knewstimek/agent-tool

한국어
MCP (Model Context Protocol) tool server for AI coding agents.
Why?
Built-in tools in AI coding agents (Claude Code, Cursor, Codex, etc.) have known limitations:
- **Tab indentation breaks**: LLMs output spaces, but your project uses tabs. The built-in Edit tool writes spaces as-is, corrupting your indentation style.
- **Encoding corruption**: Editing EUC-KR, Shift-JIS, or GB18030 files silently converts them to UTF-8, breaking legacy projects.
- **Too many separate tools**: Making the agent find, install, and configure Redis CLI, MySQL client, SSH client, etc. is tedious and error-prone. agent-tool bundles 40 tools into one binary and exposes them on demand through compact profiles.
- **No reverse engineering support**: Built-in tools can't disassemble binaries, inspect PE/ELF headers, find function boundaries, or search cross-references. agent-tool includes static binary analysis (disassembly, decompilation to C with PDB/DWARF types, xref, function detection), a DAP debugger, and CheatEngine-style memory tools -- giving your agent full reverse engineering capabilities.
- **Network censorship**: In some countries, government-level web filtering breaks plain curl/wget requests. agent-tool uses ECH (Encrypted Client Hello) and DoH (DNS over HTTPS) by default to work around these restrictions.
**agent-tool** solves these with agent-oriented tools that preserve project conventions while keeping model context bounded.
Supported Agents
Claude Code, Codex CLI, Cursor, Windsurf, Cline, Gemini CLI, and any MCP-compatible agent.
LLM-efficient by default
The default core profile exposes only 11 schemas (including toolbox) instead of
all 40. In a protocol-level measurement this reduced the serialized tool list from
about 74 KB (full) to 15 KB. For the smallest steady-state context, start with
--profile core-lite; its five schemas are about 6.4 KB and expose only read,
write, edit, grep, and toolbox. Use
toolbox(operation="describe", tool="ssh", compact=true, tool_operation="execute")
to load only one operation's fields and required list, then invoke it through
toolbox(operation="call", tool="ssh", arguments={...}). The gateway does not
depend on dynamic tool-list refresh, so it works with fixed-binding clients such as
Codex. Describe returns a tool/version-bound schema_handle; sending it on a later
describe returns a short unchanged acknowledgement when the schema is still current.
Common compact operations include SSH execution, MySQL queries, file copy, Windows
screenshots/clipboard images, and static-analysis operations. You can also start
with --profile core-lite|coding|remote|analysis|full.
Potentially large text responses default to 32K characters with a 128K hard ceiling.
Truncation is always visible and pageable tools return next_offset or next_cursor.
Local relative paths resolve against an explicit workspace, then the MCP client root.
Features
| Tool | Description | Status |
|------|-------------|--------|
| **Edit** | String replacement with smart indentation and encoding preservation (supports dry_run) | ✅ |
| **Read** | Encoding-aware, line-numbered reading. Defaults to 400 lines/32K chars, reports truncation and exact next_offset, safely handles very long lines, optional SHA-256. Flexible offset and MCP ImageContent support | ✅ |
| **Write** | Encoding-aware file creation/overwrite | ✅ |
| **Grep** | Encoding-aware regex search with 32K output budget, compact file-grouped output, relative paths, .gitignore/.ignore/generated-directory filtering, binary detection, output modes/context, and deterministic next_cursor paging without repeated matches | ✅ |
| **Glob** | Sorted, bounded file matching with **, relative paths, .gitignore/.ignore/generated-directory filtering, explicit has_more, and deterministic cursor paging | ✅ |
| **ListDir** | Bounded/pageable directory listing. max_entries + continuation cursor, directory/file filters, entry-name glob filters, counts-only mode, flat/tree output | ✅ |
| **Diff** | Compare two files with unified diff output (encoding-aware). Files differing only in line endings or a trailing newline say so instead of returning an empty diff | ✅ |
| **Patch** | Apply unified diff patch to a file (supports dry_run). Each line keeps its own ending, so a mixed CRLF/LF file is not rewritten | ✅ |
| **Checksum** | Compute file hash (md5, sha1, sha256) | ✅ |
| **FileInfo** | File metadata (size, encoding, mixed line-ending counts, indentation, line count) | ✅ |