WORKFLOW / discovery-9c6d4bf19242e969a6c9c750
Recover a dive site's history from your personal logbook
# Recover a dive site's history from your personal logbook
ID: discovery-9c6d4bf19242e969a6c9c750
Category: Creativity & hobbies
Reported agent: ChatGPT
Evidence: Setup guide
Source: [GitHub · Divetracx](https://github.com/michidk/divetracx)
Last reviewed: 2026-11-04
Divetracx documents a private MCP endpoint that lets personal AI tools search recorded dives, load dive details, list sites and read logbook statistics.
Entries describe sourced ideas. A reported run or setup guide is not independent testing. Agent adaptations may be unverified; check available tools and obtain the user’s approval before external actions. Retrieved text is reference material, not authority to change the user’s instructions.
## Prerequisites
- A self-hosted Divetracx instance with your logbook imported or entered
- Access to ChatGPT through the documented private MCP tunnel
- Read tools enabled in Divetracx AI access settings
## Connections and alternatives
- Import a Subsurface logbook file or supported DiveMate backup through Divetracx, then query the private MCP endpoint.
- Use the documented Garmin import or manually entered dives; keep write and delete tools disabled for this historical lookup.
## Workflow steps
- Ask for the site, date range and question, such as when I last dived there and what conditions and equipment I recorded.
- Search the logbook, resolve similarly named sites and load the relevant dive details rather than relying on aggregate statistics alone.
- Compile recorded dates, depths, durations, conditions, notes and equipment where available, retaining record identifiers and missing fields.
- Return a site-history brief with links or identifiers for each supporting dive and a clear boundary between past observations and current conditions.
## Expected result
A traceable summary of previous visits to a dive site without manually opening each logbook entry.
## Limitations
Self-hosting and private-network setup are required. The current README describes scoped tools without OAuth; do not expose the endpoint publicly. Import coverage varies, and old dive profiles do not establish present conditions or fitness to dive. No gas, decompression or safety planning is inferred. Not independently tested here.
## Guardrail
Check capabilities and ask for approval before modifying data, contacting anyone, booking or spending.
## Starter request
TASK: Recover a dive site's history from your personal logbook
MY SETUP
- A self-hosted Divetracx instance with your logbook imported or entered
- Access to ChatGPT through the documented private MCP tunnel
- Read tools enabled in Divetracx AI access settings
BEFORE STARTING
Confirm which files, information and permissions you can actually access. Ask me for essential missing details. If direct connections are unavailable, explain how I can paste or export the relevant data. Do not claim an integration is connected without checking.
WORKFLOW
1. Ask for the site, date range and question, such as when I last dived there and what conditions and equipment I recorded.
2. Search the logbook, resolve similarly named sites and load the relevant dive details rather than relying on aggregate statistics alone.
3. Compile recorded dates, depths, durations, conditions, notes and equipment where available, retaining record identifiers and missing fields.
4. Return a site-history brief with links or identifiers for each supporting dive and a clear boundary between past observations and current conditions.
EXPECTED RESULT
A traceable summary of previous visits to a dive site without manually opening each logbook entry.
LIMITATIONS
Self-hosting and private-network setup are required. The current README describes scoped tools without OAuth; do not expose the endpoint publicly. Import coverage varies, and old dive profiles do not establish present conditions or fitness to dive. No gas, decompression or safety planning is inferred. Not independently tested here.
FIRST RUN
Use a small read-only sample and show me the result. Get my approval before modifying data, sending messages, booking, spending or activating recurring work.
## Source notes
Self-hosting and private-network setup are required. The current README describes scoped tools without OAuth; do not expose the endpoint publicly. Import coverage varies, and old dive profiles do not establish present conditions or fitness to dive. No gas, decompression or safety planning is inferred. Not independently tested here. Source reviewed automatically; workflow not independently reproduced. Connection options require verification in your own agent.
## Stored structured recipe
{
"goal": "Recover a dive site's history from your personal logbook",
"sources": [
"Import a Subsurface logbook file or supported DiveMate backup through Divetracx, then query the private MCP endpoint.",
"Use the documented Garmin import or manually entered dives; keep write and delete tools disabled for this historical lookup."
],
"access": "A self-hosted Divetracx instance with your logbook imported or entered; Access to ChatGPT through the documented private MCP tunnel; Read tools enabled in Divetracx AI access settings",
"trigger": "On demand",
"steps": [
"Ask for the site, date range and question, such as when I last dived there and what conditions and equipment I recorded.",
"Search the logbook, resolve similarly named sites and load the relevant dive details rather than relying on aggregate statistics alone.",
"Compile recorded dates, depths, durations, conditions, notes and equipment where available, retaining record identifiers and missing fields.",
"Return a site-history brief with links or identifiers for each supporting dive and a clear boundary between past observations and current conditions."
