How do I use DataProbe MCP?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. 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

by lck-001

Overview Schema Source Related Servers Discussions Admin

JavaScript

Hybrid

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_TOKEN
DATAPROBE_USERNAME and DATAPROBE_PASSWORD

Optional:

DATAPROBE_BASE_URL, default: http://10.0.12.186:8080
DATAPROBE_DATASET_ID, default dataset id used by query tools
DATAPROBE_REFRESH_TOKEN
DATAPROBE_TIMEOUT_MS, default: 120000
DATAPROBE_MCP_DEBUG_LOG, default: ./dataprobe-mcp-debug.log
DATAPROBE_MCP_TRANSPORT, set to http for remote service mode
DATAPROBE_MCP_HOST, default: 0.0.0.0
DATAPROBE_MCP_PORT, default: 3000
DATAPROBE_MCP_PATH, default: /mcp

Compatible Ontology variable names are also supported:

ONTOLOGY_API_URL
ONTOLOGY_DATASET_ID
ONTOLOGY_PAT
ONTOLOGY_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-mcp

Install Node.js if needed:

node -v

For Ubuntu/Debian:

curl -fsSL https://deb.nodesource.com/setup_20.x | sudo -E bash -
sudo apt-get install -y nodejs

Create 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/.env

Create 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
EOF

Start it:

sudo systemctl daemon-reload
sudo systemctl enable --now dataprobe-mcp
sudo systemctl status dataprobe-mcp

Test on the server:

curl http://127.0.0.1:3000/health

Test 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/tcp

Codex Client Configuration

Each user can add this to their Codex config file.

Windows:

C:\Users\<username>\.codex\config.toml

macOS/Linux:

~/.codex/config.toml

Config:

[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 tools

dataprobe_askA

Ask a natural-language data question and poll until the DataProbe answer is finished.

ParametersJSON Schema

Name	Required	Description
`query`	Yes	Natural-language data question.
`history`	No	Optional previous Q&A context: [{ question, summary, sql }].
`max_polls`	No	Maximum polling attempts. Default 120.
`dataset_id`	No	Optional DataProbe dataset id.
`poll_interval_ms`	No	Polling interval in milliseconds. Default 1500.

TDQS

A3.9/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses a key behavioral trait (polling until the answer is finished), which adds value beyond the schema. However, it omits details about return values, error handling, side effects, or safety, leaving significant behavioral aspects undisclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, front-loaded with the action ('Ask a natural-language data question') and the polling behavior. No redundant words or information; it is appropriately concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema and a polling-centric tool, the description fails to explain what the tool returns after polling finishes (e.g., the answer itself or a status). It also does not address potential timeouts or failure modes. This is adequate for basic invocation but has clear gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, with all parameters described in the input schema (e.g., query, history, max_polls, dataset_id, poll_interval_ms). The description adds no additional parameter-level detail, so the baseline score of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description uses a specific verb 'Ask' and resource 'natural-language data question', and clearly indicates a polling behavior ('poll until the DataProbe answer is finished'). This distinguishes it from sibling tools like dataprobe_get_ask_result, making its purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly conveys when to use this tool: to ask a natural-language question and wait for completion via polling. It does not explicitly mention alternatives or when-not-to-use, but the context is strong enough given sibling names and the stated polling behavior.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

dataprobe_get_ask_resultA

Get a DataProbe ask result by query id.

ParametersJSON Schema

Name	Required	Description	Default
`query_id`	Yes

TDQS

A3.5/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It only says 'Get', implying a read operation, but fails to describe behavior on invalid or nonexistent query ids, whether results are immediately available or may require polling, or any error handling. The description is too sparse for a tool with zero annotation support.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no redundant content. Every word contributes to the core meaning, making it efficient and easy to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple one-parameter retrieval tool, the description is adequate but incomplete. It fails to explain the prerequisite that a query_id must first be obtained from dataprobe_ask, and with no output schema, it does not hint at what the returned result contains. The description covers the basic action but lacks integration context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description mentions 'by query id', which provides context that the parameter identifies the ask result, but it does not explain where the id comes from (e.g., from a dataprobe_ask response) or its expected format. With schema coverage at 0%, the description adds minimal value beyond the parameter name itself.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Get') and identifies the resource ('DataProbe ask result') and the key qualifier ('by query id'). This clearly distinguishes it from sibling tools like dataprobe_ask (submission) and dataprobe_query_sql (SQL query).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'by query id' implies the tool should be used after an ask is submitted via dataprobe_ask, but this prerequisite is not explicitly stated. No alternative tools are mentioned, nor are any exclusions given. Basic context is present but not fully articulated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

dataprobe_healthA

Check DataProbe service health. Requires DATAPROBE_ACCESS_TOKEN or DATAPROBE_USERNAME/DATAPROBE_PASSWORD.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

