# Xenition (remote · api.xenition.com)

Docs, decks, forms, apps you build and deploy, automations, and AI images, video and voice.

- Trust score: 87/100 (high trust)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-16

## Components

- remote · `api.xenition.com`: 87/100 (this document), [markdown](https://verifymcp.io/servers/com-xenition-api-xenition/api.md), [page](https://verifymcp.io/servers/com-xenition-api-xenition/api)

## Channel facts

- Endpoint: `https://api.xenition.com/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `0.2.1`

## 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 2026-10-16.

- **Endpoint Security**: 92/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server supports Client ID Metadata Documents, the current MCP client-registration mechanism.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 89/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 9986 tokens (~96/item across 103 items; 71 tools + 32 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 43/100
  - Stability observed for 13 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 98/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 92% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 73 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).
  - Supports UI / widget rendering.

## Install

### How do I install the Xenition MCP server?

Xenition is a hosted endpoint at https://api.xenition.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-xenition-api-xenition 'https://api.xenition.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-xenition-api-xenition": {
      "url": "https://api.xenition.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-xenition-api-xenition": {
      "type": "http",
      "url": "https://api.xenition.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-xenition-api-xenition]
url = "https://api.xenition.com/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add com-xenition-api-xenition --url 'https://api.xenition.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-xenition-api-xenition:
    url: "https://api.xenition.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-xenition-api-xenition": {
      "Transport": "http",
      "Url": "https://api.xenition.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-xenition-api-xenition -t streamable-http -u 'https://api.xenition.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-xenition-api-xenition": {
      "type": "http",
      "url": "https://api.xenition.com/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.

### 2026-10-16 (score 87, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-14 (score 86, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-12 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 30. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-10 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 23. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-08 (score 83, +2)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 17. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-04 (score 81, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-03 (score 81)

First indexed and scored.

## MCP tools (71)

### `add_event` (~132 tokens)

Add a calendar event

Use this when the user wants to put a new event on their Xenition calendar (a meeting, call, deadline or reminder) with a start time. Returns the upcoming schedule. Do not use to change an existing event (use reschedule_event), and it cannot send invitations to anyone.

Input parameters:

- `end` (string): optional end, same format as start
- `location` (string)
- `notes` (string)
- `start` (string, required): start: YYYY-MM-DD for all-day, or YYYY-MM-DDTHH:MM for a timed event
- `title` (string, required): the event title

Output parameters:

- `count` (integer)
- `empty` (string)
- `items` (null|array)
- `title` (string)

### `add_ledger_entry` (~153 tokens)

Add an invoice or bill

Use this when the user wants to record an invoice, bill or receipt in their Xenition ledger — vendor, amount, due date, optionally already paid. Returns the ledger's invoices. Do not use to pay, send or email an invoice; Xenition has no payment or messaging channel.

Input parameters:

- `amount` (number, required): the invoice total
- `currency` (string): currency code, default USD
- `dueDate` (string): YYYY-MM-DD
- `invoiceNumber` (string)
- `kind` (string): invoice | receipt | credit_note (default invoice)
- `markPaid` (boolean): also mark it paid now
- `vendor` (string, required): the vendor / who the invoice is from

Output parameters:

- `count` (integer)
- `empty` (string)
- `items` (null|array)
- `title` (string)

### `add_note` (~97 tokens)

Add a note

Use this when the user wants to save something as a note in Xenition — an idea, a snippet, meeting jottings — with optional tags and notebook. Returns the saved note. For a long structured piece, use create_document instead.

Input parameters:

- `content` (string, required): the note body (markdown)
- `notebook` (string)
- `tags` (null|array)
- `title` (string): the note title (optional)

Output parameters:

- `artifact` (object)

### `add_rows` (~102 tokens)

Add rows to a spreadsheet

Use this when the user wants to append rows of data to one of their existing Xenition spreadsheets. Returns the updated sheet. Do not use to create a new spreadsheet (use create_spreadsheet) or to answer questions about the data (use query_spreadsheet).

Input parameters:

- `rows` (null|array, required): rows to append; each row is a list of cell values (strings)
- `sheet` (string): which spreadsheet (name); defaults to the most recent

Output parameters:

- `artifact` (object)

### `add_task` (~125 tokens)

Add a task

Use this when the user wants to add a task or card to one of their Xenition boards, optionally in a named column with a due date. Returns the updated board. To create a whole new board, use create_board.

Input parameters:

- `assignToMe` (boolean)
- `board` (string): which board (name); defaults to the most recent
- `column` (string): which column (name); defaults to the first
- `description` (string)
- `due` (string): due date YYYY-MM-DD
- `title` (string, required): the task title

Output parameters:

- `artifact` (object)

### `add_to_knowledge` (~199 tokens)

Save to your knowledge

Use this when the user wants Xenition to remember material so it can answer from it later — pasted notes, a policy, an article, or a public web page link (e.g. 'save this pricing page so I can ask about it'). Saves it privately to their knowledge; ask_workspace and their agents then answer from it with sources. Text or a web page only; PDFs and Word files are uploaded in Xenition. Do not use to create a document (use the document tools) or to answer a question now (use ask_workspace).

Input parameters:

- `text` (string): the material itself, pasted — notes, a policy, an article. Give text OR url, not both
- `title` (string): a short name for it, e.g. 'Pricing policy 2026'; the page title is used for a link if omitted
- `url` (string): a public https web page to save instead of pasted text

Output parameters:

- `chunks` (integer)
- `result` (string)
- `source` (string)
- `title` (string)

### `app_status` (~80 tokens)

Check an app build or deploy

Use this when the user asks how their app build or deploy is going, or whether it is live. Returns the build phase and file count while building, the finished app when built, and the live URLs once deployed. Needs the id returned by build_app.

