Add C# annotator, JSON annotator, bump to 0.6.0

Add first-class C# language support: classes, interfaces, structs, enums,
records, methods, constructors, using directives, [Attributes], and ///
XML doc comments. Add JSON annotator for structured JSON files. Update
README language support table, .gitignore, and dispatch layer.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Author: RecoDemo

.gitignore

@@ -55,6 +55,9 @@ htmlcov/
 # ── Codebase index cache ─────────────────────
 .codebase-index-cache.pkl
 
+# ── MCP local config ─────────────────────────
+.mcp.json
+
 # ── Misc ───────────────────────────────────────
 *.log
 *.bak

README.md

@@ -8,7 +8,7 @@
 [![MCP](https://img.shields.io/badge/MCP-compatible-purple.svg)](https://modelcontextprotocol.io)
 [![Zero Dependencies](https://img.shields.io/badge/dependencies-zero-brightgreen.svg)]()
 
-A structural codebase indexer with an [MCP](https://modelcontextprotocol.io) server for AI-assisted development. Zero runtime dependencies — uses Python's `ast` module for Python analysis and regex-based parsing for TypeScript/JS, Go, and Rust. Requires Python 3.11+.
+A structural codebase indexer with an [MCP](https://modelcontextprotocol.io) server for AI-assisted development. Zero runtime dependencies — uses Python's `ast` module for Python analysis and regex-based parsing for TypeScript/JS, Go, Rust, and C#. Requires Python 3.11+.
 
 ## What It Does
 
@@ -26,6 +26,7 @@ Indexes codebases by parsing source files into structural metadata -- functions,
 | TypeScript/JS (`.ts`, `.tsx`, `.js`, `.jsx`) | Regex-based | Functions, arrow functions, classes, interfaces, type aliases, imports |
 | Go (`.go`) | Regex-based | Functions, methods (receiver-based), structs, interfaces, type aliases, imports, doc comments |
 | Rust (`.rs`) | Regex-based | Functions (`pub`/`async`/`const`/`unsafe`), structs, enums, traits, impl blocks, use statements, attributes, doc comments, macro_rules |
+| C# (`.cs`) | Regex-based | Classes, interfaces, structs, enums, records, methods, constructors, using directives, `[Attributes]`, `///` XML doc comments |
 | Markdown/Text (`.md`, `.txt`, `.rst`) | Heading detection | Sections (# headings, underlines, numbered, ALL-CAPS) |
 | Other | Generic | Line counts only |
 
@@ -273,7 +274,7 @@ Run the benchmarks yourself: `python benchmarks/benchmark.py`
 
 LSP answers "where is this function?" — mcp-codebase-index answers "what happens if I change it?" LSP is point queries: one symbol, one file, one position. It can tell you where `LLMClient` is defined and who references it. But ask "what breaks transitively if I refactor `LLMClient`?" and LSP has nothing. This tool returns 11 direct dependents and 31 transitive impacts in a single call — 204 characters. To get the same answer from LSP, the AI would need to chain dozens of find-reference calls recursively, reading files at every step, burning thousands of tokens to reconstruct what the dependency graph already knows.
 
-LSP also requires you to install a separate language server for every language in your project — pyright for Python, vtsls for TypeScript, gopls for Go. Each one is a heavyweight binary with its own dependencies and configuration. mcp-codebase-index is zero dependencies, handles Python + TypeScript/JS + Go + Rust + Markdown out of the box, and every response has built-in token budget controls (`max_results`, `max_lines`). LSP was built for IDEs. This was built for AI.
+LSP also requires you to install a separate language server for every language in your project — pyright for Python, vtsls for TypeScript, gopls for Go. Each one is a heavyweight binary with its own dependencies and configuration. mcp-codebase-index is zero dependencies, handles Python + TypeScript/JS + Go + Rust + C# + Markdown out of the box, and every response has built-in token budget controls (`max_results`, `max_lines`). LSP was built for IDEs. This was built for AI.
 
 ## Programmatic Usage
 

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "mcp-codebase-index"
-version = "0.5.0"
+version = "0.6.0"
 description = "Structural codebase indexer with MCP server for AI-assisted development"
 requires-python = ">=3.11"
 readme = "README.md"

src/mcp_codebase_index/annotator.py

@@ -18,8 +18,10 @@
 
 """Dispatch layer that selects the appropriate annotator by file type."""
 
+from mcp_codebase_index.csharp_annotator import annotate_csharp
 from mcp_codebase_index.generic_annotator import annotate_generic
 from mcp_codebase_index.go_annotator import annotate_go
+from mcp_codebase_index.json_annotator import annotate_json
 from mcp_codebase_index.models import StructuralMetadata
 from mcp_codebase_index.python_annotator import annotate_python
 from mcp_codebase_index.rust_annotator import annotate_rust
@@ -38,6 +40,8 @@
     ".jsx": "javascript",
     ".go": "go",
     ".rs": "rust",
+    ".cs": "csharp",
+    ".json": "json",
 }
 
 
@@ -75,5 +79,9 @@ def annotate(
         return annotate_go(text, source_name)
     elif file_type == "rust":
         return annotate_rust(text, source_name)
+    elif file_type == "csharp":
+        return annotate_csharp(text, source_name)
+    elif file_type == "json":
+        return annotate_json(text, source_name)
     else:
         return annotate_generic(text, source_name)