The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the MCP File Tools listing page.
Claude sees Настройки — not ???? or Íàñòðîéêè.
MCP server for file operations on text that isn't UTF-8. It detects the encoding from the file's bytes rather than its extension, hands the model UTF-8, and writes back in the original encoding — BOM and CRLF/LF intact, still byte-compatible with whatever legacy tool owns the file.
edit_file, grep_text_files and search_files decode the same way, not just read and writedetect_encoding reports the charset, a confidence score and any BOM, so garbled text becomes diagnosableBuilt for: Delphi/Pascal units with Cyrillic UI text, VB6 forms, legacy PHP/HTML with localized content, and INI or data files whose encoding you can't tell from the filename.
PRs welcome and merged fast — no CLA, no style review, one-line fixes count. Forked this to fix something? Please send it back instead.
Inside a session: /plugin marketplace add … and /plugin install ….
Requires Node.js 18+ on your PATH. The launcher is a Node script
and Claude Code does not bundle Node; without it /mcp shows the server as not connected.
First launch downloads the binary for your OS at a pinned version, verifies its SHA-256 and caches it. It is scoped to the folder you have open, so there is nothing to configure. For directories outside the workspace, or a machine without Node, use a manual install.
Tool names change too: mcp__file-tools__* becomes
mcp__plugin_mcp-file-tools_file-tools__*, so update your permission rules, see
Auto-approve tools.
Use the full plugin@marketplace id, not the bare name, or turn on auto-update in
/plugin → Marketplaces.
This server is listed in the Official MCP Registry for discovery by any MCP client, and indexed on Glama, which scores it A for license, quality and maintenance.
Download the binary for your platform, then register it with the directories it may access.
| Platform | Release asset | Suggested path |
|---|---|---|
| Windows x64 | mcp-file-tools_windows_amd64.exe | %LOCALAPPDATA%\Programs\mcp-file-tools\mcp-file-tools.exe |
| Linux x64 | mcp-file-tools_linux_amd64 | ~/.local/bin/mcp-file-tools |
| macOS ARM64 | mcp-file-tools_darwin_arm64 | ~/.local/bin/mcp-file-tools |
Windows (PowerShell, not CMD):
Linux / macOS (swap the asset name from the table for your platform):
For Claude Desktop, VSCode, or Cursor, use the downloaded binary path in your config:
Claude Desktop (%APPDATA%\Claude\claude_desktop_config.json on Windows, ~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
Windows:
macOS / Linux:
args lists the directories the server may access — as many as you need.
VSCode / Cursor (Claude Code extension)
If you already ran claude mcp add --scope user from the installation steps above, the server is already available in VSCode — no extra config needed.
To configure separately for VSCode only:
Alternatively, create a per-project config by adding .mcp.json to your project root:
Note: type: "stdio" is required here. The VSCode extension does not add the workspace
directory by itself, so args must list every directory you want reachable. Adding one
later means re-running claude mcp add with the full list — it overwrites the previous
config rather than appending.
Codex takes a direct MCP command, so no manual TOML editing is needed.
Windows (PowerShell):
Run codex mcp list to verify it, then start a new Codex session. Add more directory
arguments to grant access outside the current project.
To skip the permission prompts, add to .claude/settings.local.json in your project root:
That prefix is the plugin install; a manual one registered as file-tools is
mcp__file-tools__* instead, and a rule with the wrong prefix matches nothing and fails
quietly. Which modes the rules affect, and keeping delete_file / move_file behind a
prompt, are in docs/extra.md.
The server checks for updates automatically and notifies you through tool responses when a newer version is available; the notice carries the steps for your install. Plugin installs update through Updating the plugin — a re-downloaded binary is ignored there.
For a manual install, re-download the binary over the existing one — the registration does not need repeating:
To disable update checks, set the environment variable MCP_NO_UPDATE_CHECK=1.
