
AVA
Load data, inspect schemas, run SQL, analyze datasets, and build charts with AVA via MCP.
- tools
- 8
- transport
- STDIO
- last updated
- Nov 13, 2026
Tools
8 toolsPublic tool metadata for what this MCP can expose to an agent.
ava_load_dataLoad inline CSV/JSON/text or a file path (.csv, .json, .parquet, .xlsx). Replaces the current dataset and returns the schema.
Load inline CSV/JSON/text or a file path (.csv, .json, .parquet, .xlsx). Replaces the current dataset and returns the schema.
No parameter schema in public metadata yet.
ava_schemaTable names, columns, and types.
Table names, columns, and types.
No parameter schema in public metadata yet.
ava_profileRow count, nulls, distinct, min/max/mean/median per column.
Row count, nulls, distinct, min/max/mean/median per column.
No parameter schema in public metadata yet.
ava_queryOne read-only SQL statement with DuckDB semantics; results capped at AVA_MCP_MAX_ROWS.
One read-only SQL statement with DuckDB semantics; results capped at AVA_MCP_MAX_ROWS.
No parameter schema in public metadata yet.
ava_analyzeNatural-language question → AVA writes SQL, executes it, and summarizes the answer.
Natural-language question → AVA writes SQL, executes it, and summarizes the answer.
No parameter schema in public metadata yet.
ava_translateNatural-language question → SQL, without executing it, so a human can review it.
Natural-language question → SQL, without executing it, so a human can review it.
No parameter schema in public metadata yet.
ava_suggestSuggest questions worth asking about the loaded dataset.
Suggest questions worth asking about the loaded dataset.
No parameter schema in public metadata yet.
ava_visualizeRecommend a chart for rows from a previous call; returns GPT-Vis JSON.
Recommend a chart for rows from a previous call; returns GPT-Vis JSON.
No parameter schema in public metadata yet.
Sponsors
Readme
mcp-server-ava
Model Context Protocol server for AVA. Load a dataset, inspect it, run SQL, ask questions in natural language, and get charts — from Claude Desktop, Cursor, ChatGPT, or any other MCP client.
AVA does the data access, SQL execution, and chart specs; your MCP client's own agent does the reasoning. No AVA CLI or extra API key is needed for deterministic work.
Install
npm install -g mcp-server-ava @antv/ava
@antv/ava v4 is a peer dependency — install it alongside. Without installing globally: npx -y -p mcp-server-ava -p @antv/ava mcp-server-ava.
Requires Node.js ≥ 22.13.
Client configuration
Add the server to your MCP client config. The env block is only needed for the model-backed tools (ava_analyze, ava_translate, ava_suggest, ava_visualize).
Claude Desktop (claude_desktop_config.json) / Cursor (~/.cursor/mcp.json) / most clients:
Details
- Repository
- github.com/doublecore/mcp-server-ava
- Categories
- Databases, Data & Analytics
- Package
mcp-server-ava- Transport
- STDIO
- Registry
- MCP registry, active