
MCP File Tools
io.github.zoster81Published by GitHub account zoster81v2.0.0Updated Oct 27, 2026
Secure encoding-aware filesystem tools with atomic writes, legacy encodings, and typed errors
Overview
Local MCP server giving an assistant controlled read and edit access to explicitly authorized directories, with encoding detection, previewed writes and…
- What you can do
- Read, write, edit and grep text files, and read several files at once
- List directories, build trees, search files, inspect file info and verify state
- Detect and convert text encodings, line endings and byte-order marks
- Navigate source code with symbol outlines, structural search and project relations
- Read, create and edit Markdown documents through preview-then-confirm steps
- Prepare multi-file patches, run durable background tasks and manage backups
- When to use it
- Useful when an assistant needs to work on real files in a local project or workspace: reading and editing code, fixing legacy encodings, or making reviewed multi-file changes. It suits users who want file access limited to named directories with approval steps before anything is written.
- Requirements
- Runs as a local process over stdio from a published binary for Windows, Linux or macOS, or built from source with Go. Each authorized directory is passed as a startup argument. Optional Streamable HTTP mode needs a bearer token via MCP_HTTP_TOKEN_FILE or MCP_HTTP_TOKEN. Optional backup, task and deferred stores are enabled through environment variables.
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
Scripthold — Secure MCP Server for Local Workspaces
[Test Suite] [CodeQL] [OpenSSF Scorecard] [GitHub Release] [Release downloads] [Go] [License: GPL-3.0] [MCP Registry] [AgentHub 已收录:Scripthold] [Glama]
Code from the web. Work locally. Recover safely.
Scripthold is a Model Context Protocol (MCP) server that gives web, desktop, and CLI agents controlled access to explicitly authorized local workspaces. It safely handles legacy text encodings, deterministic file changes, source navigation, backups, and optional durable local execution over stdio or authenticated Streamable HTTP.
AI clients see Настройки — not ???? or Íàñòðîéêè.
Start here: Quick start · Find a tool · All documentation · Security policy.
What Scripthold provides
Scripthold 4.x provides 36 tools and 3 guided prompts; see GitHub Releases for the latest published version. Clients upgrading from 3.x should follow the 4.0 migration guide for the unified confirmation tool. In 4.0.1, the source_symbols outline response defaults to a compact tree; pass presentation: "detailed" to retain the earlier files and symbols fields.
- 168 registered text encodings with content-based detection, UTF-32 LE/BE support, and conservative ambiguity handling.
- 100 active Source Intelligence providers for bounded declaration navigation, structural search, selected project relations, and verified context assembly.
- Secure workspace boundaries with canonical-root containment, Windows reparse/junction handling, deterministic traversal, and missing-path validation.
- Approval-bound mutations using preview/apply capabilities, exact fingerprints, conflict checks, staged writes, and truthful partial-state reporting.
- Optional persistent backups with history, compare, audit, restore, explicit garbage collection, pinning, and exact-ID deletion.
- Durable asynchronous tasks with idempotency, persistent state, bounded logs, recovery, locks, and cancellation.
- Reliable long-running read-only calls through optional deferred-operation storage and bounded retained-result retrieval.
- Authenticated Streamable HTTP with loopback defaults, bearer authentication, Host/Origin validation, resource limits, and explicit TLS/proxy requirements for non-loopback exposure.
Scripthold originated from the original mcp-file-tools project, created by Dimitar Grigorov, and retains its GPL-3.0 lineage. See Project Direction.
Quick start
Choose a published binary or build from source, then configure your MCP client to grant access only to the directories you intend to share. HTTP and container deployments have additional setup below.
Use a published release
Download the asset for your platform from the latest release and verify it against checksums.txt. Releases also attach a signed Sigstore build-provenance bundle for the normal GoReleaser assets.
Build from source
The module path is github.com/zoster81/scripthold.
Local stdio client
Pass each authorized directory as a startup argument:
Startup roots are authoritative. A roots-capable stdio client may supply dynamic roots only when the process starts without directory arguments.
Verified self-update
Supported standalone installations can opt in to self-update. Stop other Scripthold processes using the same binary before running scripthold update --adopt. Adoption prepares local state without downloading or replacing the executable.
