FSI

v1.0.0Developer Toolsstable

A wrapper around F# interactive (fsi) that exposes an MCP server endpoint for AI agents allowing for fsi IO.

fsimcpai-integration
Share:
39
Stars
0
Downloads
0
Weekly
0/5

What is FSI?

FSI is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to wrapper around f# interactive (fsi) that exposes an mcp server endpoint for ai agents allowing for fsi io.

A wrapper around F# interactive (fsi) that exposes an MCP server endpoint for AI agents allowing for fsi IO.

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • A wrapper around F# interactive (fsi) that exposes an MCP se

Use Cases

Execute F# interactive (fsi) code from AI agents with full I/O support.
jovaneyck

Maintainer

LicenseMIT
Languagef#
Versionv1.0.0
UpdatedMay 20, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx fsi

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use FSI

The FSI MCP Server wraps F# Interactive (fsi) and exposes it as a Model Context Protocol endpoint, enabling AI agents to send and receive F# code for live evaluation in a persistent interactive session. It provides tools to execute F# snippets, load scripts, retrieve recent session events, and check the FSI process status — all via MCP. Developers use it to give AI coding assistants direct access to a running F# REPL, allowing iterative code generation, testing, and debugging in F# without leaving the AI client.

Prerequisites

  • .NET 6.0 SDK or later installed
  • F# Interactive (dotnet fsi) available in your PATH
  • An MCP-compatible client (e.g., JetBrains Rider with MCP plugin, or Claude Desktop)
  • Git for cloning the repository
1

Clone the repository

Clone the fsi-mcp-server repository to your local machine.

git clone https://github.com/jovaneyck/fsi-mcp-server.git
cd fsi-mcp-server
2

Build the project

Use the .NET CLI to build the MCP server binary.

dotnet build
3

Run the server

Start the server. It listens on http://0.0.0.0:5020 by default. Any CLI arguments not prefixed with 'fsi-mcp:' are forwarded to the underlying FSI process.

dotnet run
4

Optionally pass FSI arguments

You can forward arguments to FSI at startup, for example to suppress the logo, define preprocessor symbols, or preload a setup script.

dotnet run -- --nologo --define:DEBUG --load:setup.fsx
5

Configure JetBrains Rider (optional)

To replace Rider's built-in F# Interactive with this MCP-capable server, go to File → Settings → Languages & Frameworks → F# → F# Interactive and set the executable path to the fsi-mcp-server binary.

6

Connect your MCP client

Point your MCP client at http://localhost:5020. The server exposes four tools: SendFSharpCode, LoadFSharpScript, GetRecentFsiEvents, and GetFsiStatus.

FSI Examples

Client configuration

Claude Desktop configuration to connect to the locally running FSI MCP server.

{
  "mcpServers": {
    "fsi": {
      "command": "dotnet",
      "args": ["run", "--project", "/path/to/fsi-mcp-server"],
      "env": {}
    }
  }
}

Prompts to try

These prompts show how an AI agent can use the FSI server for live F# evaluation.

- "Send this F# snippet to the interactive session and return the output: let x = [1..10] |> List.sum"
- "Load the script at /workspace/helpers.fsx into the current FSI session."
- "Check the FSI session status — is it running and ready?"
- "Get the most recent events from the FSI session to see what was last evaluated."
- "Write an F# function to compute Fibonacci numbers and evaluate it in FSI."

Troubleshooting FSI

Server fails to start with 'dotnet fsi not found'

Ensure the .NET SDK (not just the runtime) is installed and 'dotnet fsi' is available in your PATH. Run 'dotnet fsi --version' to verify.

Port 5020 is already in use

The port is currently hardcoded. Stop the process using port 5020 (lsof -i :5020 on macOS/Linux) or modify the port in the server source code before building.

F# code evaluation hangs or never returns

Long-running or infinite loops will block the FSI session. Use GetFsiStatus to check if the session is busy, then restart the server process to reset the FSI state.

Frequently Asked Questions about FSI

What is FSI?

FSI is a Model Context Protocol (MCP) server that wrapper around f# interactive (fsi) that exposes an mcp server endpoint for ai agents allowing for fsi io. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install FSI?

Follow the installation instructions on the FSI GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with FSI?

FSI works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is FSI free to use?

Yes, FSI is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "fsi": { "command": "npx", "args": ["-y", "fsi"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use FSI?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides