-
Notifications
You must be signed in to change notification settings - Fork 6
Add MCP tool for querying a service #42
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Merged
Merged
Changes from all commits
Commits
Show all changes
15 commits
Select commit
Hold shift + click to select a range
0debef0
Initial basic implementation of 'tiger_db_execute_query' tool
nathanjcochran c3ddb6c
Consolidate logic for building connection strings
nathanjcochran f7c37a4
Get rid of buildConnectionConfig, roll into util.BuildConnectionString
nathanjcochran 3f9c5b6
Merge branch 'main' into nathan/mcp-query-tool
nathanjcochran 900275b
Fix circular reference issues post-merge
nathanjcochran 38d6155
Merge branch 'main' into nathan/mcp-query-tool
nathanjcochran 31a53fa
Minor tool cleanup
nathanjcochran 01210b8
Rename db.go to db_tools.go for parity with service_tools.go
nathanjcochran 5e7005e
Return rows affected instead of naive row count
nathanjcochran eab502c
Return column type information as well as name
nathanjcochran 60ce598
Add role and pooled options to make 'tiger db connect' command
nathanjcochran 9efbca3
Update spec_mcp.md to reflect changes
nathanjcochran 6b901dc
Fix nil rows/columns bug
nathanjcochran 178a33d
Support parameterized queries
nathanjcochran 20462b3
Update tool description to make it clear that multi-statement queries…
nathanjcochran File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This is the only place we use
PasswordOptional. That causesBuildConnectionStringto attempt to include the password if possible, but to return the connection string without the password if the password can't be found.The previous code would build the connection string without the password, but then
testDatabaseConnectionwould callbuildConnectionConfig, which parsed the connection string into a config struct and attempted to add the password to the config, if possible. That seemed like a pretty roundabout way of doing it (building a connection string just to parse it back into a config), so I got rid of that logic and added thePasswordOptionaloption when building the connection string.That being said, I'm not 100% convinced it's worth it to return the connection string without a password here. The old code in
buildConnectionConfighad this comment:But I'm not sure what "other authentication methods" it's talking about here, or if it's really worth worrying about it. If we don't need to support this, we could get rid of
PasswordOptionaland replacePasswordModewith aPasswordRequiredboolean, which would probably make the code a little more straightforward/clear.There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The other method I originally had in mind was PGPASSWORD env variable being set in the shell or a .pgpassword file (even if not set by the cli). I still think its worth allowing this kind of fallback.