InfluxDB MCP Server
Model Context Protocol server providing read-only access to InfluxDB v2 for LLMs. Enables querying time-series data via Flux queries and schema discovery.
Installation
Standalone using uv + python
# Clone and install
git clone <repository-url>
cd influxdb-mcp
uv sync
# Run
uv run python -m influxdb_mcp
Using Docker
# Build and run
docker build -t influxdb-mcp .
docker run -d -p 5001:5001 --env-file .env influxdb-mcp
# Or use docker-compose
docker-compose up -d
Configuration
Environment Variables
| Variable | Description | Default | Required |
|---|---|---|---|
| InfluxDB Settings | |||
INFLUXDB_TOKEN |
Auth token | - | Yes |
INFLUXDB_ORG |
Organization | - | Yes |
INFLUXDB_HOST |
InfluxDB hostname | localhost |
No |
INFLUXDB_PORT |
InfluxDB port | 8086 |
No |
INFLUXDB_USE_SSL |
Use HTTPS | false |
No |
INFLUXDB_VERIFY_SSL |
Verify SSL certs | true |
No |
INFLUXDB_TIMEOUT |
Request timeout (ms) | 10000 |
No |
| MCP Settings | |||
MCP_LISTEN_HOST |
Server bind address | 127.0.0.1 |
No |
MCP_LISTEN_PORT |
Server port | 5001 |
No |
MCP_TRANSPORT |
Transport protocol | streamable-http |
No |
.env Example
# InfluxDB Configuration
INFLUXDB_HOST=influxdb.example.com
INFLUXDB_PORT=8086
INFLUXDB_TOKEN=your-token-here
INFLUXDB_ORG=your-org
# MCP Configuration
MCP_LISTEN_HOST=0.0.0.0
MCP_LISTEN_PORT=8000
Available Tools
test_connection- Test InfluxDB connection and return statuslist_buckets- List all available bucketslist_measurements(bucket)- List measurements in a bucketexecute_flux_query(query)- Execute custom Flux queries
Available Resources
influxdb://buckets- Live bucket list with metadatainfluxdb://measurements/{bucket}- Live measurements for bucketinfluxdb://status- Current connection statusflux://templates/daily-hourly-average/{bucket}/{measurement}/{field}- Hourly averagesflux://templates/recent-data/{bucket}/{measurement}/{field}/{duration}- Recent dataflux://templates/threshold-alerts/{bucket}/{measurement}/{field}/{threshold}- Threshold monitoringflux://templates/correlation/{bucket}/{measurement1}/{field1}/{measurement2}/{field2}- Correlation analysis
Server runs on http://127.0.0.1:5001/mcp/ by default.
Author
Developed by Michael Ludvig and his AI assistants.
Metadata
Release files for influxdb-mcp 0.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| influxdb_mcp-0.1.1.tar.gz | 69.6 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| influxdb_mcp-0.1.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 80.6 kB
Release files / influxdb_mcp-0.1.1.tar.gz
| Download URL | influxdb_mcp-0.1.1.tar.gz |
|---|---|
| Size | 69.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
1f3fd08901ceef53ed5a55894323c268de9f8cb94e0bc88304eab7c4e2ddab73
|
|
BLAKE2b-256 checksum How to use checksums |
0f6737442720625d4f8389b057b27b5f755bb3c86507800dd9dc6377fb294e06
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.7.13
|
Release files / influxdb_mcp-0.1.1-py3-none-any.whl
| Download URL | influxdb_mcp-0.1.1-py3-none-any.whl |
|---|---|
| Size | 11.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
ba9cf8c684a94c16bbeed56c423bc3ca241f86690d5fca7a59366ba7ce7d70c4
|
|
BLAKE2b-256 checksum How to use checksums |
81f5e22714d4a53d946ab4b9c8ac1e0f765b4938d72a99a6351976fb7fe8a528
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.7.13
|
Security for influxdb-mcp 0.1.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.