Create interactive visualizations and query data sources (SQLite, CSV, Parquet, JSON)
Create interactive visualizations and query data sources (SQLite, CSV, Parquet, JSON). Exposed over MCP by the chart mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.
Create beautiful charts, diagrams, and tables directly from your AI conversations. Chart Canvas provides a real-time dashboard that displays visualizations as you work with LLMs like Claude.
The server ships on npm as @gluip/chart-canvas-mcp, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
Everything the assistant can do here goes through one of these:
Installation — The Installation tool exposed by this serverConfiguration — Add to your MCP client configuration (e.g., Claude Desktop):Usage — 1. Start your MCP client (e.g., Claude Desktop) 2. The server will automatically start on port 3000 3. Use the showCanvas tool to open the dashboardaddVisualization — The addVisualization tool exposed by this serverremoveVisualization — The removeVisualization tool exposed by this serverclearCanvas — The clearCanvas tool exposed by this servershowCanvas — The showCanvas tool exposed by this servergetDatabaseSchema — Inspect the structure of a SQLite database to understand available tables and columns before writing queriesqueryAndVisualize — Execute a SQL query on a SQLite database and create a visualization from the results. Queries are executed server-side and must be read-only (SELECTThis sits in the database access group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Chart's toolset — Installation, Configuration, Usage and 6 more — is a fair guide to whether it matches your workflow. It is maintained by gluip; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| Installation | The Installation tool exposed by this server. |
| Configuration | Add to your MCP client configuration (e.g., Claude Desktop): |
| Usage | 1. Start your MCP client (e.g., Claude Desktop) 2. The server will automatically start on port 3000 3. Use the showCanvas tool to open the dashboard in your browser 4. Ask the AI to create visualizations! |
| addVisualization | The addVisualization tool exposed by this server. |
| removeVisualization | The removeVisualization tool exposed by this server. |
| clearCanvas | The clearCanvas tool exposed by this server. |
| showCanvas | The showCanvas tool exposed by this server. |
| getDatabaseSchema | Inspect the structure of a SQLite database to understand available tables and columns before writing queries. |
| queryAndVisualize | Execute a SQL query on a SQLite database and create a visualization from the results. Queries are executed server-side and must be read-only (SELECT only). Maximum 10,000 rows. |
{
"mcpServers": {
"chart-canvas": {
"command": "npx",
"args": ["-y", "@gluip/chart-canvas-mcp"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
Read-only SQL access to Postgres — let your assistant inspect schemas and answer questions from real data.
Manage your whole Supabase project in conversation — database, auth, storage, Edge Functions and branches.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Official MongoDB server covering data, schemas and Atlas management — from find queries to spinning up clusters.
Serverless Postgres with database branching — point your assistant at Neon and let it work on disposable copies.