FEATURES / MCP SERVER

Your AI tools should understand your engineering team

Gitrevio's MCP server connects your engineering intelligence directly to Claude, Cursor, Windsurf, or any MCP-compatible client. Not a chat widget bolted onto a dashboard — real tools, real data, real access controls.

Set up in 60 seconds

# Add to claude_desktop_config.json
{
"mcpServers": {
"gitrevio": {
"command": "npx",
"args": ["gitrevio-mcp"],
"env": {
"GITREVIO_API_KEY": "gr_live_..."
}
}
}
}
# Or in Claude Code:
$ claude mcp add gitrevio npx gitrevio-mcp

One JSON block or one CLI command. Your AI tool now has access to every piece of engineering intelligence Gitrevio produces.

Works with Claude Desktop, Claude Code, Cursor, Windsurf, ChatGPT, and any tool that supports the Model Context Protocol.

API key scoped to your role — team leads see their teams, CTOs see the org. No shared-access loopholes.

21 MCP tools. Structured outputs.

Not a single "query" endpoint that returns raw text. Each tool is purpose-built, returns structured data, and can be composed by your AI agent.

get_team_velocity
Sprint velocity, trend, and breakdown by contributor
get_org_health_score
Composite score with drillable components
get_onboarding_progress
New hire ramp-up curve and benchmarks
get_attrition_risk
Risk scores per individual, with contributing signals
simulate_departure
What-If analysis for team member changes
get_sprint_analysis
Plan vs reality, predictability score, root causes
get_review_bottlenecks
Who's blocking, wait times, queue depth
get_code_quality
Quality trends by repo, team, or file type
get_release_risk
Per-PR risk score based on historical patterns
get_knowledge_graph
Ownership map, bus factors, knowledge silos
get_tech_debt
Debt hotspots, accumulation rate, priority ranking
get_activity_patterns
What people are working on, context switching
get_dependency_map
Cross-team blocking, wait time heat map
get_ai_impact
AI tool adoption, code quality comparison
get_team_comparison
Side-by-side team metrics with context
get_contributor_profile
Individual contribution patterns, growth trajectory
create_report
Generate a report from any query, schedule delivery
create_alert
Set up alerts on any metric or pattern
get_blast_radius
Formal reachability analysis for any file change. Affected files, services, teams.
get_project_forecast
Lognormal probability distribution for project/epic completion. P50/P75/P90.
get_causal_attribution
Shapley-based decomposition of any metric change into contributing factors.

50+ pre-built prompts

Don't start from scratch. Our prompt library covers the most common engineering intelligence questions, tested and refined to produce reliable outputs.

Weekly reviews
> Generate a sprint retrospective for the backend team
> What were this week's biggest review bottlenecks?
> Compare planned vs delivered work for Sprint 47
People
> Show onboarding progress for all engineers hired in Q1
> Who are the top 3 attrition risks and what can we do?
> What happens if we move Alex from platform to mobile?
Code quality
> Where is tech debt growing fastest?
> Which repos have the highest release risk right now?
> Compare AI-generated code quality vs hand-written for our org
Business
> What's the fully-loaded cost of the auth service rewrite?
> How would adding one engineer to mobile affect delivery date?
> Generate a board-ready engineering health report

How this compares

We're not the only platform with an MCP server. But there's a difference between bolting one onto a dashboard and building for it from the ground up.

Gitrevio LinearB Swarmia Others
MCP tools 21 purpose-built~8New (limited)None
Role-based access ✓Not yet (roadmap)—N/A
Pre-built prompts 50+~10—N/A
Structured outputs ✓ (composable)Text responses—N/A
What-If simulation ✓———
Create reports via MCP ✓———
Create alerts via MCP ✓———
Org Health Score ✓———
Pricing Free – $40/moIncluded at $29/mo€20-39/moNo MCP
Accuracy disclaimer Verified against source data"Double-check in dashboard"—N/A

Also available as an AI Skill

MCP works great for interactive use. For automation, Gitrevio is also available as an AI Skill — a packaged capability your AI agents can invoke programmatically.

Build agentic workflows that check sprint health before standup, flag risky PRs before merge, generate weekly digests automatically, or trigger onboarding reviews when a new hire hits their 30-day mark.

The same intelligence, consumable by machines as naturally as by humans.

# Agentic workflow example
every Monday at 8am:
1. gitrevio.get_org_health_score()
2. gitrevio.get_review_bottlenecks()
3. gitrevio.get_attrition_risk(threshold="medium")
4. compose digest → send to #engineering-leads
before each PR merge:
1. gitrevio.get_release_risk(pr_id)
2. if risk > 0.7: request additional review
3. if risk > 0.9: block merge, notify tech lead

Give your AI tools engineering context.

Get started free