Input parameters:

- `artifactId` (string, required): the app's id from build_app (or search_artifacts)

Output parameters:

- `apiUrl` (string)
- `artifactId` (string)
- `error` (string)
- `files` (integer)
- `liveUrl` (string)
- `mobileUrl` (string)
- `name` (string)
- `openUrl` (string)
- `phase` (string)
- `status` (string)

### `approve_action` (~43 tokens)

Approve a pending action

Approve a pending action awaiting the user's decision (from list_pending_approvals).

Input parameters:

- `id` (string, required): the pending action id (from list_pending_approvals)

Output parameters:

- `result` (string)

### `ask_workspace` (~76 tokens)

Ask your workspace

Use this when the user asks a question about their own Xenition content — their documents, notes, files or saved knowledge. Answers only from that content, with sources cited. Do not use for general knowledge or anything outside their workspace.

Input parameters:

- `question` (string, required): the question to answer from the user's own Xenition documents and saved knowledge

Output parameters:

- `answer` (string)
- `citations` (null|array)
- `question` (string)

### `build_app` (~181 tokens)

Build an app

Use this when the user wants a working web (or mobile) app built for them — e.g. a booking site, a CRM, an internal tool. Generates the full app (screens, API and database) in their Xenition workspace. Takes a few minutes: returns the app's id right away; check progress with app_status, then publish it with deploy_app. The user can also open the link to watch it build. To only open the builder with an idea, use create_app.

Input parameters:

- `idea` (string, required): what the app should do, in the user's words — e.g. 'a booking app for my yoga studio with classes, a timetable and member sign-up'
- `mobile` (boolean): also generate a native mobile app (takes longer)
- `name` (string): optional app name; the builder picks one from the idea otherwise

Output parameters:

- `apiUrl` (string)
- `artifactId` (string)
- `error` (string)
- `files` (integer)
- `liveUrl` (string)
- `mobileUrl` (string)
- `name` (string)
- `openUrl` (string)
- `phase` (string)
- `status` (string)

### `build_app_from_template` (~123 tokens)

Start an app from a template

Use this when the user picks one of Xenition's app templates (from find_app_templates) and wants their own working copy. Copies the full template into their Xenition workspace and publishes it to a live URL; publishing takes a few minutes and app_status reports the links. To generate a new app from a description instead, use build_app.

Input parameters:

- `name` (string): optional name for the user's copy; defaults to the template's name
- `templateId` (string, required): the template id from find_app_templates, e.g. 'tpl-danceschool'

Output parameters:

- `apiUrl` (string)
- `artifactId` (string)
- `error` (string)
- `files` (integer)
- `liveUrl` (string)
- `mobileUrl` (string)
- `name` (string)
- `openUrl` (string)
- `phase` (string)
- `status` (string)

### `check_3d_model` (~101 tokens)

Check a 3D model's progress

Check the status of a 3D model started by create_3d_model. Returns whether it is still generating, completed (with the model), or failed. The inline preview calls this automatically; you can also call it if the user asks whether their model is ready.

Input parameters:

- `artifactId` (string, required): the artifact id from create_3d_model
- `jobId` (string): the generation job id from create_3d_model

Output parameters:

- `artifactId` (string)
- `error` (string)
- `glbUrl` (string)
- `jobId` (string)
- `openUrl` (string)
- `prompt` (string)
- `quality` (string)
- `status` (string)
- `title` (string)

### `check_agent_run` (~84 tokens)

Check an agent run

Use this to check a background agent run started by run_agent, when the user asks whether it is done or what it found. Returns its status, the final answer when finished, and a link to view it in Xenition. An unknown id is reported as not found, not as still working.

Input parameters:

- `missionId` (string, required): the job id returned by run_agent

Output parameters:

- `agent` (string)
- `answer` (string)
- `done` (boolean)
- `error` (string)
- `failed` (boolean)
- `goal` (string)
- `missionId` (string)
- `openUrl` (string)
- `status` (string)

### `complete_task` (~73 tokens)

Complete a task

Use this when the user says a specific task is done and names it. Moves it to the board's done column and returns the updated board. If several tasks match or none is named, ask which one first.

Input parameters:

- `board` (string)
- `title` (string, required): the task to complete (matched by title)

Output parameters:

- `artifact` (object)

### `create_3d_model` (~225 tokens)

Create a 3D model

Generate a 3D model (glTF/GLB) in the user's Xenition workspace from a text prompt or a reference image. Starts generation and returns immediately; an interactive inline preview fills in as it renders (~30-60s, longer for 'realistic'), plus a link to open, edit, and export it (GLB/STL/OBJ) in Xenition. Use when the user asks for a 3D model, mesh, or asset. Best for a single object.

Input parameters:

- `imageUrl` (string): optional URL of a reference image to turn into 3D (image-to-3D); when set the prompt guides the conversion
- `prompt` (string, required): what the 3D model should be — a single object works best (e.g. 'a low-poly wooden sailboat')
- `quality` (string): 'draft' (default, fast) or 'realistic' (higher fidelity, slower — a few minutes)
- `title` (string): optional title for the saved model; defaults to the prompt

Output parameters:

- `artifactId` (string)
- `error` (string)
- `glbUrl` (string)
- `jobId` (string)
- `openUrl` (string)
- `prompt` (string)
- `quality` (string)
- `status` (string)
- `title` (string)

### `create_app` (~133 tokens)

Start an app in the builder

Use this when the user wants to open Xenition's no-code app builder themselves, pre-filled with their idea, to shape the app by hand. Returns the link. To have the app built for them from the conversation, use build_app instead.

