IoTDB MCP Server
OfficialIoTDB MCP-Server
Überblick
Eine Model Context Protocol (MCP)-Serverimplementierung, die Datenbankinteraktion und Business Intelligence-Funktionen über IoTDB ermöglicht. Dieser Server ermöglicht die Ausführung von SQL-Abfragen.
Related MCP server: XiYan MCP Server
Komponenten
Ressourcen
Der Server stellt keine Ressourcen bereit.
Eingabeaufforderungen
Der Server gibt keine Eingabeaufforderungen aus.
Werkzeuge
Der Server bietet verschiedene Tools für das IoTDB-Baummodell und das Tabellenmodell. Sie können zwischen diesen wählen, indem Sie die Konfiguration "IOTDB_SQL_DIALECT" auf "Baum" oder "Tabelle" setzen.
Baummodell
metadata_queryFühren Sie SHOW/COUNT-Abfragen aus, um Metadaten aus der Datenbank zu lesen
Eingang:
query_sql(Zeichenfolge): Die auszuführende SHOW/COUNT-SQL-Abfrage
Gibt zurück: Abfrageergebnisse als Array von Objekten
select_queryFühren Sie SELECT-Abfragen aus, um Daten aus der Datenbank zu lesen
Eingang:
query_sql(Zeichenfolge): Die auszuführende SELECT-SQL-Abfrage
Gibt zurück: Abfrageergebnisse als Array von Objekten
Tabellenmodell
Abfragetools
read_queryFühren Sie SELECT-Abfragen aus, um Daten aus der Datenbank zu lesen
Eingang:
query(Zeichenfolge): Die auszuführende SELECT-SQL-Abfrage
Gibt zurück: Abfrageergebnisse als Array von Objekten
Schema-Tools
list_tablesHolen Sie sich eine Liste aller Tabellen in der Datenbank
Keine Eingabe erforderlich
Rückgabe: Array von Tabellennamen
describe-tableSchemainformationen für eine bestimmte Tabelle anzeigen
Eingang:
table_name(Zeichenfolge): Name der zu beschreibenden Tabelle
Rückgabe: Array von Spaltendefinitionen mit Namen und Typen
Claude Desktop Integration
Voraussetzungen
Python mit
uv-PaketmanagerIoTDB-Installation
MCP-Serverabhängigkeiten
Entwicklung
# Clone the repository
git clone https://github.com/apache/iotdb-mcp-server.git
cd iotdb_mcp_server
# Create virtual environment
uv venv
source venv/bin/activate # or `venv\Scripts\activate` on Windows
# Install development dependencies
uv syncKonfigurieren Sie den MCP-Server in der Konfigurationsdatei von Claude Desktop:
macOS
Speicherort: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows
Speicherort: %APPDATA%/Claude/claude_desktop_config.json
Möglicherweise müssen Sie den vollständigen Pfad zur UV-Programmdatei in das Befehlsfeld eingeben. Sie erhalten diesen, indem Sie which uv unter MacOS/Linux oder where uv unter Windows ausführen.
{
"mcpServers": {
"iotdb": {
"command": "uv",
"args": [
"--directory",
"YOUR_REPO_PATH/src/iotdb_mcp_server",
"run",
"server.py"
],
"env": {
"IOTDB_HOST": "127.0.0.1",
"IOTDB_PORT": "6667",
"IOTDB_USER": "root",
"IOTDB_PASSWORD": "root",
"IOTDB_DATABASE": "test",
"IOTDB_SQL_DIALECT": "table"
}
}
}
}Available Tools
4 toolsdescribe_tableC
Get the schema information for a specific table Args: table_name: name of the table to describe
Inputs: table_name (required).
export_table_queryA
Execute a query and export the results to a CSV or Excel file.
Args: query_sql: The SQL query to execute (using TABLE dialect, time using ISO 8601 format, e.g. 2017-11-01T00:08:00.000) format: Export format, either "csv" or "excel" (default: "csv") filename: Optional filename for the exported file. If not provided, a unique filename will be generated.
SQL Syntax: SELECT ⟨select_list⟩ FROM ⟨tables⟩ [WHERE ⟨condition⟩] [GROUP BY ⟨groups⟩] [HAVING ⟨group_filter⟩] [FILL ⟨fill_methods⟩] [ORDER BY ⟨order_expression⟩] [OFFSET ⟨n⟩] [LIMIT ⟨n⟩];
Returns: Information about the exported file and a preview of the data (max 10 rows)
Inputs: query_sql (required), format, filename.
list_tablesB
List all tables in the IoTDB database.
Inputs: no named parameters.
read_queryB
Execute a SELECT query on the IoTDB. Please use table sql_dialect when generating SQL queries.
Args: query_sql: The SQL query to execute (using TABLE dialect, time using ISO 8601 format, e.g. 2017-11-01T00:08:00.000)
Inputs: query_sql (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
The tools have distinct primary functions (describe, export, list, read), but there's significant overlap between export_table_query and read_query as both execute SQL queries. The descriptions clarify that export_table_query focuses on file export while read_query returns query results directly, but an agent might still confuse when to use each for data retrieval.
Three tools follow a consistent verb_noun pattern (describe_table, list_tables, export_table_query), while read_query deviates slightly by using 'read' instead of a more specific verb like 'execute' or 'run'. The naming is mostly predictable and readable, with only minor inconsistency in the verb choice for one tool.
Four tools is a reasonable count for a database server, allowing core operations without being overwhelming. However, it feels slightly thin for full IoTDB coverage, as it lacks tools for table creation, deletion, or data insertion, which might be expected in a complete database interface.
The toolset is severely incomplete for a database server. It covers read operations (list, describe, query) and export, but lacks any write capabilities (create, insert, update, delete) or administrative functions. This creates significant gaps that will cause agent failures when trying to perform basic database management tasks.
Maintenance
Related MCP Connectors
The BigQuery remote MCP server is a fully managed service that uses the Model Context Protocol to connect AI applications and LLMs to BigQuery data sources. It provides secure, standardized tools for AI agents to list datasets and tables, retrieve schemas, generate and execute SQL queries through natural language, and analyze data—enabling direct access to enterprise analytics data without requiring manual SQL coding.
Text-to-SQL MCP server: read-only queries on PostgreSQL, MySQL and SQL Server with your real schema
The Grafbase MCP server sits in front of a GraphQL API and exposes an MCP protocol-compliant interface that allows AI agents and LLMs to explore and query GraphQL APIs using natural language. It provides tools to search schemas, introspect types and fields, and execute GraphQL queries while minimizing context bloat by returning only relevant schema subsets, with built-in support for authentication, authorization, and configurable access control.
Draxlr's remote MCP server connects AI assistants to your SQL databases and dashboards. Explore schemas, run read-only queries, manage saved queries and dashboards, and export results, all with row-level security so each user sees only their own data.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that enables SQL query execution, database management, and business intelligence capabilities through MySQL connections.1,462 npmMIT
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that enables natural language queries to MySQL databases, powered by XiYanSQL text-to-SQL technology.239Apache 2.0
- AlicenseBqualityDmaintenanceA Model Context Protocol server that enables executing SQL queries and managing connections with Microsoft SQL Server databases.16MIT
- FlicenseBqualityDmaintenanceA Model Context Protocol server that allows executing SELECT queries on TiDB databases, with optional support for INSERT, UPDATE, and DELETE operations when explicitly enabled.18 npm-