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Outdated suggestions cannot be applied.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.
Adds support for running this library on any JS runtime. Strips out any node-only APIs.
Specifically we now run tests on the following runtimes:
In the future we can add tests for:
The above require separate binaries so will take a bit more work to set up.
Why?
The rationale for doing this is to make it possible to embed this MCP server as a library on any JS runtime, most commonly with Vercel's AI SDK. Because AI SDK is typically used in Next.js on Vercel's edge runtime, we add tests for running in their edge runtime environment.
Running LLMs directly from the browser is less common, but possible. Testing in browser runtimes mainly forces us to stick to web standard APIs.
Keeping this server runtime agnostic also makes it easier for us to switch runtimes this later if needed (Deno, Bun, etc).