Input parameters:

- `idea` (string, required): a clear description of the app to build, distilled from the conversation (e.g. 'a task tracker with projects, due dates, and team assignments')
- `mobile` (boolean): true to also target mobile (web + mobile), otherwise web only
- `name` (string): a short app name (e.g. 'Task Tracker')

Output parameters:

- `idea` (string)
- `mobile` (boolean)
- `name` (string)
- `openUrl` (string)

### `create_automation` (~294 tokens)

Schedule an automation

Use this when the user wants something done for them on a schedule — every day, on certain weekdays, or every few hours — e.g. 'every Monday at 9, summarise my sales sheet'. Creates a Xenition automation that runs on its own at those times, even when nobody is in this chat. Results appear in Xenition, and anything that would act in a connected app waits for the user's approval. Do not use for a one-off task now (use run_agent).

Input parameters:

- `agent` (string): optional agent slug from list_agents to run it; Xenition plans it otherwise
- `days` (null|array): for weekly: days like ['mon','thu']
- `every` (string): for every: an interval like '30m' or '6h' (15 minutes minimum)
- `frequency` (string, required): daily, weekly or every
- `name` (string, required): a short name, e.g. 'Monday sales summary'
- `task` (string, required): what the agent should do each time, in plain words — e.g. 'summarise last week's rows in my Sales sheet and draft an update'
- `time` (string): HH:MM, 24-hour, for daily and weekly — e.g. '09:00'
- `timezone` (string): IANA timezone for daily/weekly, e.g. 'Asia/Dhaka'; UTC if omitted

Output parameters:

- `enabled` (boolean)
- `id` (string)
- `name` (string)
- `openUrl` (string)
- `schedule` (string)
- `when` (string)

### `create_board` (~97 tokens)

Create a task board

Use this when the user wants a new Kanban board — columns and task cards — built from a brief, e.g. 'a board to plan our product launch'. Returns the board and a link to manage it. To add a single task to an existing board, use add_task.

Input parameters:

- `brief` (string, required): what to create — a topic, brief, or outline
- `title` (string): optional title for the saved artifact

Output parameters:

- `artifact` (object)

### `create_diagram` (~81 tokens)

Create a diagram

Use this when the user wants a diagram — flowchart, sequence, architecture, ER or mind map — created from a description. Returns the diagram and a link to open and edit it in Xenition.

Input parameters:

- `brief` (string, required): what to create — a topic, brief, or outline
- `title` (string): optional title for the saved artifact

Output parameters:

- `artifact` (object)

### `create_document` (~107 tokens)

Create a document

Use this when the user asks for a written piece — a report, article, letter, brief, essay or plan — to be created in their Xenition workspace. Returns the document and a link to open and edit it. For slides use create_slides; for a fill-in template such as an invoice or resume, use find_forms.

Input parameters:

- `brief` (string, required): what to create — a topic, brief, or outline
- `title` (string): optional title for the saved artifact

Output parameters:

- `artifact` (object)

### `create_image` (~114 tokens)

Create an image

Use this when the user wants an image made from a description — an illustration, photo-style picture, logo idea or background. Saves it to their Xenition library and returns the image link. To change an existing image, use edit_image.

Input parameters:

- `prompt` (string, required): what the image should show, with style details — e.g. 'a watercolor of a lighthouse at dawn'
- `reference` (string): optional https URL of an image to base it on
- `title` (string): optional name for the saved image

Output parameters:

- `artifactId` (string)
- `error` (string)
- `kind` (string)
- `openUrl` (string)
- `status` (string)
- `title` (string)
- `url` (string)

### `create_shared_form` (~103 tokens)

Create a shareable form

Create a fillable form with a public link anyone can use to submit responses (like a Google Form) — for surveys, sign-ups, feedback, RSVPs. Returns the shareable link; responses collect in Xenition. Use when the user wants to gather input from other people.

Input parameters:

- `collectEmail` (boolean): require the respondent's email
- `fields` (null|array, required): the fields to collect
- `title` (string, required): the form's title

Output parameters:

- `artifactId` (string)
- `shareUrl` (string)
- `title` (string)
- `token` (string)
- `type` (string)

### `create_slides` (~128 tokens)

Create a slide deck

Create a polished, designed presentation deck in the user's Xenition workspace from a brief or topic. Returns the deck's slides (shown as an inline preview) plus a link to open and edit it in Xenition. Use when the user asks for slides, a deck, a presentation, or a pitch deck.

Input parameters:

- `brief` (string, required): what the deck is about — a topic, brief, or outline (e.g. 'a 10-slide investor pitch for a solar-panel startup')
- `title` (string): optional title for the saved deck; defaults to a title the engine chooses

Output parameters:

- `artifactId` (string)
- `openUrl` (string)
- `slideCount` (integer)
- `slides` (null|array)
- `theme` (object)
- `title` (string)

### `create_speech` (~96 tokens)

Turn text into speech

Use this when the user wants text read aloud as an audio file — a voiceover, narration or spoken message. Returns an MP3 link and saves it to their Xenition library.

Input parameters:

- `language` (string): optional language code, e.g. 'en', 'es', 'ja'
- `text` (string, required): the words to speak
- `title` (string)
- `voice` (string): optional voice name

Output parameters:

- `artifactId` (string)
- `error` (string)
- `kind` (string)
- `openUrl` (string)
- `status` (string)
- `title` (string)
- `url` (string)

### `create_spreadsheet` (~96 tokens)

Create a spreadsheet

Use this when the user wants a new spreadsheet or data table — a budget, tracker, schedule or list with formulas where useful — created in their Xenition workspace. Returns the sheet and a link to open it. To add rows to an existing sheet, use add_rows.

