Data-grounded sprint retro MCP server

by sathvic-kollu·io.github.sathvic-kollu/retro-mcp·v0.1.0

No reviews yet

Data-grounded sprint retrospectives from your Jira, GitHub, and Slack activity.

C69/100grade C

Write a review Install

What users say

No reviews yet

Be the first

Safety scan

C69/100

full report

Adoption

New

0 stars37 downloads/wk

Reviews

Write one

Nobody has reviewed Data-grounded sprint retro yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Data-grounded sprint retro tools (6)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

action_item_review
Close the loop on last retro's action items. Give the previous retro's action items and it attaches THIS sprint's relevant data to each, so the team can see what actually moved. Reviewing prior actions is the single proven lever on retro follow-through. It shows evidence only and lets you judge what counts as done.
discussion_prompts
Open questions for the retro board, each grounded in a real anomaly from the closed sprint (a reopened ticket, mid-sprint scope, a slow review, a revert, a blocker). Questions to start the conversation, not verdicts that end it.
list_sources
Show which data sources are configured (Jira, plus optional GitHub and Slack enrichment), or that the server is running on a synthetic demo sprint. Does not hit the network; run the server with --check to verify live connections.
retro_brief
Generate a data-grounded sprint retrospective for the most recently closed sprint: What went well, What did not, Action items, and Discussion prompts. Every line is backed by a metric, ticket, PR, or Slack thread, framed around the process not individuals. Recurring themes across recent sprints are flagged.
retro_metrics
The hard numbers behind the retro for the closed sprint: completion, mid-sprint scope change, carryover, reopens, average cycle time vs the prior sprint, velocity, PR review latency, reverts and hotfixes, and flagged Slack threads. This is the evidence base the brief draws from.
sprint_compare
Compare the closed sprint against the one before it (completion, scope, carryover, reopens, cycle time, velocity), and list the problem themes that recur across recent sprints. Use it to tell a one-off from a pattern.

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

no findings

Code scan27 source files scanned25/25
–Live reliabilityno gateway calls yet and no remote to proben/a
–Tool poisoningtools not inspected (local package is not executed); not countedn/a
Auth qualitystatic API keys via environment variables6/15
Maintenancelast push 101 days ago8/15
Maintainer identityregistry namespace matches repository owner6/10

Overall 69/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

How Data-grounded sprint retro compares

Against every graded Developer tools MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score: 69/100; higher than 28% of 1,119 Developer tools servers
Tools: 6; the typical Developer tools server has 7
Tools that change things: 0%; typical: 5%. Fewer write tools means less an agent can break
Downloads a week: 37; more than 23% of 436 Developer tools servers with a package

What its tools let an agent do: 6 read

Install Data-grounded sprint retro in Claude Code, Cursor or VS Code

Runs npx -y retro-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add retro-mcp -- npx -y retro-mcp

Add to Cursor

What the publisher says

From the Data-grounded sprint retro repository's README, as published. We do not edit it. Read it on GitHub

retro-mcp

A sprint retrospective grounded in what actually happened, not what people remember.

Retros run on memory, so they run on bias. The loudest voice and the last few days win, the same complaints come back every sprint, and the action items quietly never happen. Meanwhile the actual record of the sprint, the reopened ticket, the PR that sat two days in review, the Slack thread where someone said they were blocked, is sitting right there in your tools, unused.

retro-mcp reads that record and hands you a retro built from it. You ask your AI assistant for the retro and it answers with what went well, what didn't, and action items, every line backed by a specific metric, ticket, PR, or thread. It frames everything around the process, never individuals, and it flags the problems that keep recurring across sprints.

It is a standard Model Context Protocol server, so it works in any MCP client (Claude, Cursor, Cline, and more) on any model. It is local and read-only: nothing about your sprint leaves your machine except the calls to your own tools' APIs, and it needs no AI API key. That is also the answer to the obvious worry: it is a retro aid, not a surveillance tool.