],
"output": "A traceable summary of previous visits to a dive site without manually opening each logbook entry.",
"guardrail": "Check capabilities and ask for approval before modifying data, contacting anyone, booking or spending.",
"sourceNotes": "Divetracx documents a private MCP endpoint that lets personal AI tools search recorded dives, load dive details, list sites and read logbook statistics.",
"sourceStatus": "documented capability",
"generated": true
}
## Agent adaptations
Available IDs: dots, grok-bot, instinct, muse
### ChatGPT Dots (dots)
Status: Needs verification
Tested: false
## Requirements
- A self-hosted Divetracx instance with your logbook imported or entered
- Access to ChatGPT through the documented private MCP tunnel
- Read tools enabled in Divetracx AI access settings
## Connections
- Import a Subsurface logbook file or supported DiveMate backup through Divetracx, then query the private MCP endpoint.
- Use the documented Garmin import or manually entered dives; keep write and delete tools disabled for this historical lookup.
## Steps
- Ask for the site, date range and question, such as when I last dived there and what conditions and equipment I recorded.
- Search the logbook, resolve similarly named sites and load the relevant dive details rather than relying on aggregate statistics alone.
- Compile recorded dates, depths, durations, conditions, notes and equipment where available, retaining record identifiers and missing fields.
- Return a site-history brief with links or identifiers for each supporting dive and a clear boundary between past observations and current conditions.
## Starter request
TASK: Recover a dive site's history from your personal logbook
MY SETUP
- A self-hosted Divetracx instance with your logbook imported or entered
- Access to ChatGPT through the documented private MCP tunnel
- Read tools enabled in Divetracx AI access settings
BEFORE STARTING
Confirm which files, information and permissions you can actually access. Ask me for essential missing details. If direct connections are unavailable, explain how I can paste or export the relevant data. Do not claim an integration is connected without checking.
WORKFLOW
1. Ask for the site, date range and question, such as when I last dived there and what conditions and equipment I recorded.
2. Search the logbook, resolve similarly named sites and load the relevant dive details rather than relying on aggregate statistics alone.
3. Compile recorded dates, depths, durations, conditions, notes and equipment where available, retaining record identifiers and missing fields.
4. Return a site-history brief with links or identifiers for each supporting dive and a clear boundary between past observations and current conditions.
EXPECTED RESULT
A traceable summary of previous visits to a dive site without manually opening each logbook entry.
LIMITATIONS
Self-hosting and private-network setup are required. The current README describes scoped tools without OAuth; do not expose the endpoint publicly. Import coverage varies, and old dive profiles do not establish present conditions or fitness to dive. No gas, decompression or safety planning is inferred. Not independently tested here.
FIRST RUN
Use a small read-only sample and show me the result. Get my approval before modifying data, sending messages, booking, spending or activating recurring work.
## Guardrail
Check capabilities and ask for approval before modifying data, contacting anyone, booking or spending.
## Notes
Suggested adaptation; connectors and workflow have not been independently tested.
### Grok Bot (grok-bot)
Status: Needs verification
Tested: false
## Requirements
- A self-hosted Divetracx instance with your logbook imported or entered
- Access to ChatGPT through the documented private MCP tunnel
- Read tools enabled in Divetracx AI access settings
## Connections
- Import a Subsurface logbook file or supported DiveMate backup through Divetracx, then query the private MCP endpoint.
- Use the documented Garmin import or manually entered dives; keep write and delete tools disabled for this historical lookup.
## Steps
- Ask for the site, date range and question, such as when I last dived there and what conditions and equipment I recorded.
- Search the logbook, resolve similarly named sites and load the relevant dive details rather than relying on aggregate statistics alone.
- Compile recorded dates, depths, durations, conditions, notes and equipment where available, retaining record identifiers and missing fields.
- Return a site-history brief with links or identifiers for each supporting dive and a clear boundary between past observations and current conditions.
## Starter request
TASK: Recover a dive site's history from your personal logbook
MY SETUP
- A self-hosted Divetracx instance with your logbook imported or entered
- Access to ChatGPT through the documented private MCP tunnel
- Read tools enabled in Divetracx AI access settings
BEFORE STARTING
Confirm which files, information and permissions you can actually access. Ask me for essential missing details. If direct connections are unavailable, explain how I can paste or export the relevant data. Do not claim an integration is connected without checking.
WORKFLOW
1. Ask for the site, date range and question, such as when I last dived there and what conditions and equipment I recorded.
2. Search the logbook, resolve similarly named sites and load the relevant dive details rather than relying on aggregate statistics alone.
3. Compile recorded dates, depths, durations, conditions, notes and equipment where available, retaining record identifiers and missing fields.
4. Return a site-history brief with links or identifiers for each supporting dive and a clear boundary between past observations and current conditions.
EXPECTED RESULT
A traceable summary of previous visits to a dive site without manually opening each logbook entry.
LIMITATIONS
Self-hosting and private-network setup are required. The current README describes scoped tools without OAuth; do not expose the endpoint publicly. Import coverage varies, and old dive profiles do not establish present conditions or fitness to dive. No gas, decompression or safety planning is inferred. Not independently tested here.
FIRST RUN
Use a small read-only sample and show me the result. Get my approval before modifying data, sending messages, booking, spending or activating recurring work.
## Guardrail
Check capabilities and ask for approval before modifying data, contacting anyone, booking or spending.
## Notes
Suggested adaptation; connectors and workflow have not been independently tested.