Input parameters:

- `brief` (string, required): what to create — a topic, brief, or outline
- `title` (string): optional title for the saved artifact

Output parameters:

- `artifact` (object)

### `create_video` (~159 tokens)

Create a video clip

Use this when the user wants a short AI video clip made from a description. Starts the video and returns its id right away; generating takes a few minutes, and video_status reports when it is ready with the file link. The clip is saved to their Xenition library.

Input parameters:

- `aspect` (string): 'landscape' (16:9, default), 'portrait' (9:16) or 'square'
- `duration` (integer): length in seconds (the model may cap it; short clips of 5–10 s work best)
- `prompt` (string, required): what happens in the clip, with camera and style — e.g. 'slow drone shot over a misty pine forest at sunrise'
- `title` (string)

Output parameters:

- `artifactId` (string)
- `error` (string)
- `kind` (string)
- `openUrl` (string)
- `status` (string)
- `title` (string)
- `url` (string)

### `deny_action` (~43 tokens)

Deny a pending action

Deny a pending action awaiting the user's decision (from list_pending_approvals).

Input parameters:

- `id` (string, required): the pending action id (from list_pending_approvals)

Output parameters:

- `result` (string)

### `deploy_app` (~102 tokens)

Publish an app

Use this when the user wants their built Xenition app published to a live URL. Deploys the app from build_app (it must have finished building — check app_status) and returns right away; deploying takes a few minutes, and app_status reports the live URLs. Publishing makes the app reachable by anyone with the link, so only do it when the user asks.

Input parameters:

- `artifactId` (string, required): the app's id from build_app (or search_artifacts)

Output parameters:

- `apiUrl` (string)
- `artifactId` (string)
- `error` (string)
- `files` (integer)
- `liveUrl` (string)
- `mobileUrl` (string)
- `name` (string)
- `openUrl` (string)
- `phase` (string)
- `status` (string)

### `discover_search` (~325 tokens)

Search public listings

Look up real, current information from open public sources: jobs, hospitals, clinics, pharmacies, banks, schools, universities, companies, government offices. Reads the sources live at the moment of asking rather than from a stored copy, so it is current. Place types (hospitals, schools, banks, pharmacies, clinics, government offices) REQUIRE `near`. Always tell the user which sources answered and when. Each result may carry `phone`, `website`, `address`, `lat`/`lng` and a `detail` map (salary, cuisine, opening hours). QUOTE THEM — a phone number or an apply link that came back and was not shown is the answer the user asked for, thrown away. Do NOT web-search for a detail that is already in the result. Where a field is genuinely absent, say so for that entry rather than searching again.

Input parameters:

- `lat` (number): latitude of the user, when the conversation states it — use with lng instead of guessing a place name for 'near me'
- `lng` (number): longitude of the user, when the conversation states it
- `near` (string): a place — a city, an address, a neighbourhood
- `query` (string): what to look for — a job title, a company name, a university
- `radiusKm` (integer): how far to look, in kilometres (default 5)
- `type` (string, required): which catalogue: jobs, hospitals, clinics, pharmacies, banks, schools, universities, companies, gov_offices, events, flights

Output parameters:

- `count` (integer)
- `empty` (string)
- `items` (null|array)
- `title` (string)

### `discover_sources` (~59 tokens)

List public listing sources

Say where a Discover answer comes from: which public sources would be asked for a data type, and under what licence. Use when the user asks how we know something, or whether the information can be trusted.

Input parameters:

- `type` (string, required): which catalogue

Output parameters:

- `count` (integer)
- `empty` (string)
- `items` (null|array)
- `title` (string)

### `edit_app` (~145 tokens)

Change an app

Use this when the user wants to change an app they built in Xenition — add a feature, change a screen, restyle it, fix something — described in plain words. Rewrites the affected files and saves a new version of the app. If the app is already live, the change is not published until deploy_app is called again. The app must have finished building (check app_status).

Input parameters:

- `artifactId` (string, required): the app's id from build_app, build_app_from_template or search_artifacts
- `instruction` (string, required): the change in plain words — e.g. 'add a dark mode toggle', 'make the booking form ask for a phone number'

Output parameters:

- `apiUrl` (string)
- `artifactId` (string)
- `error` (string)
- `files` (integer)
- `liveUrl` (string)
- `mobileUrl` (string)
- `name` (string)
- `openUrl` (string)
- `phase` (string)
- `status` (string)

### `edit_artifact` (~122 tokens)

Edit a saved item

Use this when the user wants one of their existing Xenition items changed in place — rewrite, shorten, expand, change tone, fix grammar or translate. Saves a new version and returns it. Best for documents and notes. To only suggest changes without editing, use review_artifact.

Input parameters:

- `artifactId` (string, required): the id of the artifact to edit (from search_artifacts / get_artifact)
- `instruction` (string, required): what to change, in plain language (e.g. 'make it shorter', 'translate to Spanish', 'more formal tone')

Output parameters:

- `artifact` (object)

### `edit_image` (~149 tokens)

Edit an image

Use this when the user wants an existing image changed: edit it by instruction, upscale, remove the background, enhance, erase something, restyle, colorize, restore, expand the canvas, or make a variation. Saves the result as a new image in their Xenition library; the original is kept.

Input parameters:

- `image` (string, required): https URL of the image to edit (e.g. from create_image)
- `operation` (string, required): one of: edit, upscale, background-removal, enhance, erase, stylize, colorize, restore, expand, variation
- `prompt` (string): what to change, for edit / erase / stylize
- `title` (string)

Output parameters:

- `artifactId` (string)
- `error` (string)
- `kind` (string)
- `openUrl` (string)
- `status` (string)
- `title` (string)
- `url` (string)

### `edit_video` (~163 tokens)

Edit a video

Use this when the user wants an existing video improved: burned-in captions, enhanced picture and sound, the background removed, or silences cut out (jump cut). Starts the edit and returns an id right away; video_status reports when the new video is ready. The original is kept; the result is saved to their Xenition library.

