DataProbe MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@DataProbe MCP Show me the average order value per customer."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
DataProbe MCP
A minimal MCP server for DataProbe data question answering and read-only SQL queries.
It supports:
stdio mode for local MCP clients.
Streamable HTTP mode for a long-running remote MCP service.
Tools
dataprobe_health: check DataProbe service health.dataprobe_list_datasets: list available datasets.dataprobe_ask: ask a natural-language data question and poll for the final result.dataprobe_get_ask_result: get an ask result by query id.dataprobe_query_sql: execute a read SQL query through DataProbe.
Related MCP server: Copilot SQL MCP POC
Runtime
Node.js 18 or newer.
No npm dependencies are required.
Environment Variables
Required auth, choose one:
DATAPROBE_ACCESS_TOKENDATAPROBE_USERNAMEandDATAPROBE_PASSWORD
Optional:
DATAPROBE_BASE_URL, default:http://10.0.12.186:8080DATAPROBE_DATASET_ID, default dataset id used by query toolsDATAPROBE_REFRESH_TOKENDATAPROBE_TIMEOUT_MS, default:120000DATAPROBE_MCP_DEBUG_LOG, default:./dataprobe-mcp-debug.logDATAPROBE_MCP_TRANSPORT, set tohttpfor remote service modeDATAPROBE_MCP_HOST, default:0.0.0.0DATAPROBE_MCP_PORT, default:3000DATAPROBE_MCP_PATH, default:/mcp
Compatible Ontology variable names are also supported:
ONTOLOGY_API_URLONTOLOGY_DATASET_IDONTOLOGY_PATONTOLOGY_API_KEY
Remote Server Deployment
Clone the repository on the server:
sudo mkdir -p /opt
sudo chown -R "$USER:$USER" /opt
cd /opt
git clone https://github.com/lck-001/dataprobe-mcp.git
cd /opt/dataprobe-mcpInstall Node.js if needed:
node -vFor Ubuntu/Debian:
curl -fsSL https://deb.nodesource.com/setup_20.x | sudo -E bash -
sudo apt-get install -y nodejsCreate the server environment file:
cat > /opt/dataprobe-mcp/.env <<'EOF'
export DATAPROBE_BASE_URL="http://10.0.12.186:8080"
export DATAPROBE_DATASET_ID="_ontology_a3f60d33_f34f_572b_9377_26aec3ac6eb1"
export DATAPROBE_USERNAME="admin"
export DATAPROBE_PASSWORD="change-me"
export DATAPROBE_TIMEOUT_MS="120000"
export DATAPROBE_MCP_TRANSPORT="http"
export DATAPROBE_MCP_HOST="0.0.0.0"
export DATAPROBE_MCP_PORT="3000"
export DATAPROBE_MCP_PATH="/mcp"
EOF
chmod 600 /opt/dataprobe-mcp/.envCreate a systemd service so the MCP server stays online:
sudo tee /etc/systemd/system/dataprobe-mcp.service >/dev/null <<'EOF'
[Unit]
Description=DataProbe MCP Streamable HTTP Server
After=network-online.target
Wants=network-online.target
[Service]
Type=simple
WorkingDirectory=/opt/dataprobe-mcp
EnvironmentFile=/opt/dataprobe-mcp/.env
ExecStart=/usr/bin/node /opt/dataprobe-mcp/server.mjs
Restart=always
RestartSec=3
User=root
[Install]
WantedBy=multi-user.target
EOFStart it:
sudo systemctl daemon-reload
sudo systemctl enable --now dataprobe-mcp
sudo systemctl status dataprobe-mcpTest on the server:
curl http://127.0.0.1:3000/healthTest the MCP endpoint:
curl -s http://127.0.0.1:3000/mcp \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'If users connect from other machines, open the port or put it behind Nginx:
sudo ufw allow 3000/tcpCodex Client Configuration
Each user can add this to their Codex config file.
Windows:
C:\Users\<username>\.codex\config.tomlmacOS/Linux:
~/.codex/config.tomlConfig:
[mcp_servers.dataprobe]
url = "http://SERVER_IP:3000/mcp"
startup_timeout_sec = 20.0
tool_timeout_sec = 120.0
[mcp_servers.dataprobe.tools.dataprobe_health]
approval_mode = "approve"
[mcp_servers.dataprobe.tools.dataprobe_list_datasets]
approval_mode = "approve"
[mcp_servers.dataprobe.tools.dataprobe_query_sql]
approval_mode = "approve"Restart Codex after updating the config.
For production, prefer HTTPS and a private network, VPN, or reverse proxy allowlist.
Available Tools
5 toolsdataprobe_askA
Ask a natural-language data question and poll until the DataProbe answer is finished.
Inputs: query (required), history, max_polls, dataset_id, +1 more.
dataprobe_get_ask_resultA
Get a DataProbe ask result by query id.
Inputs: query_id (required).
dataprobe_healthA
Check DataProbe service health. Requires DATAPROBE_ACCESS_TOKEN or DATAPROBE_USERNAME/DATAPROBE_PASSWORD.
Inputs: no named parameters.
dataprobe_list_datasetsB
List available DataProbe datasets.
Inputs: no named parameters.
dataprobe_query_sqlC
Execute a read SQL query through DataProbe.
Inputs: sql (required), limit, dataset_id.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Tools are mostly distinct: health, list datasets, submit NL query, retrieve result, and execute SQL. The only slight overlap is between 'dataprobe_ask' and 'dataprobe_get_ask_result', but 'ask' includes polling and 'get_ask_result' is for fetching by ID, so the boundary is clear.
All names share the 'dataprobe_' prefix and use snake_case, which is consistent. However, 'dataprobe_ask' is a bare verb and 'dataprobe_health' is a noun, deviating from the verb_noun pattern seen in list_datasets, get_ask_result, and query_sql.
With 5 tools, the surface is tightly scoped for a data query service. It covers health, dataset discovery, natural-language querying, result retrieval, and SQL execution without unnecessary bloat.
Core workflows are covered: checking health, listing datasets, submitting and retrieving ask results, and running SQL. Minor gaps like a cancel operation or dataset schema access are missing but do not hinder the primary query/retrieve pattern.
Related MCP Connectors
An MCP server for search and retrieval over a local LanceDB database
Text-to-SQL MCP server: read-only queries on PostgreSQL, MySQL and SQL Server with your real schema
Read-only MCP server for The Quiet Protocol's engines, benchmarks, proof, and business data.
MCP server for the Seline Analytics API
Related MCP Servers
- AlicenseNot gradedqualityFmaintenanceRead-only MCP server for SQL databases (SQL Server, Postgres, SQLite) with multi-server support and three-layer safety using AST validation and linting.MIT
- FlicenseNot gradedqualityDmaintenanceEnables answering business questions over local SQL Server WideWorldImporters data through MCP, with support for both STDIO and Streamable HTTP endpoints.-
- FlicenseNot gradedqualityDmaintenanceCustom MCP server connected to a read-only SQLite database, exposing a schema resource and a query tool for safe data retrieval.-
- AlicenseNot gradedqualityDmaintenanceMCP server that exposes SQLite datasets as queryable tools and resources via Streamable HTTP, enabling read-only exploration and SQL queries.Apache 2.0