After adoption, run scripthold update to verify and dispatch an available release. Use scripthold update status to confirm completion; only run scripthold update recover when status offers recovery. These actions have different safety and verification requirements.
See the Verified Self-update Guide for supported installations, exact commands, failure handling, and recovery rules.
Streamable HTTP
HTTP requires exactly one bearer-token source. A minimal loopback PowerShell launch is:
The MCP endpoint is http://127.0.0.1:8765/mcp; /healthz and /readyz expose liveness/readiness. Send the token as Authorization: Bearer <token> on every MCP request.
Do not expose HTTP beyond loopback without reading HTTP Security. Non-loopback use requires explicit opt-in and TLS or a trusted proxy boundary.
OpenAI Secure MCP Tunnel
Sanitized PowerShell examples are available under examples/:
start-local-stdio.ps1start-local-http.ps1start-openai-tunnel-stdio-plus-local-http.ps1start-openai-tunnel-http-plus-local-stdio.ps1
Copy an example outside the checkout before replacing placeholders. Never commit Runtime API keys, Tunnel IDs, bearer tokens, or private state paths.
Container
The image runs as unprivileged UID/GID 10001.
Tool groups
TOOLS.md is the detailed public reference for schemas, parameters, examples, limits, and error behavior. The table below describes the 4.x catalog (36 tools). Clients upgrading from 3.3.6 must migrate the eight former apply commands to confirm_verified_operation.
Source Intelligence
Source Intelligence helps agents navigate source code without running it or requiring an external compiler, parser, or language server. Use source_symbols to map project files with digest presentation: "compact", browse a tree-structured file outline by default (or request presentation: "detailed" for the previous outline JSON structure), and inspect a selected symbol; use source_query for structural search, supported project relationships, dependency graphs, and verified context. Use grep_text_files when looking for arbitrary text or code behavior that is not represented by structural symbols.
Unsupported or ambiguous relationships are rejected rather than guessed. Markdown files have their own document tools. Check the generated Language Capabilities matrix for available source providers and analysis coverage.
Markdown documents
Markdown files use dedicated tools rather than Source Intelligence providers. Read a document with markdown_read, or inspect links and relationships across files with the read-only markdown_workspace tool.
To change a document, prepare a preview with markdown_edit (or markdown_create for a new file), review the proposed content, and pass its previewId to confirm_verified_operation. Unsafe, conflicting, or stale changes are rejected instead of being silently rewritten.
For examples and the exact operation forms, see the Markdown tool reference. For Markdown semantics, supported encodings, and the Marksplice integration boundary, see Markdown Intelligence.
Safety model
- File access is limited to explicitly authorized roots after canonical path validation.
- Symlink, junction, reparse-point, alias, and missing-path escapes fail closed.
- Encoding detection uses bytes and decoded-content evidence, never filenames or extensions.
- Mutations stage and revalidate before commit; initially missing destinations use no-replace semantics.
- Preview/apply workflows bind the approved operation to a one-shot capability so mutation parameters cannot be changed at apply time.
- Multi-file mutations do not claim transactional rollback; failures report committed/unchanged/unknown state where applicable.
- The optional backup store is a separate protected authority outside public roots.
task_runexecution is disabled by default. Shell and script execution require explicit authorization; HTTP requires an additional HTTP execution opt-in.- HTTP is authenticated and loopback-only by default.
Current architectural boundaries are summarized in Architecture.
Key configuration
Most installations need only a small subset of environment variables:
Detailed limits and subsystem-specific options are documented where they are used: TOOLS.md, Durable Tasks, and HTTP Security.
Documentation
Use the Documentation Guide to find instructions by task, whether you are configuring a client, choosing a tool, securing a deployment, or contributing to the project.
- Using the server: Tool Reference, HTTP Security, and Durable Tasks.
- Understanding and changing the project: Architecture, Contributing, and Roadmap.
- Release history: Changelog, with version-specific steps in the migration guides.
Development
The required Go version is declared by go.mod.
See CONTRIBUTING.md before proposing changes.
License
GPL-3.0 — see LICENSE.
Source: README.md at commit f8029dd
Tools
0Version history
1- v2.0.0LatestSep 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