What is the .faf format and why should I use it?

The .faf format is an IANA-registered standard for persistent project context in Grok conversations. It lets you save your project state, configuration, and conversation history so you can resume work without losing context across sessions.

How do I install and set up the grok-faf-mcp server?

Install via npm with `npx grok-faf-mcp@1.2.2`. The server runs over SSE (Server-Sent Events) and is hosted at https://grok-faf-mcp.vercel.app/sse. Connect it to your Grok client to enable .faf file management.

Can I use .faf files across different projects or with other tools?

The .faf format is IANA-registered, which means it's a standardized format. However, this MCP server is specifically designed for Grok context persistence. Compatibility with other tools depends on their .faf format support.

Is there a cost to use this MCP server?

The registry and documentation provided do not specify pricing. The server is available as an npm package and hosted endpoint, but you should check the project repository for any licensing or usage terms.

What happens if my .faf file becomes corrupted or too large?

The registry metadata does not detail file size limits or corruption recovery. Refer to the project documentation or repository for guidance on .faf file management, validation, and troubleshooting.

MCP ServerSSEOfficialv1.2.2

Persistent Project Context for xAI Grok MCP Server

Maintain persistent project context across Grok conversations using the IANA-registered .faf format. Developers can store and retrieve project state, configuration, and conversation history without losing context between sessions.

io.github.Wolfe-Jam/grok-faf-mcp

Open in Agent Studio Scan security View source

Hosted URL

https://grok-faf-mcp.vercel.app/sse

Transport

SSE

Auth

No auth required

What the Persistent Project Context for xAI Grok MCP server does

How models use it and what it is built for.

Connect to Persistent Project Context for xAI Grok

Hosted endpoint — paste into any MCP client.

https://grok-faf-mcp.vercel.app/sse

Resources

Where to find authoritative docs and source for Persistent Project Context for xAI Grok.

Example prompts for Persistent Project Context for xAI Grok

Paste any of these into Agent Studio after connecting Persistent Project Context for xAI Grok.

Save my current project configuration to a .faf file for later retrieval
Load the project context from my existing .faf file and summarize it
What fields does the .faf format support for storing project metadata
Export my conversation history and project state in .faf format

Persistent Project Context for xAI Grok MCP server — FAQ

Common questions about connecting and running Persistent Project Context for xAI Grok.

What is the .faf format and why should I use it?
The .faf format is an IANA-registered standard for persistent project context in Grok conversations. It lets you save your project state, configuration, and conversation history so you can resume work without losing context across sessions.
How do I install and set up the grok-faf-mcp server?
Install via npm with `npx grok-faf-mcp@1.2.2`. The server runs over SSE (Server-Sent Events) and is hosted at https://grok-faf-mcp.vercel.app/sse. Connect it to your Grok client to enable .faf file management.
Can I use .faf files across different projects or with other tools?
The .faf format is IANA-registered, which means it's a standardized format. However, this MCP server is specifically designed for Grok context persistence. Compatibility with other tools depends on their .faf format support.
Is there a cost to use this MCP server?
The registry and documentation provided do not specify pricing. The server is available as an npm package and hosted endpoint, but you should check the project repository for any licensing or usage terms.
What happens if my .faf file becomes corrupted or too large?
The registry metadata does not detail file size limits or corruption recovery. Refer to the project documentation or repository for guidance on .faf file management, validation, and troubleshooting.

Run Persistent Project Context for xAI Grok across 60+ AI models, side-by-side

Connect Persistent Project Context for xAI Grok to Claude, GPT, Gemini, DeepSeek and 60+ AI models in MCP Agent Studio. Compare answers side-by-side, save reusable agent presets, share runs — all in your browser, no install required.

Open Agent Studio

Related servers

Judges Panel

45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.

Addozhang Nexus

Query Sonatype Nexus Repository (OSS/Pro) for Maven, Python, and Docker artifacts

Cyanheads MCP Ts Template

TypeScript template for building MCP servers with declarative tooling, observability, and auth.

Chernistry Bernstein

Declarative agent orchestration for engineering teams