Koalr
Server Details
Connect engineering metrics, DORA performance, and deploy risk scoring to any AI assistant. Score PRs for deployment risk using a 36-signal model, query team health, incidents, coverage, and more.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 21 tools
Most tools target clearly distinct resources and actions, and the descriptions make boundaries explicit, especially between pre-PR change risk (check_change_risk) and existing PR risk (score_pr_for_deploy_risk). A few pairs are close, such as get_open_prs vs. get_at_risk_prs and get_pr_summary vs. related DORA summary tools, but they remain distinguishable by scope.
The naming is consistently snake_case and verb-first, using get_, list_, check_, score_, and search as predictable prefixes. The only slightly generic name is search, but it still follows the verb-first convention and is clearly a catch-all lookup tool.
At 21 tools, the surface is somewhat larger than the ideal 3–15 range, but the server covers many distinct analytics domains: DORA, PR risk, repositories, teams, developers, AI adoption, coverage, well-being, and incidents. Each tool appears to map to a meaningful query rather than duplicating another.
The read-only analytics surface is broad and covers the major lifecycle areas: org health, DORA, PR risk, repositories, teams, developers, AI adoption, coverage, incidents, and search. Minor gaps remain, such as detailed incident retrieval and potentially richer team-level breakdowns for some org-wide metrics, but core workflows are covered.
Available Tools
21 toolscheck_change_riskCheck Change Risk Before Opening a PRARead-onlyIdempotentInspect
Call this BEFORE opening a pull request, with the files you changed. Returns the deploy-risk score (0–100) the PR's Koalr check run will show, the reasons behind it, and toLower: ranked, concrete steps that lower the risk (for example, which files to split into their own PR), each with the score this change would drop to. Also names reviewers who know the code and how risky changes in this repository have gone lately. Get the file list with git diff --numstat <base>...HEAD (plus git diff --numstat for uncommitted work). If the result is medium or higher, take the top toLower step, call this again, and only then open the PR; mention the score and anything you chose not to fix in the PR description. Read-only: nothing about the change is stored.
Inputs: files (required), repository (required), title, baseBranch, +2 more.
get_ai_adoption_summaryAI Coding Tool Adoption SummaryARead-onlyIdempotentInspect
Get AI coding tool adoption metrics including GitHub Copilot acceptance rate, Cursor active users, AI-generated code percentage, and suggestions per developer. Organization-wide, covering the last 30 days. Use this to understand how the team is using AI coding assistants and measure their impact on productivity. Read-only.
Inputs: no named parameters.
get_ai_adoption_trendAI Tool Adoption TrendARead-onlyIdempotentInspect
Get the daily trend of AI tool adoption across Copilot, Cursor, and Claude over the last 30 days (organization-wide). Use this to track whether AI tool adoption is growing or declining. Read-only.
Inputs: no named parameters.
get_at_risk_prsAt-Risk Pull RequestsARead-onlyIdempotentInspect
Get open pull requests whose deploy risk score is 70 or above (High or Critical), newest first, with their opened time, size, author, and repository. Returns up to 100 PRs per page; pass page to read further. Use this to prompt engineering leads to review risky work before it merges. Read-only.
Inputs: page, repositoryId.
get_coverage_summaryTest Coverage SummaryARead-onlyIdempotentInspect
Get the test coverage report across all repositories that deployed in the window: latest coverage percentage, deployment count, failure rate, and incident count per repository, low-coverage hotspots, and the correlation between coverage and failure rate. Use this to find repositories with low coverage that may warrant additional review attention. Read-only.
Inputs: days.
get_developerGet Developer ProfileARead-onlyIdempotentInspect
Get metrics for an individual developer including their PR throughput, review activity, average cycle time, and code contributions. Use this when asked about a specific engineer's activity or productivity. Read-only.
Inputs: login (required).
get_dora_summaryDORA Metrics SummaryARead-onlyIdempotentInspect
Get DORA metrics (deploy frequency, lead time for changes, change failure rate, MTTR) for the organization or a specific team. Use this to understand overall engineering delivery performance and reliability. Read-only — returns aggregated metrics for the selected time window.
Inputs: to, from, teamId.
get_dora_trendDORA Metric TrendARead-onlyIdempotentInspect
Get the daily DORA metric trend to see how deployment frequency, lead time, change failure rate, or MTTR has changed over time. Pass metric to return only that series; omit it for all four. Useful for spotting regressions or improvements across releases. Read-only.
Inputs: days, metric, teamId.
get_open_prsList Open Pull RequestsARead-onlyIdempotentInspect
List currently open pull requests, newest first, regardless of how long they have been open. Each PR includes its number, title, author, branches, opened time, size (additions and deletions), deploy risk score (0-100), and repository. Returns up to 100 PRs per page; pass page to read further. Use this to find stale or large PRs that may be blocking the team. Read-only.