Input parameters:

- `language` (string): for captions: the spoken language code, e.g. 'en'
- `operation` (string, required): captions (burn in subtitles), enhance (clean up picture and sound), matte (remove the background) or jumpcut (cut out silences)
- `title` (string)
- `video` (string, required): https URL of the video to edit (e.g. from create_video or the user's library)

Output parameters:

- `artifactId` (string)
- `error` (string)
- `kind` (string)
- `openUrl` (string)
- `status` (string)
- `title` (string)
- `url` (string)

### `export_pdf` (~83 tokens)

Export a document as PDF

Use this when the user wants one of their Xenition documents as a PDF file — to download, print or attach. Returns a link to the PDF. Works for documents (reports, letters, articles); for slides, sheets or notes, open them in Xenition to export.

Input parameters:

- `artifactId` (string, required): the document's id from search_artifacts or create_document

Output parameters:

- `artifactId` (string)
- `title` (string)
- `url` (string)

### `extract_from_artifact` (~109 tokens)

Extract details from a document

Use this when the user wants a specific kind of information pulled out of one of their Xenition documents as a list — names, dates, figures, action items, tasks. Answers only from that document. To ask a free question about it, use query_document.

Input parameters:

- `artifactId` (string, required): the artifact to extract from
- `what` (string, required): what to pull out, in plain language (e.g. 'all email addresses', 'the key dates', 'every action item')

Output parameters:

- `artifactId` (string)
- `body` (string)
- `formula` (string)
- `heading` (string)
- `openUrl` (string)
- `question` (string)
- `title` (string)

### `find_app_templates` (~163 tokens)

Find an app template

Use this when the user wants a ready-made app for a kind of business — a dance school, restaurant, clinic, store, CRM — to start from. Searches Xenition's ~200 full-stack templates (web app, API and database, each with a live demo) and returns matches with their demo links. To start the user's own copy, pass a template id to build_app_from_template.

Input parameters:

- `category` (string): optional category, e.g. 'fitness-sports', 'food-drink', 'health-wellness'
- `limit` (integer): max results (default 6, max 12)
- `query` (string): what the app is for — e.g. 'dance school', 'restaurant', 'CRM', 'clinic booking'

Output parameters:

- `count` (integer)
- `empty` (string)
- `items` (null|array)
- `title` (string)

### `find_forms` (~122 tokens)

Find a document generator

Search Xenition's library of ready-made forms (invoice, resume, proposal, meeting agenda, job description, and ~200 more). Returns matching forms with their fields, shown as a fillable form the user can complete right here to generate a document. Use when the user wants to create a specific kind of document or fill out a form.

Input parameters:

- `limit` (integer): max results to return (default 6)
- `query` (string, required): what the user wants to make — e.g. 'invoice', 'resume', 'business proposal', 'meeting agenda'

Output parameters:

- `forms` (null|array)

### `find_tools` (~110 tokens)

Find a built-in tool

Use this when the user asks for a calculator, converter or generator (loan, currency, BMI, age, QR code and ~200 more) and you need the tool's id. Returns matching tools with links. To get an answer from the tool, pass its id to run_tool.

Input parameters:

- `limit` (integer): max results to return (default 6)
- `query` (string, required): what the user wants — e.g. 'loan calculator', 'currency converter', 'BMI', 'qr code'

Output parameters:

- `tools` (null|array)

### `form_responses` (~101 tokens)

Read form responses

Use this when the user wants to see what people submitted to a shareable form they made with create_shared_form — sign-ups, survey answers, RSVPs, feedback. Takes the form's link. Returns the responses, newest first, each with its answers and time. Only works for forms the user owns.

Input parameters:

- `form` (string, required): the form's share link (https://xenition.com/f/…) or its token, from create_shared_form

Output parameters:

- `count` (integer)
- `empty` (string)
- `items` (null|array)
- `title` (string)

### `get_artifact` (~109 tokens)

Open a saved item

Use this when the user wants to read or open one specific item — a document, deck, spreadsheet, note or other artifact — and you have its id (from search_artifacts or an earlier result). Returns its content. Very long items come back cut to the first part; use query_document or summarize_artifact to work with the whole thing. Do not use to find items; use search_artifacts.

Input parameters:

- `id` (string, required): the artifact id, e.g. art_abc123

Output parameters:

- `artifact` (object)

### `get_mission` (~63 tokens)

Get an agent run

Use this when the user asks about one specific Xenition mission (a long-running multi-agent job) by id. Returns its status and results. To see all missions, use list_missions.

Input parameters:

- `id` (string, required): the mission id (from list_missions)

Output parameters:

- `result` (string)

### `import_file` (~270 tokens)

Import a file into your workspace

Use this when the user wants to bring a file's content into their Xenition workspace — e.g. they attached or pasted a document and want it saved. Pass UTF-8 text in textContent, or other content base64-encoded in base64Content, with contentMimeType. Saves it as an editable document that summarize_artifact, query_document, ask_workspace and edit_artifact can work on. Supports text, Markdown, CSV, JSON, HTML and PDF. To bring in a page from the web instead, use add_to_knowledge with its URL.

