Chisle
The coding-agent plugin that bills 52% of a bare model across 20 live tasks. Terse persona + tool-output compressor + context diet.
ScalaSemantic gives AI coding agents compiler-resolved Scala facts over MCP.
Translation pending
Developer toolsGitHub @MercurieVVOnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
Repository information has not been collected yet.
No updates detected yet. GitHub releases will appear here.
MCP server for deep semantic analysis of Scala via SemanticDB — exact find-usages, class hierarchies, implicit resolution & call paths for AI coding agents like Claude Code. Beyond grep and standard LSP.
Loading the full README.
Read the full README ↗ScalaSemantic is an MCP server that gives AI coding agents compiler-resolved Scala facts — exact symbols, types, inheritance, usages, implicits, and call paths — from compiler-emitted SemanticDB. Instead of grepping source text, agents query what the compiler already knows.
Works with Scala 2.13.* and 3.., any sbt/Mill/Gradle project, and any MCP-compatible agent (Claude Code, Codex, Gemini CLI, Cline, Roo Code, Continue…).
Needs only java. One command registers the server for your user, so every Scala project on the machine gets it:
curl -fsSL https://raw.githubusercontent.com/MercurieVV/ScalaSemantic/master/scripts/scalasemantic-mcp.sh | sh
Run it from a project root with --project to also enable SemanticDB, write the agent steering files and install the Claude guard hook. Re-running is safe:
curl -fsSL https://raw.githubusercontent.com/MercurieVV/ScalaSemantic/master/scripts/scalasemantic-mcp.sh | sh -s -- --project
iwr https://raw.githubusercontent.com/MercurieVV/ScalaSemantic/master/scripts/scalasemantic-mcp.ps1 -OutFile scalasemantic-mcp.ps1; .\scalasemantic-mcp.ps1 setup
Launcher, plain jar and logging: Integration. The optional guard hook denies grep/cat/Read on .scala files and points agents at the MCP tools; it is not installed by default.
find_symbol · find_usages · class_hierarchy · method_signature · members · resolve_implicits · call_path · type_at_position · hole_context · resolve_references · literal_tokens · contract_clauses · trace_implicit_chain · find_overloads — what each does, plus the symbol grammar: Tool reference.
For a shell hook or script that can't hold an MCP session open, scalasemantic-mcp call <tool> '<json-args>' [root] [classpath] runs one tool and prints its JSON result.
grep| Question | Right tool |
|---|---|
| Exact callers of a method | find_usages |
| All subtypes of a trait | class_hierarchy |
Which given satisfies a type | resolve_implicits |
Call path from method a to c | call_path |
| Comments, TODOs, config files | grep |
| Code that hasn't compiled yet | grep |
Measured: semantic tools use ~90% fewer tokens than grep for symbol questions. Details: ScalaSemantic vs grep.
Full documentation: mercurievv.github.io/ScalaSemantic