# Framedash MCP Server

> Framedash MCP Server is a freemium MCP server for analytics and data. Query Framedash game telemetry, heatmaps and alerts from an AI assistant. It runs locally on your machine and is started by your AI client.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Platforms:** API, CLI
- **Website:** https://framedash.dev
- **Repository:** https://github.com/crane-valley/framedash-mcp-server
- **MCP Registry name:** io.github.crane-valley/framedash-mcp-server
- **Categories:** analytics and data, games and play
- **Listing updated:** 2026-11-14

## About

Framedash is a Japanese-language game telemetry service for Unity, Unreal Engine 5 and Godot (C#) that records frame time, GPU time and memory and overlays them on a game map as heatmaps, then compares builds to catch regressions before release. This server gives an assistant read-only access to that data.

Twelve tools cover a project KPI summary, retention cohorts, funnels, event insights, heatmap grids, maps, the content registry, alert rules and alert history. A raw SQL query tool accepts SELECT only and needs an API key with an extra data:admin scope, while the aggregate tools need analytics:read. Four resources expose the project, its maps, its content and its status. Set FRAMEDASH_PROJECT_ID for a default project, or pass project_id on each call.

The npm package runs over stdio and is MIT licensed. The hosted HTTP endpoint rejects request batches of more than 100 messages.

## Features

- **12 read-only tools:** Analytics, retention, funnels, heatmaps, maps, content and alerts.
- **Raw SQL queries:** SELECT-only queries with a default limit, behind an extra key scope.
- **Heatmap data:** Fetch grid data for a map to find performance hotspots.
- **Alert history:** See which threshold alerts fired and when.
- **Project resources:** Four resources expose projects, maps, content and status.
- **Scoped keys:** analytics:read for aggregates, data:admin for raw queries.

## Good for

- Ask which build regressed P95 frame time
- Compare retention cohorts after an update
- Pull heatmap data for a level to find slow areas
- Check recent alert triggers for a project
- Run an ad hoc SQL query on game events

## Install

### Claude Code (Terminal)

```sh
claude mcp add framedash-mcp-server --env FRAMEDASH_API_KEY='<FRAMEDASH_API_KEY>' -- npx -y @framedash/mcp-server
```

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "framedash-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@framedash/mcp-server"
      ],
      "env": {
        "FRAMEDASH_API_KEY": "<FRAMEDASH_API_KEY>"
      }
    }
  }
}
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "framedash-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@framedash/mcp-server"
      ],
      "env": {
        "FRAMEDASH_API_KEY": "<FRAMEDASH_API_KEY>"
      }
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "framedash-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@framedash/mcp-server"
      ],
      "env": {
        "FRAMEDASH_API_KEY": "<FRAMEDASH_API_KEY>"
      }
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "framedash-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@framedash/mcp-server"
      ],
      "env": {
        "FRAMEDASH_API_KEY": "<FRAMEDASH_API_KEY>"
      }
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "framedash-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@framedash/mcp-server"
      ],
      "env": {
        "FRAMEDASH_API_KEY": "<FRAMEDASH_API_KEY>"
      }
    }
  }
}
```

## Tools

- `query`: Executes a SELECT-only SQL analytics query.
- `get_dashboard`: Project KPI summary including DAU, MAU, sessions and events.
- `get_retention`: Cohort retention data.
- `get_funnel`: Funnel analysis for event steps.
- `get_insights`: Event insights with grouping.
- `get_heatmap`: Heatmap grid data for a map.
- `list_projects`: Shows the project bound to the API key.
- `get_project_status`: Project health overview.
- `list_maps`: Lists maps in a project.
- `list_content`: Lists content registry entries.
- `list_alerts`: Lists alert rules.
- `get_alert_history`: Alert trigger history.

## FAQ

### Is it read-only?

Yes. All 12 tools only read data.

### What API key do I need?

One with analytics:read; the raw query tool also needs data:admin.

### Which engines does Framedash support?

Unity 2022.3+, Unreal Engine 5.3+ and Godot 4.3+ (C#).

### What licence is the server?

MIT.

### Is Framedash MCP Server free?

Framedash MCP Server has a free plan, with paid plans for more usage or features.

### How do I add Framedash MCP Server to Claude Code?

Run this command in your terminal: claude mcp add framedash-mcp-server --env FRAMEDASH_API_KEY='<FRAMEDASH_API_KEY>' -- npx -y @framedash/mcp-server

### What are the best alternatives to Framedash MCP Server?

The closest alternatives to Framedash MCP Server are Agent-Native Analytics, Google Ads + Meta Ads + SEO/GEO MCP, Tapetide - Indian Stock Market MCP, World Monitor and CompanyData.

## Alternatives

- [Agent-Native Analytics](https://ai-powered.com/mcp/agent-native-analytics): Agent-Native Analytics is an open-source MCP server for analytics and data.
- [Google Ads + Meta Ads + SEO/GEO MCP](https://ai-powered.com/mcp/google-ads-meta-ads-seo-geo-mcp): Google Ads + Meta Ads + SEO/GEO MCP is a freemium MCP server for marketing and seo.
- [Tapetide - Indian Stock Market MCP](https://ai-powered.com/mcp/tapetide-indian-stock-market-mcp): Tapetide - Indian Stock Market MCP is a freemium MCP server for finance and payments.
- [World Monitor](https://ai-powered.com/mcp/world-monitor): World Monitor is a freemium MCP server for analytics and data.
- [CompanyData](https://ai-powered.com/mcp/companydata): CompanyData is a paid MCP server for analytics and data.
- [AvatarSay — Fictional Character & Talking Video MCP](https://ai-powered.com/mcp/avatarsay-fictional-character-and-talking-video-mcp): AvatarSay — Fictional Character & Talking Video MCP is a freemium MCP server for design and media.
- [ChartAnt](https://ai-powered.com/mcp/chartant): ChartAnt is a freemium MCP server for design and media.
- [VfxSmith](https://ai-powered.com/mcp/vfxsmith): VfxSmith is a freemium MCP server for design and media.

---
Source: https://ai-powered.com/mcp/framedash-mcp-server