Input parameters:

- `base64Content` (string): the file's content, base64-encoded. Use this for non-UTF-8 files such as a PDF. Set either this or textContent, not both.
- `contentMimeType` (string): the MIME type of the content, e.g. 'text/markdown', 'text/csv', 'text/html', 'application/pdf'. Recommended so the content is handled correctly.
- `textContent` (string): the file's UTF-8 text content. Use this for text, Markdown, CSV, JSON or HTML. Set either this or base64Content, not both.
- `title` (string, required): a title for the saved file, e.g. 'Q3 Board Notes'

Output parameters:

- `artifactId` (string)
- `chars` (integer)
- `openUrl` (string)
- `title` (string)
- `type` (string)

### `list_agents` (~47 tokens)

List your agents

Use this when the user asks what Xenition agents (named AI workers) they have, or before run_agent to pick the right one. Returns each agent with its name and what it does.

Output parameters:

- `count` (integer)
- `empty` (string)
- `items` (null|array)
- `title` (string)

### `list_automations` (~47 tokens)

List automations

Use this when the user asks what automations they have, when they run, or whether one is paused. Returns each with its schedule, on/off state, last run and id.

Output parameters:

- `count` (integer)
- `empty` (string)
- `items` (null|array)
- `title` (string)

### `list_connected_apps` (~51 tokens)

List connected apps

Use this when the user asks which third-party apps (Gmail, Slack, Notion, …) are connected to their Xenition account. Read-only; it cannot connect new apps or act in them.

Output parameters:

- `count` (integer)
- `empty` (string)
- `items` (null|array)
- `title` (string)

### `list_events` (~87 tokens)

List calendar events

Use this when the user asks what is on their Xenition calendar for a range — today, this week, a date, or upcoming. Returns the events with times and links. For a combined view of today's events, tasks and approvals, use my_agenda.

Input parameters:

- `range` (string): today | week | month | a YYYY-MM-DD date; default upcoming (next 30 days)

Output parameters:

- `count` (integer)
- `empty` (string)
- `items` (null|array)
- `title` (string)

### `list_missions` (~47 tokens)

List agent runs

Use this when the user asks what missions (long-running multi-agent jobs) they have in Xenition and how they are going. Returns each with its status and id for get_mission.

Output parameters:

- `count` (integer)
- `empty` (string)
- `items` (null|array)
- `title` (string)

### `list_pending_approvals` (~46 tokens)

List actions awaiting approval

List actions the user's assistant/agents are waiting on the user to approve (the 7A approval gate). Each item's id can be passed to approve_action or deny_action.

Output parameters:

- `count` (integer)
- `empty` (string)
- `items` (null|array)
- `title` (string)

### `list_tasks` (~85 tokens)

List board tasks

Use this when the user asks what tasks are open on their Xenition boards — optionally one board, only theirs, or only overdue ones. Returns each task with its board, column, due date and link.

Input parameters:

- `board` (string): optional board name to scope to
- `mine` (boolean): only tasks assigned to me
- `overdue` (boolean): only overdue tasks

Output parameters:

- `count` (integer)
- `empty` (string)
- `items` (null|array)
- `title` (string)

### `mark_paid` (~202 tokens)

Mark an invoice paid

Mark a specific invoice in the user's own Xenition ledger as paid. This changes financial records, so it is a confirmed, two-step action: first call it WITHOUT `confirmed` to preview exactly which invoice would change, relay that to the user, and only call again with `confirmed:true` after they explicitly agree. When the user asks to mark ALL/EVERY/multiple unpaid invoices paid, list the affected invoices and get the user's confirmation before marking any. Returns the ledger's invoices.

Input parameters:

- `amount` (number): amount paid (default the invoice total)
- `confirmed` (boolean): set true ONLY after the user has explicitly confirmed this invoice should be marked paid; leave false/absent on the first attempt so they can review and confirm
- `invoiceNumber` (string): the invoice number, if you know it
- `on` (string): date paid YYYY-MM-DD (default today)
- `vendor` (string, required): the invoice's vendor (matched)

Output parameters:

- `count` (integer)
- `empty` (string)
- `items` (null|array)
- `title` (string)

### `meeting_notes` (~106 tokens)

Turn a meeting into notes

Turn a meeting or call transcript into clean notes, decisions, and action items (with owners and due dates), saved to the user's Xenition workspace. Use when the user pastes a transcript or asks to summarize a call into notes and tasks.

Input parameters:

- `notes` (string): optional rough notes to clean up and anchor to the transcript
- `title` (string): optional meeting title
- `transcript` (string, required): the meeting/call transcript text (one line per utterance is ideal)

Output parameters:

- `actions` (null|array)
- `artifactId` (string)
- `decisions` (null|array)
- `notes` (null|array)
- `openUrl` (string)
- `title` (string)

### `move_task` (~81 tokens)

Move a task

Use this when the user wants a specific task moved to another column on its board (e.g. to 'In progress'). Returns the updated board. Ask which task if the name is ambiguous.

Input parameters:

- `board` (string)
- `title` (string, required): the task to move (matched by title)
- `toColumn` (string, required): the destination column name

Output parameters:

- `artifact` (object)

### `my_agenda` (~105 tokens)

Show my agenda

The user's day at a glance from Xenition: today's calendar events, tasks due today or overdue, and anything awaiting approval. Use ONLY when the user explicitly asks about their day, schedule, or agenda — e.g. 'what does my day look like', 'what's on my plate today'. Do NOT use it as a fallback for vague requests like 'just handle it' or 'take care of the rest' — for those, ask the user what they mean instead.

Output parameters:

- `count` (integer)
- `empty` (string)
- `items` (null|array)
- `title` (string)

### `publish_artifact` (~85 tokens)

Publish a shareable link

Publish an existing Xenition artifact as a public, read-only link anyone can open without signing in. Returns the shareable URL. Use when the user wants to share a document, deck, sheet, board, or other artifact.