Once installed, just ask Claude:
Security: the server reaches only the directories you allowed. It takes them from
args: ["/path/to/project"] first, then MCP_FILE_TOOLS_ALLOWED_DIRS, and failing both
from the directory it was started in — the workspace, when a client launches it there.
Clients that still speak the MCP roots protocol add their roots on top. A drive root or
your home directory is never granted by that last fallback; name it explicitly instead.
Paths are resolved before the check, so a symlink or Windows junction pointing outside is
rejected rather than followed.
20 tools — every one that touches text content is encoding-aware:
read_text_file - Read files with encoding auto-detection and conversionread_multiple_files - Read multiple files concurrently with encoding supportwrite_file - Write files in specific encodingsedit_file - Line-based edits with diff preview and whitespace-flexible matchingcopy_file - Copy a file to a new locationdelete_file - Delete a filelist_directory - Browse directories with pattern filteringtree - Compact indented tree view, optionally annotated with each file's encodingsearch_files - Recursively search for files matching glob patternsgrep_text_files - Regex search in file contents with encoding supportdetect_encoding - Auto-detect file encoding with confidence scoreconvert_encoding - Convert file between encodingsmanage_line_endings - Detect or convert line endings (CRLF/LF/mixed)manage_bom - Detect, strip, or add Unicode BOMlist_encodings - Show all supported encodingsget_file_info - Get file/directory metadatacreate_directory - Create directories recursively (mkdir -p)move_file - Move or rename files and directorieslist_allowed_directories - Show accessible directoriescheck_for_updates - Check whether a newer release is availablePlus three prompts — audit_encodings, fix_mojibake,
migrate_to_utf8 — surfaced by clients as user commands.
See TOOLS.md for detailed parameters and examples. Calls shaped like Claude Code's built-in Read/Write/Edit/Grep are accepted too — the alias layer translates them where the semantics match exactly, so a model's habits don't fail the call.
Out of scope: binary/media reading (read_media_file). This is a text
tool; agents read images with their built-in tools.
Every one below reads and writes. Name one explicitly via the encoding parameter, or
leave it to auto-detection.
| Script / region | Encodings |
|---|---|
| Unicode | UTF-8, UTF-16 LE, UTF-16 BE |
| Cyrillic | Windows-1251, KOI8-R, KOI8-U, CP866, ISO-8859-5, MacCyrillic |
| Western European | Windows-1252, ISO-8859-1, ISO-8859-15 |
| Central European | Windows-1250, ISO-8859-2 |
| Greek | Windows-1253, ISO-8859-7 |
| Turkish | Windows-1254, ISO-8859-9 |
| Chinese Simplified | GBK, GB18030 |
| Hebrew, Arabic, Baltic, Vietnamese, Thai | Windows-1255, 1256, 1257, 1258, 874 |
Common aliases are accepted (cp1251, latin1, gb2312, tis-620, …) —
list_encodings prints the whole table with aliases.
UTF-32 is partially supported: LE and BE BOMs are detected, and
manage_bom can add or strip them, but transcoding to or from
UTF-32 is not implemented and manage_line_endings
refuses UTF-32 files rather than corrupting their 4-byte alignment.