Inputs: page, highRiskOnly, repositoryId.
get_org_healthOrganization Health SnapshotARead-onlyIdempotentInspect
Get a comprehensive organization health snapshot: DORA performance tier (Elite/High/Medium/Low), cycle time percentile vs industry benchmarks, test coverage percentage, number of active teams, and incident rate. Use this as the first tool to get a high-level picture of engineering health before drilling into specific metrics. Read-only.
Inputs: teamId.
get_pr_summaryPull Request Metrics SummaryARead-onlyIdempotentInspect
Get pull request metrics including cycle time (time from first commit to merge), throughput (PRs merged per week), review health (time to first review, reviewer distribution), and PR size trends. Use this to assess code review efficiency and identify bottlenecks in your delivery pipeline. Read-only.
Inputs: days, teamId.
get_repositoryGet Repository DetailsARead-onlyIdempotentInspect
Get detailed metrics for a specific repository including deployment frequency, PR cycle time, contributor count, and code health indicators. Use this when asked about a specific codebase. Read-only.
Inputs: name (required).
get_teamGet Team DetailsARead-onlyIdempotentInspect
Get details and metrics for a specific team including DORA performance, cycle time, and member count. Use this when asked about a specific team's engineering health. Combines DORA and flow metrics in a single response. Read-only.
Inputs: teamId (required).
get_well_being_summaryTeam Well-Being & Burnout RiskARead-onlyIdempotentInspect
Get team well-being scores across pillars: focus time (uninterrupted deep work hours), meeting load (percentage of time in meetings), context switching (task interruptions per day), and burnout risk indicators. Use this to understand developer experience and identify teams under stress before it affects delivery. Read-only.
Inputs: teamId.
list_recent_incidentsRecent Production IncidentsARead-onlyIdempotentInspect
List recent production incidents from PagerDuty or OpsGenie with their severity, MTTR (mean time to recovery), and affected services. Use this to understand reliability posture or investigate a recent outage in context with deployment activity. Read-only.
Inputs: days, limit.
list_repositoriesList Connected RepositoriesARead-onlyIdempotentInspect
List all repositories connected to Koalr with their health scores, activity levels, and basic stats. Use this to get an overview of the codebase landscape or find repository IDs for filtering other tools. Read-only.
Inputs: limit.
list_team_membersList Team MembersARead-onlyIdempotentInspect
List all members of a specific team with their name, email, GitHub login (null when the user has not linked GitHub), team role, and organization role. Use this to understand team composition or find developer logins for the get_developer tool. Read-only.
Inputs: teamId (required).
list_teamsList Engineering TeamsARead-onlyIdempotentInspect
List all engineering teams in the organization with their member counts and slugs. Use this to discover team IDs needed for filtering other metrics tools. Returns an array of team objects with id, name, slug, and memberCount. Read-only.
Inputs: search.
list_top_contributorsTop ContributorsARead-onlyIdempotentInspect
List the most active contributors ranked by commits and PRs merged over a time window. Use this to identify key contributors, bus-factor risks, or to recognize top performers. Read-only.
Inputs: days, limit.
score_pr_for_deploy_riskScore PR Deployment RiskARead-onlyIdempotentInspect
Score a specific pull request for deployment risk using Koalr's 38-signal model. Returns a 0–100 risk score with a detailed factor breakdown covering change entropy, DDL migration detection, author file expertise, PR size, CODEOWNERS violations, blast radius, coverage delta, and more. Use this to answer "How risky is this PR?" or "Should we merge this before the release?". Read-only — scoring does not modify the PR.
Inputs: sha (required), repo (required), owner (required), title (required), +9 more.
searchUnified Entity SearchARead-onlyIdempotentInspect
Search Koalr entities by name: repositories, pull requests (by title or branch), issues, reports, and teams. Returns up to 5 matches per type. Developers are never returned through an API key (privacy); use list_team_members or list_top_contributors to find people. Use this when you need to find an entity before using a more specific tool. Read-only.
Inputs: query (required), type.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceRemote MCP server that lets AI assistants read tracked competitive intelligence — competitor news, reviews, website changes, social posts and ads — and act on it by managing projects, competitors, battle cards, reports and canvases. Every answer carries a source and a date, and write actions only publish when explicitly shared.MIT
- AlicenseCqualityCmaintenanceCompetitor Monitor AI - MCP server providing AI-powered tools and automation by MEOK AI Labs117 npm46 PyPIMIT
- AlicenseAqualityDmaintenanceEnables brand visibility monitoring across major AI platforms like ChatGPT, Claude, Gemini, and Perplexity. It allows users to track visibility scores, analyze competitor data, and receive actionable insights to improve AI-generated brand recommendations.169 npm1MIT

industrylens-mcpofficial
AlicenseNot gradedqualityCmaintenanceBrowse IndustryLens's published competitive-intelligence reports and head-to-head competitor comparisons from any AI agent — real, source-backed data.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.