FRENES

Files and documents · MCP server

Dowse: MCP server, setup and security

Dowse is an open-source MCP server that lets an AI agent search Windows disks for filenames, document contents and screenshot text. Its repository has 37 stars and its last commit is from October 19, 2026 and it is licensed under Apache-2.0.

Score
66/100
Adoption (stars) 16/40
Maintenance 30/30
Framework (licence, registry, official) 20/30
Actively maintainedSystem access

What Dowse does

According to its repository: “Read-only full-disk search on Windows over file names, document contents and OCR'd screenshot text.”

An MCP server gives an AI agent extra tools it calls during the conversation: the agent reads their description, decides to use them and gets the result back. Dowse is listed under Files and documents, a category of 55 servers in the directory, where it ranks #34 by stars.

Topics declared by the repository: chinese, desktop-search, everything-alternative, file-search, full-text-search, jieba.

Installing and connecting Dowse

Distribution modes declared in the official MCP registry:

  • Cargo crate (Rust)

Like any MCP server, you declare it in your client's configuration (Claude Desktop, Claude Code, Cursor, VS Code, Codex…): a name, the command that starts it or its URL, and any environment variables. The client then starts it and lists its tools. Project language: Rust. Listed systems: Windows.

Security: what to check

An MCP server runs code with the rights you give it, and the model reads its tool descriptions: a malicious or compromised server can hijack the agent. Read the code, or pick a maintained and widely used server, before connecting it.

Points found for Dowse:

  • System access: the Files and documents category gives the agent control over files, a terminal, code or a browser. A booby-trapped instruction in content the agent reads (prompt injection) can then turn into an action.

Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.

Project activity and maintenance

Created on July 11, 2026, the ltspace/dowse repository has 37 stars and 4 forks, with 6 open issues. It has more stars than 47% of the servers in the directory. It received changes this month. Version published in the registry: 0.10.0 (July 21, 2026).

Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.

MarkitdownMarkitdown : 191.9K191.9KPuterPuter : 43.9K43.9KFilestashFilestash : 14.8K14.8KRevoGrid DataGrid MCPRevoGrid DataGrid MCP : 3.5K3.5KDocling MCPDocling MCP : 777777MCP filesystem serverMCP filesystem server : 692692Haiku.ragHaiku.rag : 636636MuMu : 436436DowseDowse : 3737
GitHub stars of the most followed servers in the category (log scale); Dowse in orange. Checked October 25, 2026.

Verdict

Dowse is a reasonable choice; check the points below before connecting it.

Strengths

  • Active project: recent commit
  • Listed in the official MCP registry
  • Permissive licence (Apache-2.0)

Avoid if…

  • You cannot isolate the agent (sandbox, container)

Frequently asked questions

How do I install Dowse?

Dowse is distributed as Cargo crate (Rust). Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of ltspace/dowse.

Is Dowse free?

The code is published under the Apache-2.0 licence and can be used free of charge.

Is Dowse safe?

Points to watch: system access. Give it minimum rights and approve sensitive actions.

Is it an official server?

Nothing says so: it is a project published by ltspace on GitHub. Check who maintains it before giving it access.

What are the alternatives to Dowse?

In the same category: Markitdown, Puter, Filestash, and RevoGrid DataGrid MCP. Markitdown and Puter score higher on our grid.

Related articles

Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score