The server can be configured via environment variables:
| Variable | Description | Default |
|---|---|---|
MCP_DEFAULT_ENCODING | Default encoding for write_file on new files when none specified. Existing files keep their detected encoding. Set to cp1251 to restore the pre-2.0.0 default. | utf-8 |
MCP_DEFAULT_LINE_ENDINGS | Line endings for write_file on new files (crlf/lf). Existing files keep their own style regardless. | unset (write unchanged) |
MCP_MEMORY_THRESHOLD | Memory threshold in bytes. Files smaller are loaded into memory for faster I/O; larger files use streaming. Also affects encoding detection mode. | 67108864 (64MB) |
MCP_DETECTION_CANDIDATES | Comma-separated list pinning what detection may answer, in priority order — e.g. utf-8,windows-1252. See Pinning the encodings. | unset (detection unrestricted) |
MCP_FILE_TOOLS_ALLOWED_DIRS | Allowed directories as an OS path list (; on Windows, : elsewhere). For clients where env is the only block you control, such as the Claude Code plugin. Overridden by args. | unset |
MCP_FILE_TOOLS_NO_CWD_FALLBACK | Set to turn off granting the working directory when neither args nor MCP_FILE_TOOLS_ALLOWED_DIRS names one. | unset (fallback on) |
Set them with an env block in your config (Claude Desktop example):
Detection is a guess, and guesses have blind spots: Spanish CP1252 like MÓDULO FÍSICAMENTE ÚNICO is plausible GBK — every uppercase accent before an ASCII letter is a
valid hanzi pair — so it reads back as Chinese and edits fail with "gbk cannot represent
2 characters". If you know what the repo contains, say so:
A BOM still wins. A guess inside the list keeps its confidence; one outside it is dropped
and the first listed encoding that decodes the bytes cleanly takes over, so order is your
priority. A file that fits none of them is read as the default and reported as an ODD
ENCODING in read_text_file's hint, so a stray file gets said out loud rather than
guessed at. Unlisted encodings stop appearing in detect_encoding's candidates too. UTF-16/32 are named only by a BOM
or the structural classifier, so listing them cannot make them a catch-all.
Before 2.0.0 new files defaulted to cp1251; they now default to utf-8. Existing files
are unaffected — their encoding is detected and preserved — so this only matters if your
team creates new non-UTF-8 files, e.g. new Delphi units with Cyrillic literals. To keep
the old behaviour:
Commit that in the legacy repo's .mcp.json rather than setting it per machine, and
everyone working in that repo gets the right default with no local setup.
Delphi 2007 and older read UTF-8 only when it carries a BOM, so a UTF-8 file without one
is silently treated as ANSI. Set cp1251 (or your own ANSI code page) for such a repo and
new Cyrillic literals land in the encoding the IDE expects. Files that already exist keep
their own encoding either way, and no tool adds a BOM to them.
Prerequisites: Go 1.27+
test_server.go is an end-to-end smoke test over every tool, run by CI on each push:
MCP Inspector gives a web UI for calling tools and inspecting responses (needs Node.js 18+):
Or pipe JSON-RPC straight to stdin:
If it fits the scope and works, it gets merged. Don't ask first — just send the PR.
No CLA, no style review: make test and make lint passing is enough, and tests are
welcome but never required. One-line fixes and half-finished features behind a flag both
count. Out of scope, or breaking a tool contract other people's agents rely on, gets a
comment rather than a close. Not writing the fix yourself?
Open an issue with the file,
its encoding, and what the tool did.
Details in CONTRIBUTING.md. Found a way out of an allowed directory? That one goes to SECURITY.md, privately, not to an issue.
Forking is fine. That's what GPL-3.0 is for. Taking the project over is not.
GPL-3.0 is a license, not a preference. Distribute your fork in any form (public repo, release binary, registry listing, product you ship to customers) and you must:
[!WARNING] Deleting the license or the notice, relicensing as MIT or proprietary, or shipping only a binary is a license violation, and §8 ends your rights the moment you do it.
It will be enforced, in this order: a request to comply, then a DMCA takedown plus delisting from whichever registry or marketplace carries it, then legal action. Complying costs one license file, one notice and one source link. Ask in an issue if you are unsure whether what you ship complies.
Asked, not enforced: leave the credit in — the copyright notice is the legal minimum, one line saying "Fork of mcp-file-tools" is what tells a reader where it came from. Give your fork its own name, so a registry listing under this one with the author swapped doesn't read as if the project moved and send its bugs here. And try upstream first: a PR beats carrying merge conflicts forever, and puts your name on the commit rather than in a credits list.
Ideas that started in someone else's fork and were reimplemented here:
edit_file retry hintA PR gets your name on the commit instead of this list.
GPL-3.0 - see LICENSE
Copyright (C) 2026 Dimitar Grigorov. Free software, distributed WITHOUT ANY WARRANTY.