A bridge to translate arbitary LSPs into MCP so that agents can get ground truth about the code they write on the fly.

Design goals:

• Inspired by Crush, which treats LSP diagnostics as special and injects them deterministically. I.e., we don't have to rely on the model to be attentive to diagnostics on its own. They will get injected whether the model likes it or not.
• The simplest solution would obviously be to just create some tools that allow the model to call out to the LSP. But I don't think that would work, because LSP is stateful. In particular, the LSP spec has a lot to say about document synchronization. To be spec-compliant, a client must alert the server when it has opened, closed, or edited a document. Otherwise, the server might report inaccurate diagnostics. Therefore, the agent's basic operations, like "view," "edit," and "grep," must be LSP-aware.
• By re-implementing core tools like these in an MCP, we also solve the first problem, since we know that agents will reliably call tools like this.
• This is, in fact, the approach taken by Crush -- namely, making tool calls LSP aware. See here for example.
• Another goal: I do want it to take LSP seriously. That is, it should support incremenetal operations (synchronization, diagnostics, indexing, etc). This is potentially a lot of work, but an MVP is possible I think without making the code brittle against later changes.
• I think ^^ implies that the server has to support multiple languages, since the standard itself assumes that servers can handle multiple languages.