# PubSpace (remote · pubspace.ai)

Publish HTML or markdown from your agent as a shareable link, with password or work-email walls.

- Trust score: 66/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

> **Recent critical change**: Authorization (2026-10-27). See the changelog below before you install this server.

## Components

- remote · `pubspace.ai`: 66/100 (this document), [markdown](https://verifymcp.io/servers/ai-pubspace-mcp/pubspace.md), [page](https://verifymcp.io/servers/ai-pubspace-mcp/pubspace)

## Channel facts

- Endpoint: `https://pubspace.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.25.1`

## 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 2026-11-05.

- **Endpoint Security**: 57/100
  - 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 (update_page).
  - 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.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 68/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1886 tokens (~235/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**: 30/100
  - Stability observed for 9 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.
- **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 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

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

PubSpace is a hosted endpoint at https://pubspace.ai/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 ai-pubspace-mcp 'https://pubspace.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-pubspace-mcp": {
      "url": "https://pubspace.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-pubspace-mcp": {
      "type": "http",
      "url": "https://pubspace.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-pubspace-mcp]
url = "https://pubspace.ai/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add ai-pubspace-mcp --url 'https://pubspace.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-pubspace-mcp:
    url: "https://pubspace.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-pubspace-mcp": {
      "Transport": "http",
      "Url": "https://pubspace.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-pubspace-mcp -t streamable-http -u 'https://pubspace.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-pubspace-mcp": {
      "type": "http",
      "url": "https://pubspace.ai/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.

### 2026-11-05 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 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.

### 2026-11-03 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 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.

### 2026-11-02 (score 64, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 1477 → 1886
- [functional] Server version: 0.24.3 → 0.25.1
- [functional] New tool “create_account”
- [functional] New tool “verify_email”

### 2026-10-31 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 62, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-27 (score 61, +28)

- [critical] Authorization: Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (update_page).
- [security improvement] Transport: unverified → pass
- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [functional regression] MCP protocol: unverified → fail
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: excellent
- [functional] First check of Schema quality: fail
- [functional] First check of Destructive annotations: 100
- [functional] First check of Tool coverage: 100

### 2026-10-26 (score 33)

First indexed and scored.

## MCP tools (8)

### `publish_page` (~285 tokens)

Publish a new page

Publish a new HTML (or Markdown) page to the maker's PubSpace space and get back a live, shareable URL to hand to the human. Pages are unlisted by default — indexed by search engines only if the maker turns that on later (Pro); anyone with the link can view. Use this only for a brand-new page; to change a page that already exists, call update_page so its URL stays the same (find the id with list_pages). Each call creates a page that counts toward the plan's live-page cap; at the cap the call fails with doc_limit_reached and, on the free plan, an upgrade link to relay to the human. Returns { url, id, mode, visibility, dashboardUrl }.

Input parameters:

- `html` (string, required): Full HTML document (or Markdown when source_type is "markdown"). Served byte-faithful apart from documented meta/bar injections.
- `project` (string): Optional: which body of work this page belongs to (e.g. "Q3 board pack"). Groups pages in the maker's library — reuse their existing project names from list_pages when one fits. (Renamed from `produc…
- `source_type` (string): Default "html".
- `title` (string): Optional title (used in the dashboard and social cards).

### `update_page` (~290 tokens)

Replace a page's content

Replace the content of an existing page in place: the same URL serves the new content immediately, so links the human already shared keep working. Use this instead of publish_page whenever the page already exists. The previous version stays restorable from the dashboard for 7 days (Pro keeps full version history). Pass draft: true to stage the update instead: nothing changes for viewers until the maker reviews the previewUrl and presses "Sync to live"; use it when the human asked to see changes before they go out. Fails with page_not_found if the id is not a live or offline page in this space.

Input parameters:

- `draft` (boolean): Default false (publishes live instantly). true = stage the update; relay the returned previewUrl so the human can review and press Sync. A new draft replaces any pending one.
- `html` (string, required): The complete new document (not a diff). HTML, or Markdown when source_type is "markdown".
- `page_id` (string, required): The page id: the `id` field from publish_page or list_pages (also the last path segment of the page URL, …/docs/<page_id>). Only pages in the connected maker's space are visible.
- `project` (string): Optional; omit to keep the existing project.
- `source_type` (string): Default "html".
- `title` (string): Optional; omit to keep the existing title.

### `list_pages` (~148 tokens)

List pages

List every page in the maker's space, newest first, with no paging: { total, pages: [{ id, title, url, project, views, live, workEmailGated, hasDraft, createdAt, updatedAt }] }. Read-only. Use it to find a page_id before update_page / get_page / unpublish_page / delete_page, or to reuse an existing project name. Offline pages are included (live: false); deleted pages are not. Pass q to search instead of scanning the full list; use get_page when you need one page's HTML.

Input parameters:

- `q` (string): Optional case-insensitive search over page titles and content. Omit to list everything.

