AWS Labs Timestream for InfluxDB MCP Server

An AWS Labs Model Context Protocol (MCP) server for Timestream for InfluxDB. This server provides tools to interact with AWS Timestream for InfluxDB APIs, allowing you to create and manage database instances, clusters, parameter groups, and more. It also includes tools to interact with InfluxDB's write and query APIs.

Features

• Create, update, list, describe, and delete Timestream for InfluxDB database instances
• Create, update, list, describe, and delete Timestream for InfluxDB database clusters
• Manage DB parameter groups
• Tag management for Timestream for InfluxDB resources
• Manage InfluxDB 2 buckets and organizations
• Write and query data using InfluxDB 2 APIs

Pre-requisites

1. Install uv from Astral or the GitHub README
2. Install Python using uv python install 3.10
3. Set up AWS credentials with access to AWS services
   • You need an AWS account with appropriate permissions
   • Configure AWS credentials with aws configure or environment variables
   • Consider starting with Read-only permission if you don't want the LLM to modify any resources

Installation

Kiro	Cursor	VS Code

You can modify the settings of your MCP client to run your local server (e.g. for Kiro, ~/.kiro/settings/mcp.json)

{
  "mcpServers": {
    "awslabs.timestream-for-influxdb-mcp-server": {
      "command": "uvx",
      "args": ["awslabs.timestream-for-influxdb-mcp-server@latest"],
      "env": {
        "AWS_PROFILE": "your-aws-profile",
        "AWS_REGION": "us-east-1",
        "INFLUXDB_URL": "https://your-influxdb-endpoint:8086",
        "INFLUXDB_TOKEN": "your-influxdb-token",
        "INFLUXDB_ORG": "your-influxdb-org",
        "INFLUXDB_WRITE_MODE": "false",
        "ALLOW_WRITE": "false",
        "FASTMCP_LOG_LEVEL": "ERROR"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

Windows Installation

For Windows users, the MCP server configuration format is slightly different:

{
  "mcpServers": {
    "awslabs.timestream-for-influxdb-mcp-server": {
      "disabled": false,
      "timeout": 60,
      "type": "stdio",
      "command": "uv",
      "args": [
        "tool",
        "run",
        "--from",
        "awslabs.timestream-for-influxdb-mcp-server@latest",
        "awslabs.timestream-for-influxdb-mcp-server.exe"
      ],
      "env": {
        "AWS_PROFILE": "your-aws-profile",
        "AWS_REGION": "us-east-1",
        "INFLUXDB_URL": "https://your-influxdb-endpoint:8086",
        "INFLUXDB_TOKEN": "your-influxdb-token",
        "INFLUXDB_ORG": "your-influxdb-org",
        "INFLUXDB_WRITE_MODE": "false",
        "ALLOW_WRITE": "false",
        "FASTMCP_LOG_LEVEL": "ERROR"
      }
    }
  }
}

InfluxDB Connection Security

InfluxDB tools use the INFLUXDB_URL, INFLUXDB_TOKEN, and INFLUXDB_ORG environment variables when no connection parameters are supplied in a tool call.

Connection parameters are treated as a single trust boundary:

• If a tool call supplies any connection parameter, it must supply all parameters required by that tool. Server environment credentials are never used to complete a partial caller-supplied configuration.
• A caller-supplied URL must match INFLUXDB_URL or an entry in the optional, comma-separated INFLUXDB_ALLOWED_URLS environment variable.
• Configure additional endpoints before allowing tool calls to target them. For example, set INFLUXDB_ALLOWED_URLS to https://influxdb-a.example.com:8086,https://influxdb-b.example.com:8086.

This is a breaking change for clients that previously supplied only some connection parameters and relied on environment-variable fallback for the others. Update those clients to either omit all connection parameters or provide a complete configuration for an operator-approved URL.

Available Tools

The Timestream for InfluxDB MCP server provides the following tools:

AWS Timestream for InfluxDB Management

Database Cluster Management

• CreateDbCluster: Create a new Timestream for InfluxDB database cluster
• GetDbCluster: Retrieve information about a specific DB cluster
• DeleteDbCluster: Delete a Timestream for InfluxDB database cluster
• ListDbClusters: List all Timestream for InfluxDB database clusters
• UpdateDbCluster: Update a Timestream for InfluxDB database cluster
• ListDbClusters: List all Timestream for InfluxDB database clusters
• ListDbInstancesForCluster: List DB instances belonging to a specific cluster
• ListClustersByStatus: List DB clusters filtered by status

Database Instance Management

• CreateDbInstance: Create a new Timestream for InfluxDB database instance
• GetDbInstance: Retrieve information about a specific DB instance
• DeleteDbInstance: Delete a Timestream for InfluxDB database instance
• ListDbInstances: List all Timestream for InfluxDB database instances
• UpdateDbInstance: Update a Timestream for InfluxDB database instance
• ListDbInstancesByStatus: List DB instances filtered by status

Parameter Group Management

• CreateDbParamGroup: Create a new DB parameter group
• GetDbParameterGroup: Retrieve information about a specific DB parameter group
• ListDbParamGroups: List all DB parameter groups

Tag Management

• ListTagsForResource: List all tags on a Timestream for InfluxDB resource
• TagResource: Add tags to a Timestream for InfluxDB resource
• UntagResource: Remove tags from a Timestream for InfluxDB resource

InfluxDB Data Operations

Write API

• InfluxDBWritePoints: Write data points to InfluxDB
• InfluxDBWriteLP: Write data in Line Protocol format to InfluxDB

Query API

• InfluxDBQuery: Query data from InfluxDB using Flux query language

Bucket Management

• InfluxDBListBuckets: List all buckets in InfluxDB
• InfluxDBCreateBucket: Create a new bucket in InfluxDB

Organization Management

• InfluxDBListOrgs: List all organizations in InfluxDB
• InfluxDBCreateOrg: Create a new organization in InfluxDB

Configuration

Environment Variables

Write Mode

By default, the server runs read-only: all mutating tools (create/update/delete DB clusters and instances, tag/untag, create parameter group, and the data-plane writes InfluxDBWritePoints, InfluxDBWriteLP, InfluxDBCreateBucket, InfluxDBCreateOrg) are refused. Write authorization is operator-controlled via the ALLOW_WRITE environment variable and is evaluated once at startup — it is not a tool parameter and cannot be set or overridden by a tool caller. To enable mutating tools, start the server with:

ALLOW_WRITE=true

When ALLOW_WRITE is not enabled, mutating tools raise an error and never call the underlying AWS or InfluxDB APIs.

Flux Query Write Mode

By default, the InfluxDBQuery tool rejects Flux queries that contain write-producing operations such as to(), experimental.to(), and wideTo(). This ensures that the query tool behaves as read-only, even when the configured InfluxDB token has write permissions.

To enable write-producing Flux operations through the query tool, set:

INFLUXDB_WRITE_MODE=true

This setting is operator-controlled and cannot be overridden by tool callers.

Best practice: For deployments that need both read and write capabilities, configure a read-only InfluxDB token for general use and enable writes with ALLOW_WRITE=true (and INFLUXDB_WRITE_MODE=true for Flux-query writes) only when needed. This provides the strongest data integrity guarantee regardless of the MCP server's write-mode setting.