InfluxDB 3

Official InfluxDB 3 MCP server: query, write and manage Core, Enterprise and Cloud databases.

Connector by influxdata · GitHub account verified by the MCP Registry

IndexedApache-2.0 OR MITLocal (stdio)★ 38

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/influxdata-influxdb3-mcp-server

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Official InfluxDB 3 MCP server: query, write and manage Core, Enterprise and Cloud databases.

Use cases: database-access, monitoring-observability

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Tools: 20 read · 9 write · 4 delete · 1 not yet classified
Secrets: 2 (API keys, tokens or passwords)
Install scripts: None found
Runs as: Node.js package

Tools by what they do 34

Read from the source code; the running server may list different tools.

Read 20 · Look things up without changing anything.

check-health
cloud_get_database_token
cloud_list_database_tokens
describe_table
get_help
get_measurement_schema
get_measurements
health_check
investigate_database
list_admin_tokens
list_databases
list_resource_tokens

Show 8 more tools

list_tables
list-databases
load_database_context
load-context
query_influxql
query_sql
serverless_get_schema
serverless_list_schemas

Write 9 · Create, change, send or run things.

cloud_create_database_token
cloud_update_database_token
create_admin_token
create_database
create_resource_token
serverless_create_schema
serverless_update_schema
update_database
write_line_protocol

Delete 4 · Delete, drop, revoke or wipe things.

cloud_delete_database_token
delete_database
delete_token
regenerate_operator_token

Not yet classified 1 · We could not tell from the name and description.

execute_query

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

INFLUX_DB_MANAGEMENT_TOKEN
INFLUX_DB_TOKEN

Other settings (environment variables or headers).

INFLUX_DB_ACCOUNT_ID
INFLUX_DB_CLUSTER_ID
INFLUX_DB_INSTANCE_URL
INFLUX_DB_PRODUCT_TYPE
INFLUX_MCP_TOOL_PROFILE

Network hosts it talks to 4

console.influxdata.com · found in code
github.com · found in code
host.docker.internal · found in code
your-region.aws.cloud2.influxdata.com · found in code

Tools (34)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

check-health
Generate a prompt to check InfluxDB health status
cloud_create_database_token
Create a new database token for InfluxDB Cloud-Dedicated/Clustered cluster. Specify exact permissions per database or create a no-access token. Permissions format: [{"database": "db_name", "action": "read|write"}, ...] Examples: • No access: omit permissions field or use [] • Read-only on 'analytics': [{"database": "analytics", "action": "read"}] • Mixed permissions: [{"database": "logs", "action": "read"}, {"database": "metrics", "action": "write"}] • Full access: [{"database": "*", "action": "read"}, {"database": "*", "action": "write"}]
cloud_delete_database_token
Delete a database token from InfluxDB Cloud-Dedicated/Clustered cluster. This action cannot be undone.
cloud_get_database_token
Get details of a specific database token by ID for InfluxDB Cloud-Dedicated/Clustered cluster.
cloud_list_database_tokens
List all database tokens for InfluxDB Cloud-Dedicated/Clustered cluster. Returns token information including permissions and creation dates.
cloud_update_database_token
Update an existing database token for InfluxDB Cloud-Dedicated/Clustered cluster. Can update description and/or permissions with precise control. Permissions format: [{"database": "db_name", "action": "read|write"}, ...] Note: Permissions completely replace existing ones - include all desired permissions. Examples: • No access: use [] • Read-only on 'analytics': [{"database": "analytics", "action": "read"}] • Mixed permissions: [{"database": "logs", "action": "read"}, {"database": "metrics", "action": "write"}] • Full access: [{"database": "*", "action": "read"}, {"database": "*", "action": "…
create_admin_token
Create a new InfluxDB named admin token with full administrative permissions (Core/Enterprise only). Named admin tokens can manage databases, users, and resource tokens, but cannot manage other admin tokens.
create_database
Create a new database in InfluxDB. Database names must follow InfluxDB naming rules: alphanumeric characters, dashes (-), underscores (_), and forward slashes (/) are allowed. Must start with a letter or number. Maximum 64 characters. For Cloud Dedicated/Clustered: maxTables, maxColumnsPerTable, retentionPeriod. For Cloud Serverless: description, retentionPeriod.
create_resource_token
Create a new InfluxDB Enterprise resource token with specific database permissions. Example: databases=["mydb", "testdb"], actions=["read", "write"]
delete_database
Delete a database from InfluxDB. Use the exact database name as returned by the list_databases tool.
delete_token
Delete an InfluxDB token by name (Core/Enterprise only).
describe_table
Describe table schema using InfluxDB metadata. Unknown tag/field roles are returned as category=unknown instead of guessed. Use this before retrying SQL queries that fail on quoted wildcard or unknown-field selectors; expand matching fields explicitly and run one bounded query_sql.
execute_query
Execute a SQL query against an InfluxDB database (all versions). Returns results in the specified format (defaults to JSON). On Cloud Dedicated, Cloud Serverless, and Clustered, this tool supports only JSON output. Large Dataset Warning: InfluxDB might contain massive time-series data. Always use COUNT(*) first to check size, then LIMIT/OFFSET for large results (>1000 rows). Cloud Dedicated/Clustered & Cloud Serverless (v3) Requirements: - GROUP BY: Include all group columns in SELECT (e.g., SELECT place, COUNT(*) ... GROUP BY place) - Aggregations: Cast and alias COUNT (e.g., CAST(COUNT(*) …
get_help
Get help and troubleshooting guidance for InfluxDB operations. Supports specific categories or keyword search.
get_measurement_schema
Get the schema (column information) for a specific measurement/table (all versions). Shows column names, types, and categories (time/tag/field).