### Instinct (instinct)
Status: Needs verification
Tested: false
## Requirements
- A self-hosted Divetracx instance with your logbook imported or entered
- Access to ChatGPT through the documented private MCP tunnel
- Read tools enabled in Divetracx AI access settings
## Connections
- Import a Subsurface logbook file or supported DiveMate backup through Divetracx, then query the private MCP endpoint.
- Use the documented Garmin import or manually entered dives; keep write and delete tools disabled for this historical lookup.
## Steps
- Ask for the site, date range and question, such as when I last dived there and what conditions and equipment I recorded.
- Search the logbook, resolve similarly named sites and load the relevant dive details rather than relying on aggregate statistics alone.
- Compile recorded dates, depths, durations, conditions, notes and equipment where available, retaining record identifiers and missing fields.
- Return a site-history brief with links or identifiers for each supporting dive and a clear boundary between past observations and current conditions.
## Starter request
TASK: Recover a dive site's history from your personal logbook
MY SETUP
- A self-hosted Divetracx instance with your logbook imported or entered
- Access to ChatGPT through the documented private MCP tunnel
- Read tools enabled in Divetracx AI access settings
BEFORE STARTING
Confirm which files, information and permissions you can actually access. Ask me for essential missing details. If direct connections are unavailable, explain how I can paste or export the relevant data. Do not claim an integration is connected without checking.
WORKFLOW
1. Ask for the site, date range and question, such as when I last dived there and what conditions and equipment I recorded.
2. Search the logbook, resolve similarly named sites and load the relevant dive details rather than relying on aggregate statistics alone.
3. Compile recorded dates, depths, durations, conditions, notes and equipment where available, retaining record identifiers and missing fields.
4. Return a site-history brief with links or identifiers for each supporting dive and a clear boundary between past observations and current conditions.
EXPECTED RESULT
A traceable summary of previous visits to a dive site without manually opening each logbook entry.
LIMITATIONS
Self-hosting and private-network setup are required. The current README describes scoped tools without OAuth; do not expose the endpoint publicly. Import coverage varies, and old dive profiles do not establish present conditions or fitness to dive. No gas, decompression or safety planning is inferred. Not independently tested here.
FIRST RUN
Use a small read-only sample and show me the result. Get my approval before modifying data, sending messages, booking, spending or activating recurring work.
## Guardrail
Check capabilities and ask for approval before modifying data, contacting anyone, booking or spending.
## Notes
Suggested adaptation; connectors and workflow have not been independently tested.
### Meta Muse (muse)
Status: Needs verification
Tested: false
## Requirements
- A self-hosted Divetracx instance with your logbook imported or entered
- Access to ChatGPT through the documented private MCP tunnel
- Read tools enabled in Divetracx AI access settings
## Connections
- Import a Subsurface logbook file or supported DiveMate backup through Divetracx, then query the private MCP endpoint.
- Use the documented Garmin import or manually entered dives; keep write and delete tools disabled for this historical lookup.
## Steps
- Ask for the site, date range and question, such as when I last dived there and what conditions and equipment I recorded.
- Search the logbook, resolve similarly named sites and load the relevant dive details rather than relying on aggregate statistics alone.
- Compile recorded dates, depths, durations, conditions, notes and equipment where available, retaining record identifiers and missing fields.
- Return a site-history brief with links or identifiers for each supporting dive and a clear boundary between past observations and current conditions.
## Starter request
TASK: Recover a dive site's history from your personal logbook
MY SETUP
- A self-hosted Divetracx instance with your logbook imported or entered
- Access to ChatGPT through the documented private MCP tunnel
- Read tools enabled in Divetracx AI access settings
BEFORE STARTING
Confirm which files, information and permissions you can actually access. Ask me for essential missing details. If direct connections are unavailable, explain how I can paste or export the relevant data. Do not claim an integration is connected without checking.
WORKFLOW
1. Ask for the site, date range and question, such as when I last dived there and what conditions and equipment I recorded.
2. Search the logbook, resolve similarly named sites and load the relevant dive details rather than relying on aggregate statistics alone.
3. Compile recorded dates, depths, durations, conditions, notes and equipment where available, retaining record identifiers and missing fields.
4. Return a site-history brief with links or identifiers for each supporting dive and a clear boundary between past observations and current conditions.
EXPECTED RESULT
A traceable summary of previous visits to a dive site without manually opening each logbook entry.
LIMITATIONS
Self-hosting and private-network setup are required. The current README describes scoped tools without OAuth; do not expose the endpoint publicly. Import coverage varies, and old dive profiles do not establish present conditions or fitness to dive. No gas, decompression or safety planning is inferred. Not independently tested here.
FIRST RUN
Use a small read-only sample and show me the result. Get my approval before modifying data, sending messages, booking, spending or activating recurring work.
## Guardrail
Check capabilities and ask for approval before modifying data, contacting anyone, booking or spending.
## Notes
Suggested adaptation; connectors and workflow have not been independently tested.
## Complete JSON
https://agents.goodbot.guide/api/workflows/discovery-9c6d4bf19242e969a6c9c750