Input parameters:

- `artifactId` (string, required): the id of the artifact to publish (from search_artifacts, get_artifact, or a create_* tool)

Output parameters:

- `artifactId` (string)
- `shareUrl` (string)
- `title` (string)
- `token` (string)
- `type` (string)

### `query_document` (~82 tokens)

Ask about a document

Answer a question about, or find a specific thing inside, ONE of the user's Xenition documents (grounded only in that document). Use to look something up in a specific file the user names.

Input parameters:

- `artifactId` (string, required): the document to search/answer from
- `question` (string, required): what to find or ask about the document, in plain language

Output parameters:

- `artifactId` (string)
- `body` (string)
- `formula` (string)
- `heading` (string)
- `openUrl` (string)
- `question` (string)
- `title` (string)

### `query_ledger` (~139 tokens)

Look up invoices and bills

List the user's own Xenition ledger invoices with paid/unpaid status. Optionally filter to a vendor or only unpaid ones. Use ONLY when the user is asking to see or total invoices already recorded in their Xenition ledger — e.g. 'what invoices are unpaid', 'how much do I owe vendor X'. Do NOT use it to send, text, email, or deliver an invoice to anyone (Xenition cannot send communications), and do NOT use it to look up invoices that are not in the user's Xenition ledger.

Input parameters:

- `unpaidOnly` (boolean): only unpaid invoices
- `vendor` (string): only invoices from this vendor

Output parameters:

- `count` (integer)
- `empty` (string)
- `items` (null|array)
- `title` (string)

### `query_spreadsheet` (~98 tokens)

Ask about a spreadsheet

Answer a question or compute a result over one of the user's Xenition spreadsheets — sums, trends, lookups, or 'what does this data say'. Returns the answer and, when relevant, a suggested formula.

Input parameters:

- `artifactId` (string, required): the spreadsheet artifact to query
- `question` (string, required): a question to compute/answer over the sheet (e.g. 'total revenue in Q3', 'which region grew fastest')

Output parameters:

- `artifactId` (string)
- `body` (string)
- `formula` (string)
- `heading` (string)
- `openUrl` (string)
- `question` (string)
- `title` (string)

### `repurpose_artifact` (~151 tokens)

Turn an item into another format

Use this when the user wants one of their Xenition items turned into a different format: a task board, calendar events, a form or a slide deck — e.g. meeting notes into a board of action items, or a document into a deck. Creates a new item and returns it; the original is unchanged.

Input parameters:

- `artifactId` (string, required): the source artifact to repurpose (from search_artifacts / get_artifact)
- `target` (string, required): what to turn it into: 'board' (tasks), 'calendar' (events), 'form', or 'slides' (a deck)
- `title` (string): optional title for the new artifact; defaults to the source title

Output parameters:

- `artifact` (object)

### `reschedule_event` (~92 tokens)

Reschedule an event

Use this when the user wants to move an existing Xenition calendar event to a new time. Returns the upcoming schedule. Ask which event if several share the name; to add a new event use add_event.

Input parameters:

- `end` (string): new end (optional)
- `start` (string, required): new start, same format as add_event
- `title` (string, required): the event to move (matched by title)

Output parameters:

- `count` (integer)
- `empty` (string)
- `items` (null|array)
- `title` (string)

### `review_artifact` (~72 tokens)

Review a document

Review one of the user's Xenition documents and return constructive comments — each tied to a quoted passage — on clarity, structure, and correctness. Non-destructive: it suggests, it doesn't edit (use edit_artifact to apply changes).

Input parameters:

- `artifactId` (string, required): the artifact to review (best for documents)

Output parameters:

- `artifactId` (string)
- `comments` (null|array)
- `openUrl` (string)
- `title` (string)

### `run_agent` (~105 tokens)

Run an agent

Use this when the user wants one of their Xenition agents to work on a task in the background (research can take a few minutes). Returns a run id right away; progress, the final result and a link appear as it finishes, and check_agent_run reports on it. Call list_agents first if you do not know the agent.

Input parameters:

- `input` (string): the task/prompt for the agent
- `slug` (string, required): the agent's slug (from list_agents)

Output parameters:

- `agent` (string)
- `answer` (string)
- `done` (boolean)
- `error` (string)
- `failed` (boolean)
- `goal` (string)
- `missionId` (string)
- `openUrl` (string)
- `status` (string)

### `run_tool` (~270 tokens)

Run a built-in tool

Use this when the user wants an answer from one of Xenition's built-in tools — a unit conversion (length, weight, volume, area, speed, data size, energy, pressure, and more), a loan payment, BMI, tip split, discount, sales tax, percentage, temperature or age. Returns the computed answer. For interactive tools (timers, QR codes, live weather) it returns what the tool needs and a link that opens it ready to use. Call find_tools first if you do not know the tool id. Do not use for general maths you can do yourself, or for anything that is not a built-in tool.

Input parameters:

- `inputs` (object): the tool's inputs. Converters: {value, from, to} using the unit names find_tools/run_tool report (e.g. {value: 5, from: 'km', to: 'mi'}). Calculators: see each tool's inputs — e.g. loan {amount, annu…
- `tool` (string, required): the tool id from find_tools, e.g. 'loan', 'bmi', 'length-convert', 'temperature'

Output parameters:

- `computed` (boolean)
- `inputs` (null|array)
- `openUrl` (string)
- `result` (string)
- `title` (string)
- `tool` (string)
- `units` (null|array)

### `search_artifacts` (~153 tokens)

Search your workspace

Search the signed-in user's own Xenition artifacts (documents, slides, sheets, media, code) and return matches. Use ONLY when the user is explicitly looking for their existing content. Do NOT call it to check whether an unsupported or out-of-scope action is possible, to find another person's content, or as a first step toward a bulk/irreversible action — confirm or decline those first.