Show 19 more tools

get_measurements
Get a list of all measurements (tables) in a database/bucket (all versions). Uses the InfluxDB information_schema.columns to discover tables.
health_check
Check current connection status to the InfluxDB instance. Returns connection status, configuration, and available endpoint results. Health assessment is flexible - if any check passes (client initialization, /health endpoint, or /ping), the instance is considered healthy. Available checks depend on the InfluxDB product type and token configuration.
investigate_database
Discover tables and schemas in a database, optionally sampling recent rows from each table with bounded reads.
list_admin_tokens
List all admin tokens (operator and named admin tokens) with optional filtering by token name (Core/Enterprise only). Named admin tokens have full administrative access including resource token management.
list_databases
List all databases in the InfluxDB instance (all versions). Returns database names, count, and status information.
list_resource_tokens
List all Enterprise resource tokens with optional filtering by database name and/or token name, and ordering.
list_tables
List tables, also called measurements, in an InfluxDB database.
list-databases
Generate a prompt to list all available databases
load_database_context
Check for and load custom database context if available. Always check this first as it can significantly speed up analysis and clarify data nuances. User-provided context is optional but when present, it contains valuable information about database structure, business context, or personal notes that can guide more accurate analysis.
load-context
Load custom database context and documentation
query_influxql
Run one bounded, read-only InfluxQL query against an InfluxDB 3 database. Rejects SELECT INTO and destructive statements. Prefer query_sql for SQL prompts; use InfluxQL regex field selection only when the user explicitly asks for InfluxQL or regex field matching.
query_sql
Run one bounded, read-only SQL query against an InfluxDB 3 database. Defaults to JSON output and returns structured rows, warnings, and query metadata. On Cloud Dedicated, Cloud Serverless, and Clustered, this tool supports only JSON output. In SQL, quoted identifiers are exact column names; if a quoted selector contains *, treat it as wildcard intent, call describe_table, expand matching fields explicitly, then retry one bounded query_sql. Use query_influxql regex only when the user explicitly asks for InfluxQL or regex field selection.
regenerate_operator_token
Regenerate the InfluxDB operator token (Core/Enterprise only). Returns the new token value. ⚠️ This action invalidates current operator token and is irreversible. Receive the explicit user confirmation before proceeding.
serverless_create_schema
Create a new measurement schema in a Cloud Serverless bucket with explicit schema type. Define columns with their types (tag, field, timestamp) and data types.
serverless_get_schema
Get detailed information about a specific measurement schema in a Cloud Serverless bucket. Shows column definitions, data types, and schema metadata.
serverless_list_schemas
List all measurement schemas in a Cloud Serverless bucket. Only available for buckets with explicit schema type. Shows schema names, column definitions, and metadata.
serverless_update_schema
Add new columns to an existing measurement schema in a Cloud Serverless bucket. IMPORTANT: You can only ADD new columns, not modify existing ones. The endpoint requires ALL columns (existing + new) to be sent. Use get_schema first to retrieve current columns, then include them along with new columns in this update.
update_database
Update database configuration for InfluxDB. For Cloud Dedicated/Clustered: modify maxTables, maxColumnsPerTable, and retentionPeriod. For Cloud Serverless: modify bucket name, description, and retentionPeriod. For Core/Enterprise: modify retentionPeriod only (Core requires v3.2.0+).
write_line_protocol
Write data to InfluxDB using line protocol format (all versions). Supports single records or batches. Line Protocol Syntax: measurement,tag1=value1,tag2=value2 field1=value1,field2=value2 timestamp Components: - measurement: table/measurement name (required) - tags: indexed metadata (optional) - comma-separated key=value pairs - fields: actual data (required) - space-separated from tags, comma-separated key=value pairs - timestamp: optional timestamp (precision must be specified in tool parameters) Field Value Types: - Strings: "quoted string" - Floats: 123.45 - Integers: 123i (note the '…

Signals

Stars: 38
Forks: 14
Open issues: 20
Contributors: 12
Weekly downloads: 164
Last commit: Oct 23, 2026 (5 days ago)
Last release: Oct 8, 2026 (20 days ago)
Last package publish: Oct 8, 2026 (20 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name: io.github.influxdata/influxdb3-mcp-server
Version: 1.4.2
Auth: API key
Packages: npm @influxdata/influxdb3-mcp-server
License: Apache-2.0 OR MIT
Repository: github.com/influxdata/influxdb3_mcp_server
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: Official MCP Registry github-graphql

More from influxdata

Cite this page

InfluxDB 3 MCP server. Agent Mart. https://agentmart.dev/connectors/influxdata-influxdb3-mcp-server (last updated 2026-10-24)