mcp:write scope.

Discovered
poker.game.task.select

Puts a task on the table: everyone looking at the game sees it as the one being estimated right now. Only the team owner or an admin can change a game. Requires mcp:write scope.

Discovered
poker.game.task.sync

Writes the agreed estimate back to the issue tracker — Jira story points, Linear estimate. Works only for tasks imported from a tracker and only when the integration was connected with write permissions; poker.sources.list shows whether it was. Only the team owner or an admin can change a game. Requires mcp:write scope.

Discovered
poker.game.tasks.add

Adds tasks to a poker game by hand — for work that lives outside an issue tracker, or when no tracker is connected. To pull tasks from Jira or Linear use poker.game.tasks.import instead. Requires mcp:write scope.

Discovered
poker.game.tasks.import

Pulls tasks from a connected issue tracker into a poker game. Give it either iteration_ref from poker.iterations.list to take a whole sprint, or query to search by text and issue key. Tasks already in the game are skipped. Only the team owner or an admin can change a game. Requires mcp:write scope.

Discovered
poker.game.tasks.list

Returns the tasks of a poker game with their estimate, individual votes, tracker key and link. needs_sync tells whether the agreed estimate still differs from the one stored in the tracker — feed those tasks to poker.game.task.sync. Filter with estimated to see what is done or what is left.

Discovered
poker.games.create

Creates a planning poker game for a team and returns the link participants join with. Pick a ready-made scale — fibonacci, modified_fibonacci, tshirts, powers_of_two — or pass your own values in scale_values. Requires mcp:write scope.

Discovered
poker.games.list

Returns the planning poker games of a team, newest first, with how many tasks each of them has and how many already carry an estimate. Personal games outside a team are not exposed over MCP.

Discovered
poker.iterations.list

Returns the iterations of a connected issue tracker — Jira sprints (active and upcoming), and whatever a future tracker calls the same thing. Filter by name with query, for example "AFT 50". Pass the ref of the iteration you want to poker.game.tasks.import to pull its tasks into a game. Trackers without iteration support (currently Linear) return an empty list — search by text instead.

Discovered
poker.sources.list

Returns the issue trackers connected to a team (Jira, Linear) and what each of them can do: search for tasks, list iterations (sprints, cycles), write estimates back. Call this first — the other poker tools depend on what is connected. An empty list means tasks can only be added manually with poker.game.tasks.add.

Discovered
retro.actions.complete

Marks an action item as completed. Requires mcp:write scope.

Discovered
retro.actions.create

Creates a new action item on a retrospective board. Requires mcp:write scope.

Discovered
retro.actions.list

Returns action items across all retrospectives at once — the answer to "what did we agree on and never finish". Covers every team available unless team_id narrows it down; filters by status, assignee and date. Use this instead of walking boards one by one with retro.board.actions.list.

Discovered
retro.actions.update

Updates an existing action item: text, priority, due date, or assignee. Requires mcp:write scope.

Discovered
retro.board.actions.list

Returns action items from a retrospective board, including status, priority, assignee, and due date.

Discovered
retro.board.health.get

Returns the health check of a retrospective: score per category on a 0-10 scale, alignment between participants, turnout, and the same score across the previous retrospectives of the team. Returns health_check: null when the team did not run a health check on this board.

Discovered
retro.board.insights.list

Returns insights (clusters) and suggested actions for a retrospective board. Insights include topic clusters with sentiment, urgency, and category analysis.

Discovered
retro.board.messages.delete_own

Deletes a single board message. Access is strictly governed by API policies: users can delete their own messages, or any message if they have board update rights (requires mcp:write scope for the latter).

Discovered
retro.board.messages.list

Returns all participant messages (cards) for a retrospective board, organized by template columns (e.g. "What went well", "What didn't go well"). Includes text, sentiment, category, grouping, and vote counts.

Discovered
retro.board.messages.update

Updates the text of an existing board message created by the current MCP user.

Discovered
retro.board.roti.get

Returns ROTI (Return on Time Invested) voting metrics for a retrospective board, including average score, distribution, and trend across previous retrospectives.

Discovered
retro.board.suggested_actions.promote

Turns a pending suggested action from retro.board.insights.list into a real action item on the board and marks the suggestion accepted, keeping the wording and the link to its cluster. Requires mcp:write scope.

Discovered
retro.board.suggested_actions.reject

Rejects a pending suggested action from retro.board.insights.list: the suggestion moves to rejected and no action item is created. Requires mcp:write scope.

Discovered
retro.board.summary.get

Returns the summary of a retrospective with participant info and metadata. Works for unfinished boards too — summary is null until the retro is wrapped up, so check is_finished.

Discovered
retro.boards.list

Returns retrospectives (boards) of a team, newest first. Unfinished boards are included unless finished_only is set — otherwise check the is_finished flag. Filters by period via since/until. Pass team_id when several teams are available; with a single team it can be omitted.

Discovered
retro.boards.search

Search across retrospectives by keyword: board summaries, action items and participant cards. Cards hidden by private writing during an ongoing retro are excluded. Optionally filter by team.

Discovered
retro.team.members.list

Returns the members of a team with their id, name and role (owner, admin, facilitator, member). Use the id as assign_to in retro.actions.create, retro.actions.update and retro.board.suggested_actions.promote. This is the team roster, the same one people see in team settings — it says nothing about who wrote which card. Pass team_id when several teams are available; with a single team it can be omitted.

Discovered
retro.teams.list

Returns the list of teams the user belongs to. boards_count is the total number of boards in a team, finished and unfinished alike — use retro.boards.list to tell them apart.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected368 ms29