Input parameters:

- `project` (string): optional project id to scope the search
- `query` (string): free-text search over the user's artifacts
- `type` (string): filter by type: document, slides, sheet, image, media, code
- `workspace` (string): optional workspace id to scope the search

Output parameters:

- `artifacts` (null|array)
- `total` (integer)

### `search_marketplace` (~150 tokens)

Search the marketplace

Use this when the user is looking for a ready-made digital product to buy or download — a template, e-book, design pack or app — from creators on the Xenition Marketplace. Returns matching listings with price and a link to each listing page. Do not use for the user's own files (search_artifacts) or for Xenition's free built-in templates (find_app_templates, find_forms).

Input parameters:

- `category` (string): optional category: design, documents or apps
- `limit` (integer): max results (default 6, max 12)
- `query` (string): what the user is looking for — e.g. 'resume template', 'budget tracker', 'kids coloring book'

Output parameters:

- `count` (integer)
- `empty` (string)
- `items` (null|array)
- `title` (string)

### `search_notes` (~92 tokens)

Search notes

Use this when the user is looking for one of their Xenition notes by words, tag or notebook. Returns matching notes with links. To search all their content (documents, decks, sheets), use search_artifacts.

Input parameters:

- `notebook` (string): only notes in this notebook
- `query` (string): free text to match in the note title/content
- `tag` (string): only notes with this tag

Output parameters:

- `count` (integer)
- `empty` (string)
- `items` (null|array)
- `title` (string)

### `set_automation_enabled` (~78 tokens)

Pause or resume an automation

Use this when the user wants to pause one of their automations or turn a paused one back on. Needs the automation's id from list_automations.

Input parameters:

- `enabled` (boolean, required): false to pause it, true to resume it
- `id` (string, required): the automation's id from list_automations or create_automation

Output parameters:

- `result` (string)

### `submit_form` (~114 tokens)

Generate a document from a form

Submit a filled Xenition form (from find_forms) to generate its document. Saves the result to the user's workspace and returns it. Usually called by the form widget when the user clicks submit.

Input parameters:

- `formId` (string, required): the form id from find_forms (e.g. 'invoice', 'resume')
- `title` (string): optional title for the produced document
- `values` (object, required): the filled field values, keyed by field name; a list field is an array of objects keyed by its sub-field names

Output parameters:

- `artifact` (object)

### `summarize_artifact` (~117 tokens)

Summarize a document

Use this when the user wants a summary of one of their Xenition documents, notes or research — a TL;DR, key points, action items or a fuller summary. Works on long documents in full. Do not use to change the document (use edit_artifact).

Input parameters:

- `artifactId` (string, required): the artifact to summarize (from search_artifacts / get_artifact)
- `style` (string): 'tldr' (default, short), 'key_points' (bulleted), 'action_items', or 'detailed'

Output parameters:

- `artifactId` (string)
- `body` (string)
- `formula` (string)
- `heading` (string)
- `openUrl` (string)
- `question` (string)
- `title` (string)

### `transcribe_audio` (~155 tokens)

Transcribe a recording

Use this when the user wants the words from an audio or video recording — a meeting, lecture, interview or voice memo — and gives a link to the file (https, up to 25 MB). Returns the transcript and saves it as a document in their Xenition workspace. To turn it into notes and action items, pass the text to meeting_notes.

Input parameters:

- `language` (string): optional spoken language code, e.g. 'en', 'es'; detected when omitted
- `title` (string): optional name for the saved transcript
- `url` (string, required): https link to an audio or video file (mp3, m4a, wav, mp4, webm …), up to 25 MB

Output parameters:

- `artifactId` (string)
- `openUrl` (string)
- `text` (string)
- `title` (string)
- `truncated` (boolean)

### `video_status` (~63 tokens)

Check a video

Use this when the user asks whether a video from create_video or edit_video is ready. Returns generating, the finished file link, or why it failed. Needs the id from create_video or edit_video.

Input parameters:

- `artifactId` (string, required): the id returned by create_video

Output parameters:

- `artifactId` (string)
- `error` (string)
- `kind` (string)
- `openUrl` (string)
- `status` (string)
- `title` (string)
- `url` (string)

## Diagnostics

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

## Score history

- 2026-10-16: 87
- 2026-10-15: 86
- 2026-10-14: 86
- 2026-10-13: 85
- 2026-10-12: 85
- 2026-10-10: 84
- 2026-10-08: 83
- 2026-10-04: 81
- 2026-10-03: 81

## Common questions

### What is the Xenition MCP server?

Xenition is an MCP server listed in the public MCP registry as com.xenition.api/xenition. Docs, decks, forms, apps you build and deploy, automations, and AI images, video and voice. This page covers its hosted endpoint (https://api.xenition.com/mcp).

### Is the Xenition MCP server safe to use?

Xenition scores 87 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Xenition MCP server expose?

Xenition exposes 71 tools: add_event, add_ledger_entry, add_note, add_rows, add_task, and 66 more. Their descriptions and schemas cost roughly 8,360 tokens of context every time the server is loaded.

### Does the Xenition MCP server require authentication?

Yes. Xenition asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the Xenition MCP server still maintained?

Xenition is still listed as active in the MCP registry. We last reached this channel on 16 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://api.xenition.com/mcp
- Repository: https://github.com/xenition/xenition-mcp
- Website: https://xenition.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-xenition-api-xenition/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-xenition-api-xenition/api.json
- HTML version of this page: https://verifymcp.io/servers/com-xenition-api-xenition/api