Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

ai.spideriq/publish

NPM · @SPIDERIQ/MCP-PUBLISH · SCANNED SEP 25

SpiderIQ Publish: content platform MCP (pages, posts, templates, components, domains, media)

0 this week 67 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security81
  • No malware found by supply-chain analysis.Pass
  • CVE check failed: a known high-severity CVE affects sharp 0.33.5, a direct dependency. A fixed version is available. View diagnostics → Fail
  • No install/post-install scripts declared.Pass
  • 33 of 132 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency19
  • Repository check failed: the declared repository URL returned HTTP 404. See how to fix → View diagnostics → Fail
  • Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 20 days ago).Pass
  • Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability61
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 36639 tokens (~234/item across 156 items; 156 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management87
  • Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage91
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 72% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 23 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "logout" implies "remove" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 156 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the ai.spideriq/publish MCP server?

ai.spideriq/publish runs locally as an npm package, launched with npx -y @spideriq/mcp-publish. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @spideriq/mcp-publish

# add to Claude Code
claude mcp add ai-spideriq-publish -- npx -y @spideriq/mcp-publish
// .cursor/mcp.json
{
  "mcpServers": {
    "ai-spideriq-publish": {
      "command": "npx",
      "args": [
        "-y",
        "@spideriq/mcp-publish"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "ai-spideriq-publish": {
      "command": "npx",
      "args": [
        "-y",
        "@spideriq/mcp-publish"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add ai-spideriq-publish -- npx -y @spideriq/mcp-publish
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-spideriq-publish": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@spideriq/mcp-publish"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add ai-spideriq-publish --command npx --arg -y --arg @spideriq/mcp-publish
# ~/.hermes/config.yaml
mcp_servers:
  ai-spideriq-publish:
    command: "npx"
    args: ["-y", "@spideriq/mcp-publish"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "ai-spideriq-publish": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@spideriq/mcp-publish"
      ]
    }
  }
}
# add to Vellum
assistant mcp add ai-spideriq-publish -t stdio -c npx -a -y @spideriq/mcp-publish
// mcp.json
{
  "mcpServers": {
    "ai-spideriq-publish": {
      "command": "npx",
      "args": [
        "-y",
        "@spideriq/mcp-publish"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 25 Sept 26 +1
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 23 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 22 Sept 26 +1
    • Stability: 0.97 → pass security
  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 15 Sept 26 +1
    • Stability: 0.97 → pass security
  • 13 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 25 Sept 2026 · Analysed npm/@spideriq/mcp-publish@1.25.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Vulnerabilities 2 findings
ID CVE Severity Vector Fix available
GHSA-f88m-g3jw-g9cj high yes
GHSA-rgj7-g3m4-5g8c high yes

Background: What a vulnerability scan can and cannot prove →

Dependencies 132 packages
Packages resolved 132
Stale 31
No linked repository 2
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 156 exposed · ~36,639 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
template_list_themes ~83

List available pre-built themes.

NameTypeReqDescription
projectstring–Optional project — a website inside the workspace (proj_xxx) — to scope this call to. Sent as the X-Project-Id header. If omitted, the spideriq.json / SPIDERIQ_PROJECT_ID binding (or the workspace de…
workspacestring––

No output schema declared.

No examples provided.

template_preview ~113

Render a template with mock data and return the HTML output.

NameTypeReqDescription
dataobject–Mock data to pass to the template
projectstring–Optional project — a website inside the workspace (proj_xxx) — to scope this call to. Sent as the X-Project-Id header. If omitted, the spideriq.json / SPIDERIQ_PROJECT_ID binding (or the workspace de…
template_pathstringyesTemplate path to render
workspacestring––

No output schema declared.

No examples provided.

template_update_config ~148

Update template config: theme, route overrides, settings, or data sources.

NameTypeReqDescription
data_sourcesarray–Connected SpiderIQ data sources
projectstring–Optional project — a website inside the workspace (proj_xxx) — to scope this call to. Sent as the X-Project-Id header. If omitted, the spideriq.json / SPIDERIQ_PROJECT_ID binding (or the workspace de…
routesobject–Path → template overrides (e.g. {"/pricing": "templates/pricing.liquid"})
settingsobject–Theme-level settings
themestring–Theme name
workspacestring––

No output schema declared.