A4.1/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The disclosure of required credentials (DATAPROBE_ACCESS_TOKEN or username/password) adds operational context. However, it does not describe the response format, whether the call is read-only, or what indicates healthy vs unhealthy status, which would be useful given no annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with no redundancy. It conveys the core action and a key requirement efficiently.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple health check, the description covers purpose and auth, but since there is no output schema, it should ideally mention what the tool returns. This is a noticeable gap that prevents full completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are no parameters, so the description is not expected to document any. The baseline for 0 params is 4, and the description doesn't introduce any parameter-related ambiguity.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb 'Check' and a clear resource 'DataProbe service health', making the tool's purpose unambiguous. It also differentiates from sibling tools that handle datasets, questions, and SQL queries.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool is used to verify service health and states authentication prerequisites. However, it does not explicitly discuss when to use this over alternatives, though the distinction is fairly obvious from the name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

dataprobe_list_datasetsB

List available DataProbe datasets.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

B3.4/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It accurately conveys a read-only listing behavior via the word 'List', but it does not disclose whether the operation is expensive, requires authentication, or what the return format looks like. This is a minimal but non-misleading disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single focused sentence with no redundant words. It earns its place and is optimally concise for a simple list operation.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (0 params, no output schema), the description is adequate but incomplete. It does not explain the structure of the returned dataset list or any potential filtering options, so the agent has limited context about what the result will contain.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters and an empty input schema, so the baseline is 4. The description does not need to explain parameter semantics, as there are none to explain.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a verb ('List') and resource ('available DataProbe datasets'), which distinguishes it from sibling tools like dataprobe_health and dataprobe_ask. However, it lacks any scope or detail about what a dataset is, so it is not a full 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. It simply states the function without mentioning prerequisites, exclusions, or context, leaving the agent to infer usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

dataprobe_query_sqlC

Execute a read SQL query through DataProbe.

ParametersJSON Schema

Name	Required	Description
`sql`	Yes
`limit`	No	Maximum rows. Default 500.
`dataset_id`	No

TDQS

C2.8/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure. It does state 'read' indicating a non-mutating operation, but it does not disclose return format, pagination behavior, side effects, or authorization requirements. The description is too sparse to provide meaningful behavioral transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that is easy to parse. It avoids fluff and gets straight to the point. However, it is somewhat under-specified for the tool's complexity, which slightly lowers the score from a 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has 3 parameters, no output schema, and no annotations. The description only states the basic action, omitting critical context such as what the result looks like, whether a dataset_id is required, and how the limit applies. This is insufficient for an AI agent to fully understand the tool's behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has only 33% coverage (limit's description), and the description adds no parameter information. It does not explain what 'sql' should contain, how 'dataset_id' is used, or the meaning of 'limit' beyond schema. With low schema coverage and no description compensation, parameter semantics are effectively absent.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: 'Execute a read SQL query through DataProbe.' It has a specific verb ('execute'), a clear resource ('SQL query'), and a scope ('read'), which distinguishes it from siblings like dataprobe_ask (which likely handles natural language) and dataprobe_health/list_datasets.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. It does not mention any prerequisites, exclusions, or compare itself to sibling tools like dataprobe_ask. The only implicit clue is 'SQL query', but there is no explicit context for choosing it over other DataProbe tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

5 tool updatesv0.1.0Jul 31, 2026
- First observeddataprobe_ask
- First observeddataprobe_get_ask_result
- First observeddataprobe_health
- First observeddataprobe_list_datasets
- First observeddataprobe_query_sql

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.5/5.0

Scored 2026-07-31 18:45 across 5 tools

Disambiguation4/5

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.

Naming Consistency4/5

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.

Tool Count5/5

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.

Completeness4/5

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.

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

mcpOAuth
io.prisma
MCP server for managing Prisma Postgres.
Databases Developer Tools
247
The Quiet Protocol Growth Offense MCP A
com.thequietprotocol.www
Read-only MCP server for The Quiet Protocol's engines, benchmarks, proof, and business data.
Databases Research & Data Finance
292
QuLab Infinite MCP Server
io.github.Workofarttattoo
QuLab MCP remote server (Streamable HTTP) for computational science and lab tools.
Research & Data Command Line Code Execution
2
ChromaDB Remote MCP Server
io.github.meloncafe
Remote ChromaDB vector database MCP server with streamable HTTP transport
Vector Databases RAG Systems Databases
212

Related MCP Servers

sql-explorer-mcp
Databases Search
govern-agents
A
license
Not graded
quality
F
maintenance
Read-only MCP server for SQL databases (SQL Server, Postgres, SQLite) with multi-server support and three-layer safety using AST validation and linting.
Updated a month ago (2026-07-29 13:07 UTC)
MIT
Copilot SQL MCP POC
Databases Data Visualization
PhilFer1973
F
license
Not graded
quality
D
maintenance
Enables answering business questions over local SQL Server WideWorldImporters data through MCP, with support for both STDIO and Streamable HTTP endpoints.
Updated 3 months ago (2026-06-19 13:29 UTC)
-
paycoreDb
Databases Developer Tools
MaxenceBdu
F
license
Not graded
quality
C
maintenance
Custom MCP server connected to a read-only SQLite database, exposing a schema resource and a query tool for safe data retrieval.
Updated 2 months ago (2026-06-30 14:47 UTC)
-
Zaia
Databases Search
prithivrajmu
A
license
Not graded
quality
B
maintenance
MCP server that exposes SQLite datasets as queryable tools and resources via Streamable HTTP, enabling read-only exploration and SQL queries.
Updated 2 months ago (2026-07-15 11:02 UTC)
Apache 2.0