See it in 30 seconds (no accounts needed)

It ships with a realistic closed sprint and runs against it automatically when no credentials are set:

npx -y retro-mcp --demo

Here is the headline tool on that demo sprint:

# Sprint Retrospective: MBANK Sprint 23
_May 27 to Jun 10. Demo data, no credentials configured._
_Grounded in 8 issues, 5 merged PRs, and 4 flagged threads. System-level and blameless: this is about the process, not people._

## What went well
- **Work moved through faster than last sprint.** avg cycle time 4.6d, down from 5.6d.

## What did not go well
- **The sprint fell short of its commitment.** only 23 of 34 pts done (68%).  ⟳ recurring across recent sprints
- **Scope grew mid-sprint.** +5 pts across 2 issues pulled in after the sprint started.  ⟳ recurring across recent sprints
- **Work carried over into the next sprint.** 3 issues (16 pts) not finished.  ⟳ recurring across recent sprints
- **Some work was called done before it was.** MBANK-203 · reopened 1 time: Statement PDF export.
- **Code review was a bottleneck.** PRs waited 20.3h on average for a first review; PR #503 · sat 52h: statement PDF export.
- **Changes had to be reverted or hotfixed.** PR #504 · revert: OTP delivery change; 1 hotfix merged.
- **The team hit repeated blockers and interruptions.** 2 threads mentioned being blocked; 1 thread mentioned an incident.

## Action items
- [ ] (recurring) Adopt a scop

Every line points at something real. Nobody typed it from memory, and the three recurring problems are flagged as patterns, not fresh complaints.

What it does

Six tools. Everything defaults to the most recently closed sprint.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Data-grounded sprint retro: common questions

Is Data-grounded sprint retro MCP server safe?: With care: it is graded C, so read the findings first (69/100). Read the Data-grounded sprint retro safety report
How do I install Data-grounded sprint retro?: It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Data-grounded sprint retro need an API key?: Yes. The registry entry asks for JIRA_API_TOKEN, GITHUB_TOKEN, SLACK_TOKEN.
Is Data-grounded sprint retro maintained?: The last commit was 140 days ago (2026-06-17). The latest release is v0.1.0.
What can I use instead of Data-grounded sprint retro?: Servers from other publishers that do the same job: Atlassian Extended MCP server, GitDiagram MCP server and GitHub MCP server.
How does Data-grounded sprint retro compare with other Developer tools MCP servers?: safety score 69/100 (higher than 28% of 1,119 Developer tools servers); tools 6 (the typical Developer tools server has 7); tools that change things 0% (typical: 5%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Data-grounded sprint retro

Same job from other publishers: the closest match first, then the best rated.

Atlassian Extended
Jira/Confluence MCP server (MCP 2026-07-28): sprints, boards, attachments; writes or read-only
not reviewed
Growing
B
GitDiagram
Architecture diagrams, explanations and Mermaid source for public GitHub repositories.
not reviewed
Established
A
GitHub
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
not reviewed
Established
A
Gk CLI
The GitKraken MCP Server for managing repos, PRs, issues across GitHub, GitLab, Bitbucket and more.
not reviewed
Established
B
Agent Harnesses
Agent-harness picks, decision guides, setup templates, and skills; live GitHub/HN discovery.
not reviewed
Established
A

Run it through the gateway

Local package. It runs on your machine, not through the gateway.

Rating: —
Safety grade: C · 69/100
Stars: 0
Downloads/wk: 37
Price: Free
Licence: MIT
Transport: Local · npm
Version: 0.1.0
Category: Developer tools
Last release: 2026-06-17

Credentials it needs

JIRA_BASE_URLYour Jira Cloud site, e.g. https://your-company.atlassian.net. Required for a live retro.
JIRA_EMAILAtlassian account email the API token belongs to.
JIRA_API_TOKENsecretJira API token from id.atlassian.com. Read-only use.
JIRA_BOARD_IDOptional board id to pin when the account has several boards.
GITHUB_TOKENsecretOptional GitHub read-only token for PR review latency and reverts.
GITHUB_REPOSOptional comma-separated owner/name repos to scope PR analysis.
SLACK_TOKENsecretOptional Slack read token to scan sprint channels for blocker and incident language.
SLACK_CHANNELSOptional comma-separated Slack channel ids to scan for the sprint window.
RETRO_DEMO_MODESet to true to force the synthetic demo sprint even when credentials are present.

Own this server?

Claim it to keep the listing current and reply to reviews. Claiming never changes the grade or hides a review.

Claim listing

Badge for your README

Shows the safety grade and links back to this page. It updates itself after every scan and review.

[![mcp.market](https://mcp.market/badge/sathvic-kollu-retro-mcp.svg)](https://mcp.market/server/sathvic-kollu-retro-mcp)

How the badge works