microsoft / microsoft/vscode-pgsql
MCP tool's querying of schemas should be more fine grained
Nobody has claimed this yet.
- Dominant language
- No language data
- Stars
- 395
- Forks
- 33
- Avg merge
- 1h 46m
- Merged PRs (30d)
- 3
Description
I'm currently working with a database that has a large number of tables, views and functions.
Currently the psql MCP tool is completely unusable as the first thing it does is fetch the schema of all tables (which previously didn't manage to complete at all, but now at least seems to succeed).
This immediately fills the context and leaves you stuck in your tracks.
Really it should behave more like reading of files from the filesystem, choosing the most relevant things to query and add to context.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by examining the psql MCP tool's schema-querying entry point and how it currently fetches all tables, views, and functions. Define a selective querying flow that avoids loading an entire large database schema into context, then verify it against a database with many objects; the payload names no files or tests.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- postgresql
- Domain
- databases, tooling
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100