What does File Finder Server do exactly?
It runs an HTTP server that scans the local computer for filenames matching a query string and returns the results as JSON. It also saves the results to `search_results.json`.
@romanshablio
基本信息
Lightweight Python HTTP service that searches local files by name and returns JSON results for tools such as Cline.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mcp-server-romanshablio": {
"command": "python",
"args": [
"mcp_server.py",
"--port",
"8080"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
File Finder Server is a small Python service that searches for files by name on the user's local computer and returns results as JSON. It was created as an MCP-style helper that can be connected to tools such as Cline in VS Code.
Clone the repository, start the server with python mcp_server.py --port 8080, and configure Cline in VS Code by copying the appropriate configuration into cline_config.json and restarting Cline. The server exposes a single HTTP endpoint /search that accepts a query parameter.
search_results.json.It runs an HTTP server that scans the local computer for filenames matching a query string and returns the results as JSON. It also saves the results to `search_results.json`.
After cloning the repository, run `python mcp_server.py --port 8080` from the project folder. The server will listen on the specified port (default 8080).
Send a GET request to `http://localhost:8080/search?query=example` using curl, a browser, or another tool. The server will respond with a JSON array of matching files.
Open `cline_config.json`, copy the server configuration provided in the repository into it, and then restart Cline. The server will then be available as a tool within Cline.
No authentication is mentioned. The server runs locally and scans the filesystem using the permissions of the user who starts the process.

Local-first MCP server that snapshots your project's working state into one context object. Open-core, privacy-first.
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 162 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

Persistent memory for AI agents. Hosted MCP server with capsule-scoped key/value storage, tags, TTL expiration, bulk ops, and RBAC.
Local MCP server and CLI that keeps a Git-versioned, model-written index of a codebase and its database schema, so coding agents start each task with the whole system in view.

One permissioned folder your team and your AI agents both log into.
评论