No examples provided.

template_upsert ~445

Create or update a Liquid template. Provide the FULL Liquid template source code. The `path` param is the file path under the client's theme (e.g. 'templates/default.liquid', 'layout/theme.liquid', 'snippets/post-card.liquid'). It is a FILENAME, not a slug or shorthand — passing 'form' or 'page' as `path` will store garbage that no template-lookup path consults. Customizing form-page chrome at /f/<flow_id>: override 'templates/forms-standalone.liquid' (NOT 'templates/form.liquid', which is unused). Same for booking pages: 'templates/booking-standalone.liquid'. Both extend layout/theme.liquid, so a layout override applies to page + form + booking chrome together. To target form pages from inside layout/theme.liquid use `{% if template == 'forms-standalone' %}` (the Liquid `template` variable mirrors the file's basename, NOT a short name like 'form'). Phase 11+12 Lock 4 gate is opt-in via dry_run/confirm_token.

NameTypeReqDescription
confirm_tokenstring–Token from a prior dry_run call. Single-use, 7d TTL.
contentstringyesLiquid template source code (full file body, not a diff).
dry_runboolean–Preview the change without mutating and receive a confirm_token. When omitted, the change is applied immediately (legacy behaviour preserved).
pathstringyesTemplate file path under the theme (e.g. 'templates/default.liquid', 'templates/forms-standalone.liquid', 'layout/theme.liquid'). Required. Backend rejects literal 'undefined' / 'null' / empty / non-…
projectstring–Optional project — a website inside the workspace (proj_xxx) — to scope this call to. Sent as the X-Project-Id header. If omitted, the spideriq.json / SPIDERIQ_PROJECT_ID binding (or the workspace de…
themestring–Theme name (default: "default")
workspacestring––

No output schema declared.

No examples provided.

upload_local_directory ~489

Upload all matching files from a local directory to SpiderMedia. Walks the directory (recursive), sniffs content-type, uploads in a single /media/upload-batch request (up to 500 MB total for general folders, 20 MB for scroll-sequences/*). Returns {uploaded: [...], failed: [...], warnings}. Scroll-sequence workflow: - Default folder rule: if `folder` starts with "scroll-sequences/", the tool auto-enables both `auto_optimize=true` (Sharp → WebP q75, max 1920px) and `preserve_filename=true` (so frame_0001.webp lands at frame_0001.webp). - Override with explicit flags if needed. Filtering: pass `pattern` as a simple glob (e.g. "frame_*.webp") to filter the dir; default is all allowed extensions. Allowed: webp, jpg, jpeg, png, gif, pdf, mp4, webm, mov. Sharp is an optional peer dep. If missing, auto_optimize silently falls back to uploading originals (which may then hit server hard ceilings).

NameTypeReqDescription
auto_optimizeboolean–Run Sharp locally before upload (WebP q75, max 1920px). Default: true for scroll-sequences/*, false otherwise.
folderstring–Target folder in the bucket. For scroll-sequences use 'scroll-sequences/<name>'.
local_dirstringyesAbsolute or cwd-relative path to the directory on disk
max_widthnumber–When optimizing, max image width (default 1920)
patternstring–Optional glob pattern (e.g. "frame_*.webp"). Matched against filename and relative path.
preserve_filenameboolean–Deterministic storage keys. Default: true for scroll-sequences/*, false otherwise.
projectstring–Optional project — a website inside the workspace (proj_xxx) — to scope this call to. Sent as the X-Project-Id header. If omitted, the spideriq.json / SPIDERIQ_PROJECT_ID binding (or the workspace de…
qualitynumber–When optimizing, WebP quality 1-100 (default 75)
workspacestring–Workspace name (default: "default")

No output schema declared.

No examples provided.

upload_local_file ~342

Upload a single local file to SpiderMedia. Reads the file from disk, sniffs content-type from the extension, and POSTs multipart to /dashboard/content/media/upload-batch. Server enforces weight policy (500 KB/file for scroll-sequences/*, 20 MB otherwise; video/* gets 500 MB). Returns {public_url, key, size, content_type}. Filenames: pass preserve_filename=true for deterministic storage keys (scroll-sequences that consume {base_url, pattern, count}). Default false keeps the legacy YYYYMMDD_HHMMSS_ prefix. Requires LLM11 SpiderMedia backend 2026-04-18+ when preserve_filename=true. Allowed extensions: webp, jpg, jpeg, png, gif, pdf, mp4, webm, mov.

