InfluxDB 3 MCP server

InfluxDB 3 MCP Server

<!-- --> <!-- -->

Model Context Protocol (MCP) server for InfluxDB 3 integration. Provides tools, resources, and prompts for interacting with InfluxDB 3 Core and Enterprise, plus InfluxDB Cloud Dedicated, InfluxDB Clustered, and InfluxDB Cloud Serverless via MCP clients.

Prerequisites

• InfluxDB 3 Instance: URL and token (Core/Enterprise/Cloud Serverless) or Cluster ID and tokens (Cloud Dedicated/Clustered)
• Node.js: v20.11 or newer (for npm/npx usage)
• npm: v9 or newer (for npm/npx usage)
• Docker: (for Docker-based setup)

Read-only Agent Workflows

Set INFLUXMCPTOOLPROFILE=readonly when you want an MCP client to explore and query InfluxDB 3 data without exposing write, admin, token-management, or host-level tools. In Enterprise deployments that use preview user auth, the same read-only flow works when the configured bearer credential is a JWT instead of an apiv3 token.

Analyst explores an unfamiliar database

An analyst can connect an MCP client such as Claude Desktop, Cursor, Codex, or another agent harness and ask a question like:

Which sensors had the highest average temperature in the last 24 hours?

With the read-only profile, the agent can:

columns.

1. Call list_databases to see accessible databases.
2. Call listtables and describetable to discover measurements and

metadata.

1. Treat uncertain tag and field categories as unknown.
2. Build a bounded SQL query with db, q, and optional params.
3. Call query_sql with structured JSON output.
4. Return the result, row count, truncation status, warnings, and correlation

The user gets a grounded answer and a reusable query while the agent explores and queries data without access to mutation or administration tools.

Operator investigates an InfluxQL dashboard query

An operator can troubleshoot an existing InfluxQL dashboard panel and ask:

Why did this panel stop showing data after the deploy?

With the read-only profile, the agent can:

referenced columns.

1. Keep the user's query in InfluxQL and call query_influxql.
2. Use SHOW queries and schema discovery to verify the measurement and

broken query.

1. Sample recent rows with bounded reads to distinguish missing data from a

statements.

1. Reject unsafe follow-up attempts, such as SELECT INTO or destructive

correlate the MCP result with system.queries.id when query history is available.

1. Return requestid, queryid, and queryidsource so the operator can

reserved for MCP protocol messages.

1. Emit structured logs to stderr for stdio transports so stdout remains

The user gets a practical diagnosis, such as missing data, renamed schema, a wrong time predicate, or a query failure. The investigation is traceable without logging full query text by default.

Available Tools

Shortened. The full README is on GitHub.