
MCP File Tools
io.github.dimitar-grigorovPublished by GitHub account dimitar-grigorovv4.6.2Updated Oct 31, 2026
Non-UTF-8 files: CP1251, CP1252, KOI8, ISO-8859, UTF-16, GBK auto-detected and preserved
Overview
Local MCP server for reading, editing and writing text files in non-UTF-8 encodings, detecting the charset from bytes and preserving it on write.
- What you can do
- Read files with automatic encoding detection, including several files at once, and inspect the detected charset, confidence and BOM
- Write and edit files in a chosen encoding, with line-based edits and diff preview, plus copy, move, rename and delete files
- Browse and search the filesystem: list directories, show a tree, find files by glob and grep file contents with encoding support
- Convert encodings, manage line endings and BOMs, and list the supported encodings
- Inspect file metadata, create directories and list the directories the server may access
- When to use it
- Useful when an assistant must work with legacy or localized text files whose encoding is not UTF-8, such as Delphi/Pascal units, VB6 forms, older PHP or HTML pages, and INI or data files, and the encoding must survive edits byte-compatibly.
- Requirements
- Runs as a local process on the desktop. The plugin launcher needs Node.js 18+ on the PATH; a manual install uses a downloaded binary per platform, or Go 1.27+ to build from source. Directories it may access are passed as arguments or set via MCP_FILE_TOOLS_ALLOWED_DIRS. No account or API key is declared.
Installation
In SourceWeft
- Open MCP File Tools in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
MCP File Tools
[Release] [Downloads] [Test] [OpenSSF Scorecard] [License: GPL-3.0] [MCP Registry] [Glama score]
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.
- 45 encodings, read and write — Cyrillic (CP1251, KOI8-R/U, CP866/855), Windows-125x, ISO-8859-x, DOS code pages, MacRoman, UTF-16/UTF-32, CJK (GBK, Big5, Shift_JIS, EUC-JP/KR) (full list)
- Encoding-aware across the whole tool set —
edit_file,grep_text_filesandsearch_filesdecode the same way, not just read and write - Detection you can inspect —
detect_encodingreports the charset, a confidence score and any BOM, so garbled text becomes diagnosable - BOM and line endings are first-class — including on UTF-16, where a naive byte-level rewrite corrupts the file
- Sandboxed — every path, symlink and junction targets included, is checked against the directories you allowed
Built 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.
Installation
Claude Code plugin (recommended)
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.
Coming from 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.
Updating the plugin
Use the full plugin@marketplace id, not the bare name, or turn on auto-update in
/plugin → Marketplaces.
Registries and directories
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.
Manual install (other MCP clients, or access outside your workspace)
Download the binary for your platform, then register it with the directories it may access.
Windows (PowerShell, not CMD):
Linux / macOS (swap the asset name from the table for your platform):
Go install (all platforms)
Other Clients
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.
OpenAI Codex CLI
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.
Auto-approve tools (Claude Code)
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.
Update
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:
- Close all Claude Code sessions (the binary is locked while running)
- Re-download:
To disable update checks, set the environment variable MCP_NO_UPDATE_CHECK=1.
Verify & Uninstall
How to Use
Once installed, just ask Claude:
- "List all .pas files in this directory"
- "Read config.ini and detect its encoding"
- "Show all supported encodings"
- "Read MainForm.dfm using CP1251 encoding"
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.
Tools
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 available
Plus 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.
Supported encodings
Every one below reads and writes. Name one explicitly via the encoding parameter, or
leave it to auto-detection.
Common aliases are accepted (cp1251, latin1, gb2312, tis-620, …) —
list_encodings prints the whole table with aliases.
Auto-detection never guesses MacRoman, the DOS pages or the rarer ISO tables; name them explicitly. UTF-32 is found only by its BOM.
Configuration
The server can be configured via environment variables:
Set them with an env block in your config (Claude Desktop example):
Pinning the encodings
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 listed encoding that reads most like text takes over, list order breaking ties. 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.
Legacy teams (pre-2.0.0 behaviour)
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.
Development
Prerequisites: Go 1.27+
scripts/smoke-test starts the server over stdio and calls the read-only tools, run by CI on each push:
Debugging
MCP Inspector gives a web UI for calling tools and inspecting responses (needs Node.js 18+):
Or pipe JSON-RPC straight to stdin:
Contributing
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
Forks are welcome; that is what GPL-3.0 is for. If you distribute one (a public repo, a release binary, a registry listing, a product), the license asks you to:
- Keep GPL-3.0, LICENSE and the copyright notices (§4, §5c)
- Say what you changed and when (§5a)
- Give the source to everyone who gets the binary (§6)
Removing the license or the notice, relicensing, or shipping only a binary breaks the license and ends the rights it grants (§8). Unsure whether what you ship complies? Ask in an issue.
Beyond that, please keep a line such as "Fork of mcp-file-tools" so readers know where it came from, and give your fork its own name, so its bugs don't land here. Fixed something? A PR saves you the merge conflicts and puts your name on the commit.
Credits
Ideas that started in someone else's fork and were reimplemented here:
- @skyispainted - GBK/GB18030, JSON-string array args,
edit_fileretry hint - @haobiao - GBK/GB18030, independently
- Hugo Rosário - merging MCP roots with CLI allowed dirs
- @zoster81 - UTF-16 line endings and grep, path containment fixes, write durability, BOM policy, ordered concurrency
- Mario Rial - pinning detection to known encodings, multi-pattern grep
A PR gets your name on the commit instead of this list.
License
GPL-3.0 - see LICENSE
Copyright (C) 2026 Dimitar Grigorov. Free software, distributed WITHOUT ANY WARRANTY.
Source: README.md at commit f6328bb
Tools
0Version history
6- v4.6.2LatestOct 31, 2026
- v4.6.0Oct 31, 2026
- v4.5.2Oct 16, 2026
- v4.5.1Oct 14, 2026
- v4.5.0Sep 28, 2026
- v4.4.1Sep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts