Fractera

io.github.FracteraPublished by GitHub account Fracterav1.0.0Updated Oct 24, 2026

Zero-Ops deploy of a private AI workspace to your own VPS — from your AI chat. Free and open-source.

The publisher's own server: deploy.social

VerifiedStreamable HTTPWeb executableCloud & InfrastructureAI & ML

Overview

AI-generated overview

Fractera deploys a private, self-hosted AI workspace onto the user's own VPS from an AI chat, handling signup, install, status and retries.

What you can do
  • Register a new user and start the server deployment in one call, given email, server IP and root password
  • Check installation progress on demand and retrieve the final admin address once install completes
  • Retry a failed deployment on the same server using a server token, returning a new session to track
  • Get a recommended VPS provider for users who do not yet have a server
  • Answer questions about the project: architecture, components, modes, data ownership, pricing and partner program
When to use it
Useful when someone wants a private AI workspace on their own VPS but does not want to run the installation by hand, and prefers to drive signup, deployment and troubleshooting from a chat. Also handy for explaining what Fractera is while a deploy is running.
Requirements
A remote MCP endpoint; no local package or environment variables are declared. The user must supply an email address, the VPS IP address and the server's root password, and needs an existing VPS (or a recommendation for one). Deployment reportedly takes 8-14 minutes.
Before you install
The register_and_deploy tool takes the server's root password and IP and sends them to a third-party service, so the assistant handles root credentials for the user's machine. It creates an account and a subscription record, and retry_deploy wipes the previous install on the same server. The initial admin URL is plain HTTP without a domain or HTTPS certificate.

Installation

In SourceWeft

  1. Open Fractera in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.Fractera%2Fdeploy/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "fractera": {
      "type": "http",
      "url": "https://www.fractera.ai/api/mcp"
    }
  }
}

Tools

6

register_and_deploy

Deploy Fractera Workspace

Register a new Fractera user and start the deployment of their server in one atomic call. Use this AFTER you have collected the user's email (entered twice for typo protection), server IP, and root password. Creates the User row (or reuses an existing one with the same email), creates a free Subscription, creates a ServerToken, wipes any previous installation on the target server, and launches bootstrap. The deploy is IP-first (phase-1): the server comes up on plain HTTP at http://<IP>:3002 in 8-14 minutes; it does NOT get a domain or HTTPS cert here (that is an optional later step inside the workspace). Returns session_id (for a single on-demand check_status read — do not poll) and server_token (so the user can recover via retry_deploy if anything breaks). Call this AT MOST ONCE per conversation.

Parametersiprequiredlangemailrequiredloginpasswordrequiredterms_acceptedrequiredemail_confirmedrequiredcomponents_selectedrequired

check_status

Check Deployment Status

Read the current installation progress ONCE, on demand. Call this only when the user explicitly asks how the deploy is going (e.g. "what is the status", "did it finish") — never on a timer and never in a polling loop. The deploy takes 8-14 minutes and the authoritative status channels are the email pipeline + the dashboard; one read on request is enough. Returns the current step, the list of completed steps (~44 total in a full bootstrap), and whether installation is done or failed.

Parameterssession_idrequired

get_subdomain

Get Workspace Address

Return the final entry address of the server once installation is complete. In phase-1 (IP-first) this is a plain-HTTP Admin URL of the form http://<IP>:3002 — the server has NO domain and NO HTTPS cert yet (attaching a custom domain with HTTPS is an optional later step the user does inside Admin -> Personal Domain). Call this once after check_status reports status="done".

Parameterssession_idrequired

retry_deploy

Retry Failed Deployment

Retry a failed deployment using a server_token (from the failure email, the deploy-progress UI, or the dashboard). Wipes the previous broken install and runs a fresh deploy on the SAME server. Returns a new session_id — poll with check_status. Use this when the user reports a failed deploy or pastes a server_token.

Parametersiploginpasswordserver_tokenrequired

get_vps_recommendation

Get VPS Recommendation

Return a single recommended VPS provider for users who do not yet have a server. Call this ONLY when the user explicitly says they have no server. The user buys the VPS at this provider and comes back with IP + password.

Takes no parameters.

get_project_info

Get Project Information

Project reference / help desk about Fractera. Use this to answer ANY user question about what Fractera is, how it works, its architecture, components, modes, data ownership, pricing, use cases, partner program, etc. — especially while a deploy is running and the user wants to learn more. TOKEN-ECONOMY: call with NO arguments first to get the lightweight list of section ids+titles, then call again with a single `section` id to fetch just that section. NEVER try to fetch everything at once; pull only the section(s) relevant to the user question. Set `lang:"ru"` for Russian-speaking users.

Parameterslangsection

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

83% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.

Other Deploy integrations