### `get_page` (~199 tokens)

Get one page

Fetch one page by id: metadata always ({ id, title, url, project, views, live, workEmailGated, hasDraft, createdAt, updatedAt, visibility }), plus the stored HTML when include_html is true. Read-only. Use it to read a page before editing it with update_page; use list_pages to find ids or browse. Fails with page_not_found if the id is not in this space or the page was deleted.

Input parameters:

- `include_html` (boolean): Default false. true adds `html`: the document exactly as stored (the source you or the maker published, before serve-time injections). Can be large; only ask for it when you need the content.
- `page_id` (string, required): The page id: the `id` field from publish_page or list_pages (also the last path segment of the page URL, …/docs/<page_id>). Only pages in the connected maker's space are visible.

### `unpublish_page` (~169 tokens)

Take a page offline or back online

Take a page offline without deleting it: its URL shows an "offline" notice to viewers, and the content, id, URL and view count are kept. Pass restore: true to put it back online at the same URL. Prefer this over delete_page when the human wants a page hidden or paused. Calling it twice is harmless. Returns { ok, id, live }; fails with page_not_found if the id is not in this space.

Input parameters:

- `page_id` (string, required): The page id: the `id` field from publish_page or list_pages (also the last path segment of the page URL, …/docs/<page_id>). Only pages in the connected maker's space are visible.
- `restore` (boolean): Default false (take offline). true = put the page back online.

### `delete_page` (~144 tokens)

Delete a page

Delete a page: its URL stops working at once. The maker gets only a brief undo in the dashboard, then it is purged for good (there is no restore tool). Only use it when the human asked for deletion; to hide a page reversibly, use unpublish_page instead. Returns { ok, id, deleted }; fails with page_not_found if the id is not in this space or is already deleted.

Input parameters:

- `page_id` (string, required): The page id: the `id` field from publish_page or list_pages (also the last path segment of the page URL, …/docs/<page_id>). Only pages in the connected maker's space are visible.

### `create_account` (~263 tokens)

Create a PubSpace account for your human

Sign your human up for a free PubSpace space (no card) without leaving this session. Callable without an API key. Only call it after the human has told you their email and chosen a space name; never invent or guess either. Their pages will live at <subdomain>.pubspace.ai, so treat the name as permanent (renames are limited). A 6-digit verification code is emailed to them: ask them to read it to you, then call verify_email. Once verified, publish_page works in this same session. Returns { subdomain, email, apiKey, verificationRequired, connectHint }; persist the key with the connectHint command so future sessions start connected. Fails with email_taken (they already have an account: have them sign in and copy their key from Settings → Connect your agent), subdomain_taken, invalid_subdomain, invalid_email or rate_limited. If this session is already connected with a key, it fails with already_connected.

Input parameters:

- `email` (string, required): The human's real email address, as they gave it to you. The verification code goes here.
- `subdomain` (string, required): The space name the human chose: lowercase letters, numbers and hyphens. Becomes <subdomain>.pubspace.ai.

### `verify_email` (~104 tokens)

Verify the account email

Finish account verification with the 6-digit code PubSpace emailed to the human (ask them to read it to you). Publishing unlocks on success. Works in the session where create_account ran, or with an API key for an unverified account. Returns { ok, verified, subdomain }; fails with invalid_code (and attemptsRemaining), code_expired, too_many_attempts or already_verified.

Input parameters:

- `code` (string, required): The 6-digit code from the verification email.

## Diagnostics

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

## Score history

- 2026-11-05: 66
- 2026-11-04: 65
- 2026-11-03: 65
- 2026-11-02: 64
- 2026-11-01: 63
- 2026-10-31: 63
- 2026-10-30: 62
- 2026-10-29: 62
- 2026-10-28: 62
- 2026-10-27: 61
- 2026-10-26: 33

## Common questions

### What is the PubSpace MCP server?

PubSpace is an MCP server listed in the public MCP registry as ai.pubspace/mcp. Publish HTML or markdown from your agent as a shareable link, with password or work-email walls. This page covers its hosted endpoint (https://pubspace.ai/mcp).

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

PubSpace scores 66 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 PubSpace MCP server expose?

PubSpace exposes 8 tools: publish_page, update_page, list_pages, get_page, unpublish_page, and 3 more. Their descriptions and schemas cost roughly 1,602 tokens of context every time the server is loaded.

### Does the PubSpace MCP server require authentication?

No. We connected to PubSpace without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the PubSpace MCP server still maintained?

PubSpace is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the PubSpace MCP server?

VerifyMCP ran 13 checks on PubSpace, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://pubspace.ai/mcp
- Website: https://pubspace.ai/
- Changelog RSS feed: https://verifymcp.io/servers/ai-pubspace-mcp/pubspace.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-pubspace-mcp/pubspace/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/ai-pubspace-mcp/pubspace.json
- HTML version of this page: https://verifymcp.io/servers/ai-pubspace-mcp/pubspace