Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Agent Ransack MCP find all .txt files containing 'invoice' in D:\Documents"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Give Cursor's AI agent supercharged local file search on Windows by connecting it to Agent Ransack via MCP.
Instead of relying only on Cursor's built-in search, the agent can call search_files_content and run headless searches through flpsearch.exe — ideal for large codebases, regex-heavy queries, and deep folder scans.
Windows only. Requires Node.js 18+ and a licensed Agent Ransack build that supports command-line export (
-o).
search_files_content MCP tool — Cursor's agent invokes Agent Ransack autonomously
Content search — find text or regex inside files
Filename search — omit containingText to search by file name pattern only
Headless — no Agent Ransack window pops up; results are parsed from CSV output
Auto-detects common flpsearch.exe install paths
Related MCP server: Fast Context MCP
Requirement | Notes |
Windows | Uses |
Node.js 18+ | |
Agent Ransack (licensed) | Free edition blocks headless |
Cursor | With MCP support enabled |
flpsearch.exe pathCommon locations:
C:\Program Files\Mythicsoft\Agent Ransack\flpsearch.exe
C:\Program Files\Agent Ransack\flpsearch.exegit clone https://github.com/amrsohil/Agent-Ransack-MCP-Cursor.git
cd Agent-Ransack-MCP-Cursornpm installOpen (or create) your global MCP config:
C:\Users\YOUR_USER\.cursor\mcp.jsonAdd the server (adjust paths to match your machine):
{
"mcpServers": {
"agent-ransack": {
"command": "C:\\Program Files\\nodejs\\node.exe",
"args": ["C:\\path\\to\\Agent-Ransack-MCP-Cursor\\index.js"],
"env": {
"FLPSEARCH_PATH": "C:\\Program Files\\Mythicsoft\\Agent Ransack\\flpsearch.exe"
}
}
}
}See mcp.json.example for a copy-paste template.
Open Settings → MCP. You should see agent-ransack with the search_files_content tool available.
Once configured, ask Cursor's agent naturally:
"Search D:\Projects\MyApp for every reference to WorkOrderStatus"
"Find all .tsx files containing useEffect in my repo"
"List every .config file under C:\Projects"
The agent will call the MCP tool automatically.
Parameter | Required | Description |
| Yes | Absolute path to search |
| No | Text or regex inside files. Omit for filename-only search. |
| No | e.g. |
| No | Search recursively. Default: |
| No | Treat |
| No | Case-sensitive content search. Default: |
| No | Cap matching lines per file |
Cursor Agent → MCP Server (Node.js) → flpsearch.exe → CSV results → AgentCursor's agent calls search_files_content
The MCP server runs flpsearch.exe headlessly with -o to a temp CSV file
Results are parsed and returned as formatted text
No Agent Ransack UI window appears
Problem | Fix |
Tool not listed in Cursor | Reload Cursor; check |
| Set |
| Upgrade to Agent Ransack premium / FileLocator Pro |
| Use full path to |
No results | Verify the |
Need help setting this up for your team or building custom MCP integrations?
Amr Sohil
📧 amr.sohil@gmail.com
Available for:
Agent Ransack + Cursor MCP setup for teams
Custom MCP server development
Windows dev workflow automation
Enterprise Cursor tooling
This MCP server is released under the MIT License.
Agent Ransack is commercial software by Mythicsoft. This project does not include or redistribute Agent Ransack. Each user must install and license Agent Ransack separately.
Amr Sohil
📧 amr.sohil@gmail.com
If this project helps you, consider starring the repo on GitHub.
Search a folder using Agent Ransack (flpsearch.exe). Finds files by name pattern and optionally searches file contents. Use for large trees, regex-heavy searches, or cases where built-in search is insufficient. Omit containingText for filename-only search.
| Name | Required | Description | Default |
|---|---|---|---|
| regex | No | Treat containingText as a regular expression (-cex). Default: false | |
| folder | Yes | Absolute path to the directory to search | |
| matchCase | No | Case-sensitive content search (-cm). Default: false | |
| subfolders | No | Search subfolders recursively. Default: true | |
| filePattern | No | File name pattern, e.g. "*.cs" or "*.tsx". Default: "*.*" | |
| containingText | No | Text or regex to find inside files. Omit for filename-only search. | |
| maxLinesPerFile | No | Maximum matching lines to return per file (-ol). Optional. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It mentions using an external executable and the ability to search by name/content, but does not detail behavior like performance, permission requirements, or return format. Moderately transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three concise sentences, each adding value. Front-loaded with purpose and main use case. No wasted words, well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 7 parameters, no output schema, and no annotations, the description covers purpose, usage scenarios, and parameter relationship (containingText omission). Lacks return format details but is sufficient for a search tool. Adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, baseline 3. Description adds value by clarifying the omission of containingText for filename-only search and implicitly covering regex, which goes beyond schema repetition. Slightly above baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states the tool searches a folder using Agent Ransack for files by name pattern and optionally file contents, which is a specific verb+resource. It distinguishes from built-in search, fulfilling purpose clarity exceptionally well.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to use: for large trees, regex-heavy searches, or when built-in search is insufficient. Also gives guidance on omitting containingText for filename-only search. Provides clear usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.0search_files_contentThere is only one tool, so no ambiguity exists. An agent will always select the correct tool.
The single tool uses a clear snake_case name (search_files_content) which is descriptive and follows a consistent pattern.
With only one tool, the server feels minimal. However, for a focused file search purpose, a single comprehensive tool can be sufficient, though it may limit flexibility.
The tool covers both filename and content search, including regex. Minor gaps like advanced filtering or archive search may exist, but the core search domain is well-covered.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Securely search and manage workspace context files for AI agents and teams.
Search your AI chat history (ChatGPT, Claude, Codex) from any MCP client. Remote, private, read-only
Multi-engine search for AI agents. Trust scoring, local corpus, MCP-native. Self-hostable, BYOK.
Code intelligence for coding agents: semantic, AST, graph, and full-text search. 279+ languages.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/amrsohil/Agent-ransack-MCP-cursor'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
