Overlook
Allows dashboards to be built from DuckDB databases, using DuckDB as a local data source for KPIs, charts, and tables.
Provides experimental support for connecting to MySQL databases as a dashboard data source, configured through environment variables.
Allows dashboards to be built from SQLite databases, reading data in place as a supported data source.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Install
You need Node.js 22 or later. Then run one command:
npx overlook-dash setupIt finds the AI agents on your computer and adds Overlook to each one. Restart your agent and you're done.
/plugin install overlook --marketplace furkancodes/overlookThis also adds a /overlook:dashboard command. Use the plugin or setup, not
both.
Overlook is a standard MCP server. Point any MCP client at:
npx -y overlook-dash mcpFor example, in Cursor (~/.cursor/mcp.json):
{ "mcpServers": { "overlook": { "command": "npx", "args": ["-y", "overlook-dash", "mcp"] } } }npx overlook-dash setup --print shows the exact entry for every supported
agent.
Works with:
Claude Code, Claude Desktop, Codex, Cursor, Windsurf, Gemini CLI, VS Code (Copilot), OpenCode, Cline and Zed;
any other MCP client;
any agent that can run a shell command, through
overlook auto.
Related MCP server: Nightingale's Hoard
Use it
Open your agent in any project that has data, and say:
make a dashboard of my data
Overlook finds the data, builds a dashboard, checks every number, and opens it in your browser. Then keep talking to it:
You say | What happens |
make a dashboard of my data | A full overview: KPIs with trends, a trend chart, breakdowns and a summary table |
show monthly revenue by region from sales.csv | Exactly the charts you asked for |
add a filter for country | The open page updates by itself |
turn the bar chart into a table | Change any panel in plain words |
what dashboards do I have? | Every saved dashboard with its link |
No MCP in your agent? Run this in the project folder instead:
npx overlook-dash autoFeatures
β¨ One sentence, whole dashboard. No config files, no spec writing. Even small models manage it in one step.
π Any agent, any model. Claude, GPT, Gemini, Qwen, Llama, or anything else that can call tools.
ποΈ Any data.
CSV, Parquet, JSON, SQLite and DuckDB.
Postgres and MySQL from your
.env(experimental).Your agent finds the data in the project for you.
β Checked before you see it. Every query runs before a dashboard is saved. Mistakes go back to the model as a numbered list of fixes.
π Every number shows its source. One click shows the SQL behind any chart, and the data under it as a table.
π Real dashboard features.
KPI tiles with trends and comparisons.
Line, area, bar, scatter and table panels.
Filters, hover tooltips and CSV export.
π Looks good everywhere. Light and dark themes, color-blind-safe charts, and phone layouts.
π Private by design.
Your data is read in place, read-only.
The page is served from
127.0.0.1only.Nothing is uploaded and no CDN is used.
Your data
Inside a project, there is nothing to add. Your agent finds the data files and
.env database URLs there itself, and most agents ask you before adding one.
For data anywhere else:
npx overlook-dash source add sales ~/Downloads/sales.csvData | Example |
CSV, TSV, Parquet, JSON (or a glob) |
|
SQLite, DuckDB |
|
Postgres, MySQL (experimental) |
|
Commands
Command | What it does |
| Add Overlook to your agents |
| Build a dashboard from the data and open it |
| Add data from anywhere |
| Open a saved dashboard |
| Check that everything works |
| Stop the dashboard server |
Run commands with npx overlook-dash <command>, or install it once with
npm i -g overlook-dash and use overlook <command>.
Questions
No. Overlook reads your files where they are and serves the dashboard from your
own machine. Your AI model sees only what the tools return to it: column names,
a few sample rows, and query results. Run with OVERLOOK_SAMPLES=0 to leave
out sample rows.
Your agent still prints the link, usually http://127.0.0.1:4777/d/<name>.
Overlook doesn't open a browser in CI, over SSH, or with OVERLOOK_OPEN=0.
The dashboard server stopped (for example after a restart). Run
npx overlook-dash open <name>, which restarts the server and opens the
dashboard.
Set another port with OVERLOOK_PORT=4800, or put "port": 4800 in
~/.overlook/config.json.
You have both the plugin and the setup entry. Remove one with
claude mcp remove overlook, or uninstall the plugin.
Run npx overlook-dash doctor. It checks Node, your data sources and the
server. Then open an issue
with its output.
Learn more
Guide: every agent, data source, tool and setting, the dashboard spec, and the security model.
Changelog: what's in each release, and what's experimental.
Security: how to report a vulnerability.
Design: why Overlook works the way it does.
Contributing
git clone https://github.com/furkancodes/overlook && cd overlooknpm installnpm testIssues and pull requests are welcome. The guide covers the demo, the benchmarks and the model eval.
License
MIT. Bundled third-party components are listed in THIRD_PARTY_NOTICES.md. Overlook is an independent project and is not affiliated with Anthropic or any model provider.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
This server cannot be deployed
Maintenance
Related MCP Connectors
Charts and dashboards as images for AI agents. No browser, same data same bytes. Local and free.
The all-in-one data stack for agents. Upload files, run SQL, evolve tables, and render charts.
Interactive data visualization and executive PDF dashboards for ChatGPT, Claude, and Cursor.
Charts and tables for AI agents with live-updating embed links. No account: signup returns a key.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to create interactive charts, diagrams, and tables displayed on a real-time dashboard, supporting multiple data sources with privacy-focused local execution.1MIT
- AlicenseNot gradedqualityBmaintenanceEnables a local assistant to drive a full data workbench: ingest messy files, clean them with versioned and undoable steps, enforce quality rules, build charts and dashboards as code, train quick models, and ask questions of the dataβall on the user's own machine.MIT
- AlicenseBqualityBmaintenanceEnables AI agents to safely describe, query, and compute metrics across SQL databases using open-format semantic models, custom context, and skills, with read-only and dialect-checked execution.184 PyPIApache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to ingest and link datasets, plan and render interactive D3.js visualizations and dashboards, validate and refine outputs, and export standalone HTML, SVG, PNG, PDF, JSON, or CSV artifacts from natural-language requests.MIT