Yes. The InfluxDB 3 MCP server is open source under a dual Apache-2.0 / MIT license and free to run; you pay only for the InfluxDB 3 instance or InfluxDB Cloud service it connects to.

Does it support remote/OAuth?

It runs as a local stdio server (via npx or Docker) and authenticates with an InfluxDB token, not a hosted OAuth login. Point it at a remote InfluxDB Cloud instance by setting the instance URL and token.

Which InfluxDB versions does it support?

It targets the InfluxDB 3 family — Core, Enterprise, Cloud Serverless, Cloud Dedicated, and Clustered — selected via INFLUX_DB_PRODUCT_TYPE, which also controls which administration tools are exposed.

InfluxDB MCP server

OfficialInfluxData32Config last verified Jun 1, 2026

InfluxData's official MCP server lets an agent write, query, and manage time-series data in InfluxDB 3 using SQL and line protocol.

The InfluxDB 3 MCP Server is the official server from InfluxData for the InfluxDB 3 family — Core, Enterprise, Cloud Serverless, Cloud Dedicated, and Clustered. It gives an AI agent end-to-end access to a time-series database: list and create databases, discover the measurements (tables) inside them and their schemas, write points with line protocol, and run SQL queries against the data with execute_query. A load_database_context tool lets you feed the agent custom documentation about your schema so it asks better questions, and get_help surfaces troubleshooting guidance.

Beyond data, it covers token administration: for Core and Enterprise it creates and lists admin and resource tokens, deletes tokens, and regenerates the operator token, while for Cloud Dedicated and Clustered it manages database tokens through the cloud_* tools. It runs over stdio and launches with npx (or a Docker image), authenticating with INFLUX_DB_TOKEN against the instance named by INFLUX_DB_INSTANCE_URL, with INFLUX_DB_PRODUCT_TYPE selecting which deployment's behavior and tools apply. This makes it a complete bridge for letting an agent explore metrics, IoT, and observability data in plain language.

Quick install

Copy-paste configs are provided for all 8 supported clients. Pick your client below.

Add to ~/.claude.json

~/.claude.json

json

{
  "mcpServers": {
    "influxdb": {
      "command": "npx",
      "args": [
        "-y",
        "@influxdata/influxdb3-mcp-server"
      ],
      "env": {
        "INFLUX_DB_INSTANCE_URL": "<INFLUX_DB_INSTANCE_URL>",
        "INFLUX_DB_TOKEN": "<INFLUX_DB_TOKEN>",
        "INFLUX_DB_PRODUCT_TYPE": "<INFLUX_DB_PRODUCT_TYPE>"
      }
    }
  }
}

Or via CLI

bash

claude mcp add influxdb -- npx -y @influxdata/influxdb3-mcp-server

Step-by-step guides

Available tools

Tool	Description
load_database_context	Load custom database context and documentation so the agent understands your schema.
get_help	Get help and troubleshooting guidance for using the server.
write_line_protocol	Write data points to a database using InfluxDB line protocol.
create_database	Create a new database.
update_database	Update the configuration of an existing database.
delete_database	Delete a database by name.
execute_query	Run a SQL query against a database.
get_measurements	List all measurements (tables) in a database.
get_measurement_schema	Get the schema for a specific measurement.
create_admin_token	Create an admin token (Core/Enterprise).
list_admin_tokens	List admin tokens (Core/Enterprise).
create_resource_token	Create a resource token scoped to specific databases (Core/Enterprise).
list_resource_tokens	List resource tokens (Core/Enterprise).
delete_token	Delete a token by name (Core/Enterprise).
regenerate_operator_token	Regenerate the operator token (Core/Enterprise).
cloud_list_database_tokens	List database tokens (Cloud Dedicated/Clustered).
cloud_get_database_token	Get details for a specific database token (Cloud Dedicated/Clustered).
cloud_create_database_token	Create a database token (Cloud Dedicated/Clustered).
cloud_update_database_token	Update a database token (Cloud Dedicated/Clustered).
cloud_delete_database_token	Delete a database token (Cloud Dedicated/Clustered).
list_databases	List all available databases.
health_check	Check the connection and health status of the InfluxDB instance.

Required configuration

INFLUX_DB_INSTANCE_URLRequired
URL of your InfluxDB 3 instance (Core, Enterprise, Cloud Serverless, Clustered).
INFLUX_DB_TOKENRequired
Authentication token for query and write operations.
INFLUX_DB_PRODUCT_TYPERequired
Deployment type: core, enterprise, cloud-serverless, cloud-dedicated, or clustered.
INFLUX_DB_CLUSTER_IDOptional
Cluster ID for Cloud Dedicated / Clustered deployments (alternative to instance URL).
INFLUX_DB_MANAGEMENT_TOKENOptional
Management token for token administration on Cloud Dedicated / Clustered.
INFLUX_DB_ACCOUNT_IDOptional
Account ID for Cloud Dedicated management operations.

What you can do with it

Ask questions of time-series data

The agent lists measurements, reads their schemas, and runs SQL with execute_query to answer questions about metrics, IoT readings, or events without you writing the query.

Write and manage data and tokens

Beyond reads, the agent can ingest points with line protocol, create databases, and provision scoped resource tokens, automating setup and ingestion workflows.

FAQ

Is it free?: Yes. The InfluxDB 3 MCP server is open source under a dual Apache-2.0 / MIT license and free to run; you pay only for the InfluxDB 3 instance or InfluxDB Cloud service it connects to.
Does it support remote/OAuth?: It runs as a local stdio server (via npx or Docker) and authenticates with an InfluxDB token, not a hosted OAuth login. Point it at a remote InfluxDB Cloud instance by setting the instance URL and token.
Which InfluxDB versions does it support?: It targets the InfluxDB 3 family — Core, Enterprise, Cloud Serverless, Cloud Dedicated, and Clustered — selected via INFLUX_DB_PRODUCT_TYPE, which also controls which administration tools are exposed.

← Browse all databases servers