> ## Documentation Index
> Fetch the complete documentation index at: https://docs.periscope.sh/llms.txt
> Use this file to discover all available pages before exploring further.

# MCP server

> Query your engineering metrics from AI coding assistants like Claude Code, Cursor, and Windsurf through the Model Context Protocol.

Periscope exposes a Model Context Protocol (MCP) server that lets you query your DORA metrics, SPACE metrics, and deployment data directly from your AI coding assistant. Instead of switching to the dashboard, ask your AI assistant about your team's metrics in natural language.

## Overview

* **Server URL:** `https://app.periscope.sh/mcp`
* **Protocol:** MCP over HTTP (streamable)
* **Authentication:** OAuth 2.0 (same login as the dashboard)
* **Available tools:** 18 read-only query tools
* **Plan requirement:** Business or Enterprise (included in 14-day trial)

<Info>
  Periscope is currently in private beta. Setup instructions will be available once you have access. [Join the waitlist](https://tally.so/r/MeAqPM) to get early access.
</Info>

## Available tools

Periscope provides 18 read-only tools organized by category.

### Overview

| Tool                   | Description                                                                                                                    |
| ---------------------- | ------------------------------------------------------------------------------------------------------------------------------ |
| `ping`                 | Health check — returns "pong" to verify the server is running                                                                  |
| `get_overview_summary` | High-level DORA summary: PRs merged, cycle time p50, production deploys, lead time p50, all with period-over-period comparison |

### DORA metrics

| Tool                       | Description                                                                           |
| -------------------------- | ------------------------------------------------------------------------------------- |
| `get_deployment_frequency` | Daily deployment counts, success/failure breakdown, environment breakdown, DORA level |
| `get_lead_time`            | PR merge to production time — p50, p75, p95 percentiles with sample PRs               |
| `get_change_failure_rate`  | Failed deployment percentage, per-service breakdown, recent failures                  |
| `get_mttr`                 | Mean time to recovery — p50, p75, p95 with incident details                           |

### SPACE / PR analytics

| Tool                       | Description                                              |
| -------------------------- | -------------------------------------------------------- |
| `get_pr_cycle_time`        | PR open to merge time — p50, p75, p95 with weekly trends |
| `get_throughput`           | Weekly PR merge counts and averages                      |
| `get_pr_velocity`          | Daily PR merge counts over time                          |
| `get_contributor_activity` | Per-contributor PR counts, sizes, cycle times            |
| `get_service_health`       | Per-repository health status (healthy/warning/stale)     |
| `get_risk_signals`         | Detected engineering risks with recommendations          |
| `get_combined_activity`    | Daily PRs merged + deployments overlaid                  |

### Deployment details

| Tool                               | Description                                                    |
| ---------------------------------- | -------------------------------------------------------------- |
| `get_recent_deployments`           | List of recent deployments with status, duration, pipeline URL |
| `get_deployment_service_breakdown` | Per-service deployment stats, failure rates, durations         |
| `get_prs_in_deployment`            | PRs included in specific deployments with lead times           |
| `get_slowest_lead_times`           | PRs with the worst lead times (bottleneck identification)      |
| `get_undeployed_prs`               | Merged PRs not yet deployed to production                      |

### Common parameters

Most tools accept these parameters:

| Parameter     | Type     | Options                              | Description                        |
| ------------- | -------- | ------------------------------------ | ---------------------------------- |
| `time_range`  | `string` | `"7d"`, `"30d"`, `"90d"`, `"all"`    | Time range to analyze              |
| `environment` | `string` | `"production"`, `"staging"`, `"all"` | Environment filter (some tools)    |
| `limit`       | `number` | Any positive integer                 | Max results to return (some tools) |
| `service`     | `string` | Any service name                     | Service filter (some tools)        |

## Usage examples

### Check overall engineering health

Ask your AI assistant:

> "How are our DORA metrics looking for the last 30 days?"

The assistant will call `get_overview_summary` and summarize your PRs merged, cycle time, deployment count, and lead time with period-over-period comparisons.

### Investigate deployment issues

> "Which services have the highest failure rate this month?"

The assistant will call `get_change_failure_rate` and `get_deployment_service_breakdown` to identify problematic services.

### Find undeployed code

> "Are there any merged PRs that haven't been deployed yet?"

The assistant calls `get_undeployed_prs` to show code that is merged but waiting for a deployment.

### Identify team risks

> "Are there any risk signals I should know about?"

The assistant calls `get_risk_signals` to surface bus factor risks, stale services, workload imbalances, and activity anomalies.

### Understand a deployment

> "What PRs went out in the last production deployment?"

The assistant calls `get_prs_in_deployment` with a limit of 1 to show the most recent deployment and its associated PRs.

### Track cycle time trends

> "How has our PR cycle time changed over the last 90 days?"

The assistant calls `get_pr_cycle_time` with `time_range: "90d"` and presents the weekly trend data.

<Card title="Get early access" icon="clock" href="https://tally.so/r/MeAqPM">
  Join the waitlist to get access to the MCP server and all 18 metric tools.
</Card>