# Fractera (remote · www.fractera.ai)

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

- Trust score: 61/100 (medium)
- Change this week: +5
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `www.fractera.ai`: 61/100 (this document), [markdown](https://verifymcp.io/servers/fractera-deploy/api-mcp.md), [page](https://verifymcp.io/servers/fractera-deploy/api-mcp)

## Channel facts

- Endpoint: `https://www.fractera.ai/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (register_and_deploy).
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 53/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 5501 tokens (~687/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http fractera-deploy https://www.fractera.ai/api/mcp
```

### Codex

```toml
[mcp_servers.fractera-deploy]
url = "https://www.fractera.ai/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "fractera-deploy": {
      "type": "remote",
      "url": "https://www.fractera.ai/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add fractera-deploy --url https://www.fractera.ai/api/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  fractera-deploy:
    url: "https://www.fractera.ai/api/mcp"
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 61, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-01 (score 60, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 59, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 58, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-28 (score 57, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 56, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 55)

First indexed and scored.

## MCP tools (8)

### `register_and_deploy` (~671 tokens)

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.

Input parameters:

- `components` (array): Optional — which AI tools to install (lets the user save money on a smaller server). OMIT this to install the full recommended set (5 coding agents + Memory + Brain). Pass a subset of ["claude-code",…
- `components_selected` (boolean, required): REQUIRED, must be true. Set this ONLY after you have actually asked the component question (Q5) — told the user the full set is the default and asked, in three short steps, whether to keep all five c…
- `email` (string, required): The email the user typed (and confirmed by re-typing). Welcome / failure emails go here.
- `email_confirmed` (boolean, required): REQUIRED, must be true. Set this ONLY after the user has typed their email a SECOND time (Q2) and the two entries match (case-insensitive, trimmed). Do not set it if you only asked once.
- `ip` (string, required): IPv4 address of the user's VPS, e.g. 185.10.20.30.
- `login` (string): Optional — defaults to "root". Override only if the VPS provider gave a non-root username.
- `password` (string, required): Root password for the VPS.
- `terms_accepted` (boolean, required): REQUIRED, must be true. Set this ONLY after the user has explicitly confirmed in the chat that they (1) have read and agree to Fractera's Terms of Service (https://www.fractera.ai/en/terms) and Priva…

### `check_status` (~134 tokens)

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.

Input parameters:

- `session_id` (string, required): The session_id returned by register_and_deploy or retry_deploy.

### `get_subdomain` (~106 tokens)

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".

Input parameters:

- `session_id` (string, required): The session_id used during installation.

### `retry_deploy` (~239 tokens)

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.

Input parameters:

- `components` (array): Optional — same meaning as in register_and_deploy. OMIT to reinstall the full recommended toolset. Pass a subset (or [] for none) only if the user wants to change which AI tools are installed on this…
- `ip` (string): Optional — only pass if the user discovered the original IP was wrong (e.g. typo). Otherwise the stored IP is used.
- `login` (string): Optional — Linux user, defaults to root.
- `password` (string): Optional — only pass if the user discovered the original password was wrong. Otherwise the stored password is used.
- `server_token` (string, required): The unique server token the user received in the deploy-failure email, the active deploy UI, or the dashboard. Acts as the authorisation for this retry.

### `get_vps_recommendation` (~57 tokens)

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.

### `get_project_info` (~200 tokens)

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.

Input parameters:

- `lang` (string): Language of the returned content. Defaults to "en". Use "ru" for Russian-speaking users.
- `section` (string): A section id from the list returned when called with no section. Omit to get the list (table of contents) first.

### `get_ai_workspace_architect_info` (~227 tokens)

Get AI Workspace Architecture

Architecture reference for Fractera AI Workspace: what it is made of and how it works (the admin drives it through Hermes — chat Web UI or Telegram — or directly through the five coding agents; a modal subscription sign-in layer + MCP keep work resilient when a subscription is limited; LightRAG is the central memory that slashes token use; Hermes is a light orchestrator while the coding agents do the heavy lifting; the result ships over HTTPS on a custom domain or plain HTTP on an IP). RETURNS A DIAGRAM IMAGE URL you can show the user when they ask what Fractera is or how it works. Call with NO arguments to get the wide illustration URL + the core "how it works" scenario + the section list; call again with a single `section` id to read one entity in depth.

Input parameters:

- `section` (string): A section id from the list (e.g. "hermes", "lightrag", "coding-agents", "claude-code"). Omit to get the illustration, the overview scenario and the section list.

### `get_ai_development_loop_info` (~246 tokens)

Get Fractera Development Loop

Explains the Fractera development loop: how one admin request becomes tested, deployed, recorded code with no human writing it — Hermes orchestrates and loads its identity + project context, picks a ready coding agent (Claude Code, Codex, Gemini, Qwen, Kimi), the agent is enriched (SOUL.md / AGENTS.md / GLOSSARY.md / completed steps), generates a task then code, it is built and deployed, and the result branches (error feeds back; success updates the completed steps and the deployments tab) — all grounded by LightRAG memory at every step. RETURNS A DIAGRAM IMAGE URL you can show the user when they ask how Fractera builds software or how its agents work. Call with NO arguments to get the diagram URL + the "how the loop works" overview + the section list; call again with a single `section` id to read one stage in depth.

Input parameters:

- `section` (string): A section id from the list (e.g. "hermes", "lightrag", "test-deploy", "the-record"). Omit to get the diagram, the overview and the section list.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/fractera-deploy/api-mcp#diagnostics

## Score history

- 2026-08-03: 61
- 2026-08-02: 60
- 2026-08-01: 60
- 2026-07-31: 59
- 2026-07-30: 58
- 2026-07-29: 57
- 2026-07-28: 57
- 2026-07-27: 56
- 2026-07-26: 55

## Links

- Remote endpoint: https://www.fractera.ai/api/mcp
- Website: https://www.fractera.ai/
- Changelog RSS feed: https://verifymcp.io/servers/fractera-deploy/api-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/fractera-deploy/api-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/fractera-deploy/api-mcp