io.github.Codeturion/codesurface
Indexes your codebase's public API and serves it via compact MCP tool responses.
Open source Open in the app JSON README (API)
About
Indexes your codebase's public API and serves it via compact MCP tool responses.
Details
- Kind
- MCP servers
- Topic
- No topic detected
- Publisher
- codeturion
- Origin
- official
- Category
- ferramentas
- Transport
- local
- Version
- 0.8.0
- Stars
- 21
- Forks
- 4
- Last push
- 2026-07-28T20:04:18Z
- Repository state
- ativo
- Language
- Python
- License
- MIT
- Added
- 2026-08-29 03:01:48
- Updated
- 2026-08-29 03:01:48
- Origin id
io.github.Codeturion/codesurface
README
<!-- mcp-name: io.github.Codeturion/codesurface -->
# codesurface
[](https://pypi.org/project/codesurface/)
[](https://pypi.org/project/codesurface/)
[](https://registry.modelcontextprotocol.io/?q=codesurface)
[](https://github.com/Codeturion/codesurface)
[](https://github.com/Codeturion/codesurface)
[](https://github.com/Codeturion/codesurface)
[](https://opensource.org/licenses/MIT)
[](https://www.python.org/downloads/)
[](https://fuatcankoseoglu.com/blog/reducing-llm-agent-hallucinations-through-constrained-api-retrieval)
**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`), C++ headers (`.h`, `.hpp`, `.hxx`, `.h++`), Go (`.go`), Java (`.java`), Python (`.py`), TypeScript/JavaScript (`.ts`, `.tsx`, `.js`, `.jsx`)
## Quick Start
Add to your `.mcp.json`:
```json
{
"mcpServers": {
"codesurface": {
"command": "uvx",
"args": ["codesurface", "--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.
````markdown
## 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 with 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 |
`search`, `get_signature`, and `get_class` accept two optional filters:
- `file_path`: scope results to a directory prefix or exact file (e.g. `"src/services/"` or `"src/services/MergeService.ts"`)
- `include_tests`: include test files in results (default `false`). Detects `__tests__/`, `tests/`, `test/`, `*.test.*`, `*.spec.*`, `*_test.*`, `test_*`
## Tested On
| Project | Language | Files | Records | Time |
|---------|----------|-------|---------|------|
| [vscode](https://github.com/microsoft/vscode) | TypeScript | 6,611 | 88,293 | 9.3s |
| [Paper](https://github.com/PaperMC/Paper) | Java | 2,909 | 33,973 | 2.3s |
| [client-go](https://github.com/kubernetes/client-go) | Go | 219 | 2,760 | 0.4s |
| [langchain](https://github.com/langchain-ai/langchain) | Python | 1,880 | 12,418 | 1.1s |
| [pydantic](https://github.com/pydantic/pydantic) | Python | 365 | 9,648 | 0.3s |
| [guava](https://github.com/google/guava) | Java | 891 | 8,377 | 2.4s |
| [immich](https://github.com/immich-app/immich) | TypeScript | 919 | 7,957 | 0.6s |
| [fastapi](https://github.com/tiangolo/fastapi) | Python | 881 | 5,713 | 0.5s |
| [ant-design](https://github.com/ant-design/ant-design) | TypeScript | 2,947 | 5,452 | 0.9s |
| [dify](https://github.com/langgenius/dify) | TypeScript | 4,903 | 5,038 | 1.9s |
| [crawlee-python](https://github.com/apify/crawlee-python) | Python | 386 | 2,473 | 0.3s |
| [flask](https://github.com/pallets/flask) | Python | 63 | 872 | <0.1s |
| [cobra](https://github.com/spf13/cobra) | Go | 15 | 249 | <0.1s |
| [gin](https://github.com/gin-gonic/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:
```python
# 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 across 5 real-world projects in 5 languages, each using a 10-step cross-cutting research workflow.
| Language | Project | Files | Records | MCP | Skilled | Naive | MCP vs Skilled |
|----------|---------|------:|--------:|----:|--------:|------:|---------------:|
| C# | Unity game | 129 | 1,034 | **1,021** | 4,453 | 11,825 | 77% fewer |
| TypeScript | immich | 694 | 8,344 | **1,451** | 4,500 | 14,550 | 68% fewer |
| Java | guava | 891 | 8,377 | **1,851** | 4,200 | 26,700 | 56% fewer |
| Go | gin | 38 | 534 | **1,791** | 2,770 | 15,300 | 35% fewer |
| Python | codesurface | 9 | 40 | **753** | 2,000 | 10,400 | 62% fewer |
Even with follow-up reads for implementation detail, the hybrid MCP + targeted Read approach uses **44% fewer tokens** than a skilled Grep+Read agent and **87% fewer** than a naive agent:
### Per-question breakdown
See [workflow-benchmark.md](workflow-benchmark.md) for the full step-by-step analysis across all languages.
## Filtering What Gets Indexed
By default, codesurface skips common vendored, build, and VCS directories: `node_modules`, `vendor`, `bin`, `obj`, `dist`, `build`, `target`, `.git`, `.venv`, `__pycache__`, and a few dozen others. Git worktrees and submodules are also skipped.
To exclude additional paths:
**Project-level (committed):** create a `.codesurfaceignore` file at your project root with one glob per line.
```
generated/**
docs/**
**/*.pb.go
```
**Per-instance (CLI):** pass `--exclude` with comma-separated globs.
```json
{
"command": "uvx",
"args": ["codesurface", "--project", "src", "--exclude", "generated/**,vendor/**"]
}
```
Other indexing flags:
- `--include-submodules`: index git submodules (skipped by default)
- `--language <name>`: pin to a single parser (e.g. `--language cpp`) instead of auto-detecting
## Multiple Projects
Each `--project` flag indexes one directory. To index multiple codebases, run separate instances with different server names:
```json
{
"mcpServers": {
"codesurface-backend": {
"command": "uvx",
"args": ["codesurface", "--project", "/path/to/backend/src"]
},
"codesurface-frontend": {
"command": "uvx",
"args": ["codesurface", "--project", "/path/to/frontend/src"]
}
}
}
```
Each instance gets its own in-memory index and tools. The AI agent sees both and can query across projects.
## Setup Details
<details>
<summary>Alternative installation methods</summary>
**Using pip install:**
```bash
pip install codesurface
```
```json
{
"mcpServers": {
"codesurface": {
"command": "codesurface",
"args": ["--project", "/path/to/your/src"]
}
}
}
```
</details>
<details>
<summary>Project structure</summary>
```
codesurface/
├── src/codesurface/
│ ├── server.py # MCP server with 5 tools
│ ├── db.py # SQLite + FTS5 database layer
│ ├── filters.py # PathFilter (default exclusions, .codesurfaceignore, --exclude)
│ └── parsers/
│ ├── base.py # BaseParser ABC
│ ├── cpp.py # C++ header parser
│ ├── csharp.py # C# parser
│ ├── go.py # Go parser
│ ├── java.py # Java parser
│ ├── python_parser.py # Python parser
│ └── typescript.py # TypeScript/JavaScript parser
├── pyproject.toml
└── README.md
```
</details>
<details>
<summary>Troubleshooting</summary>
**"No codebase indexed"**
- Ensure `--project` points to a directory containing supported source files (`.cs`, `.h`, `.hpp`, `.go`, `.java`, `.py`, `.ts`, `.tsx`, `.js`, `.jsx`)
- The server indexes at startup. Check stderr for `[codesurface] scanning N files...` and `[codesurface] done:` lines
**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
</details>
---
## Contact
fuatcankoseoglu@gmail.com
## License
[MIT](LICENSE)