codesurface 0.7.0

MCP server that indexes a codebase's public API at startup and serves it via compact tool responses. Pluggable parsers for C#, Go, Java, TypeScript, Python, and more.

codesurface

MCP server that indexes your codebase's public API at startup and serves it via compact tool responses — saving tokens vs reading source files.

Parses source files, extracts public classes/methods/properties/fields/events, and serves them through 5 MCP tools. Works with Claude Code, Cursor, Windsurf, or any MCP-compatible AI tool.

Supported languages: C# (.cs), Go (.go), Java (.java), Python (.py), TypeScript/TSX (.ts, .tsx)

Quick Start

pip install codesurface

Then add to your .mcp.json:

{
  "mcpServers": {
    "codesurface": {
      "command": "codesurface",
      "args": ["--project", "/path/to/your/src"]
    }
  }
}

Point --project at any directory containing supported source files — a Unity Assets/Scripts folder, a Spring Boot project, a .NET src/ tree, a Node.js/React project, a Python package, etc. Languages are auto-detected.

Restart your AI tool and ask: "What methods does MyService have?"

CLAUDE.md Snippet

Add this to your project's CLAUDE.md (or equivalent instructions file). This step is important. Without it, the AI has the tools but won't know when to reach for them.

## Codebase API Lookup (codesurface MCP)

Use codesurface MCP tools BEFORE Grep, Glob, Read, or Task (subagents) for any class/method/field lookup. This applies to you AND any subagents you spawn.

| Tool | Use when | Example |
|------|----------|---------|
| `search` | Find APIs by keyword | `search("MergeService")` |
| `get_signature` | Need exact signature | `get_signature("TryMerge")` |
| `get_class` | See all members on a class | `get_class("BlastBoardModel")` |
| `get_stats` | Codebase overview | `get_stats()` |

Every result includes file path + line numbers. Use them for targeted reads:
- `File: Service.cs:32` → `Read("Service.cs", offset=32, limit=15)`
- `File: Converter.java:504-506` → `Read("Converter.java", offset=504, limit=10)`

Never read a full file when you have a line number. Only fall back to Grep/Read for implementation details (method bodies, control flow).

Tools

Tool	Purpose	Example
search	Find APIs by keyword	"MergeService", "BlastBoard", "GridCoord"
get_signature	Exact signature by name or FQN	"TryMerge", "CampGame.Services.IMergeService.TryMerge"
get_class	Full class reference card — all public members	"BlastBoardModel" → all methods/fields/properties
get_stats	Overview of indexed codebase	File count, record counts, namespace breakdown
reindex	Incremental index update (mtime-based)	Only re-parses changed/new/deleted files. Also runs automatically on query misses

Tested On

Project	Language	Files	Records	Time
vscode	TypeScript	6,611	88,293	9.3s
Paper	Java	2,909	33,973	2.3s
client-go	Go	219	2,760	0.4s
langchain	Python	1,880	12,418	1.1s
pydantic	Python	365	9,648	0.3s
guava	Java	891	8,377	2.4s
immich	TypeScript	919	7,957	0.6s
fastapi	Python	881	5,713	0.5s
ant-design	TypeScript	2,947	5,452	0.9s
dify	TypeScript	4,903	5,038	1.9s
crawlee-python	Python	386	2,473	0.3s
flask	Python	63	872	<0.1s
cobra	Go	15	249	<0.1s
gin	Go	41	574	<0.1s
Unity game (private)	C#	129	1,018	0.1s

Line Numbers for Targeted Reads

Every record includes line_start and line_end (1-indexed). Multi-line declarations span the full signature:

[METHOD] com.google.common.base.Converter.from
  Signature: static Converter<A, B> from(Function<...> forward, Function<...> backward)
  File: Converter.java:504-506          ← multi-line signature

[METHOD] server.AlbumController.createAlbum
  Signature: createAlbum(@Auth() auth: AuthDto, @Body() dto: CreateAlbumDto)
  File: album.controller.ts:46          ← single-line

This lets AI agents do targeted reads instead of reading full files:

# Instead of reading the entire 600-line file:
Read("Converter.java")                     # 600 lines, ~12k tokens

# Read just the method + context:
Read("Converter.java", offset=504, limit=10)  # 10 lines, ~200 tokens

Benchmarks

Measured against a real Unity game project (129 files, 1,018 API records) across a 10-step cross-cutting research workflow.

Strategy	Total Tokens	vs MCP
MCP (codesurface)	1,021	—
Skilled Agent (Grep + partial Read)	4,453	4.4x more
Naive Agent (Grep + full Read)	11,825	11.6x more

Even with follow-up reads for implementation detail, the hybrid MCP + targeted Read approach uses 54% fewer tokens than a skilled Grep+Read agent.

See workflow-benchmark.md for the full step-by-step analysis.

Setup Details

Claude Code configuration

Add to <project>/.mcp.json:

Using uv (recommended):

{
  "mcpServers": {
    "codesurface": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/codesurface", "codesurface", "--project", "/path/to/your/src"]
    }
  }
}

Using pip install:

{
  "mcpServers": {
    "codesurface": {
      "command": "codesurface",
      "args": ["--project", "/path/to/your/src"]
    }
  }
}

Project structure

codesurface/
├── src/codesurface/
│   ├── server.py           # MCP server — 5 tools
│   ├── db.py               # SQLite + FTS5 database layer
│   └── parsers/
│       ├── base.py         # BaseParser ABC
│       ├── csharp.py       # C# parser
│       ├── go.py           # Go parser
│       ├── java.py         # Java parser
│       ├── python_parser.py # Python parser
│       └── typescript.py   # TypeScript/TSX parser
├── pyproject.toml
└── README.md

Troubleshooting

"No codebase indexed"

• Ensure --project points to a directory containing supported source files (.cs, .go, .java, .py, .ts, .tsx)
• The server indexes at startup — check stderr for the "Indexed N records" message

Server won't start

• Check Python version: python --version (needs 3.10+)
• Check mcp[cli] is installed: pip install mcp[cli]

Stale results after editing source files

• The index auto-refreshes on query misses — if you add a new class and query it, the server reindexes and retries automatically
• You can also call reindex() manually to force an incremental update

---

Contact

[e-mail]

License

MIT