NameTypeReqDescription
filenamestring–Rename the file on upload (default: use the local basename)
folderstring–Target folder in the bucket, e.g. 'scroll-sequences/hero' or 'migrations/homepage'
local_pathstringyesAbsolute or cwd-relative path to the file on disk
preserve_filenameboolean–If true, storage key is {folder}/{filename} exactly (overwrites on collision). Default false.
projectstring–Optional project — a website inside the workspace (proj_xxx) — to scope this call to. Sent as the X-Project-Id header. If omitted, the spideriq.json / SPIDERIQ_PROJECT_ID binding (or the workspace de…
workspacestring–Workspace name (default: "default")

No output schema declared.

No examples provided.

video_to_scroll_sequence ~826

Build a scroll-linked image-sequence hero from a video URL, end-to-end. One call replaces the 5-step recipe: upload video -> submit extract_frames -> poll -> build block -> update page. Extracts numbered WebP frames from the source video (ffmpeg, ~7x smaller than raw), uploads them to the client's SpiderMedia bucket with a deterministic pattern (frame_{0001..NNNN}.webp), then injects a 'sys-scroll-sequence' component block into the target page AS A DRAFT. **Never auto-publishes.** After this tool returns, call: 1. content_deploy_site_preview (review at preview-{hash}.sites.spideriq.ai) 2. content_deploy_site_production (with confirm_token) When to use: - Agent received "add a scroll-sequence hero from this video" request - Video is at a public URL (SpiderMedia, di-atomic, or public http/https) - Target page already exists (use content_create_page first if not) Frame-count strategies (pick one): - strategy='target_frames' + target_frames=N — exact N frames spread across full duration (most common) - strategy='fps' + fps=N — sample at N frames/second - strategy='duration_fps' + fps + duration_seconds — clip + sample Returns: manifest {base_url, pattern, count}, the inserted block JSON, and the new draft page version ID.

NameTypeReqDescription
background_colorstring–Hex color painted before frames load (default: #ffffff)
canvas_heightnumber–Canvas render height, 240-1080 (default: 720)
canvas_widthnumber–Canvas render width, 320-1920 (default: 1280)
dry_runboolean–If true, returns block JSON without touching the page (default: false)
duration_secondsnumber–Clip duration in seconds (1-120). Required if strategy=duration_fps
fpsnumber–Sample FPS (1-60). Required if strategy=fps or duration_fps
output_formatstring–Frame format (default: webp — half the bytes of jpeg at same quality)
output_qualitynumber–Encoder quality 50-95 (default: 80)
output_widthnumber–Output frame width 320-1920 (default: 1280)
page_slugstringyesTarget page slug — MUST already exist. Use content_create_page first if not.
poll_interval_secondsnumber–Poll interval in seconds (0.5-10, default: 2)
poll_timeout_secondsnumber–Max seconds to wait for extract_frames (30-900, default: 300)
position––Where to insert: "append" (default), "prepend", {index: N}, {before: slug}, or {after: slug}
preload_strategystring–progressive (default) loads ±15 frame window; all pre-loads everything
prioritynumber–Job priority 0-10 (default: 5)
projectstring–Optional project — a website inside the workspace (proj_xxx) — to scope this call to. Sent as the X-Project-Id header. If omitted, the spideriq.json / SPIDERIQ_PROJECT_ID binding (or the workspace de…
scroll_distance_vhnumber–Viewport heights to scroll through full sequence, 200-800 (default: 400)
strategystring–Frame-count strategy (default: target_frames)
target_framesnumber–Exact frame count (10-600). Required if strategy=target_frames. Default: 120
video_urlstringyesSource video URL (SpiderMedia, di-atomic, or public http/https)
workspacestring–Workspace name (default: "default")

No output schema declared.

No examples provided.

Common questions

What is the ai.spideriq/publish MCP server?

ai.spideriq/publish is an MCP server listed in the public MCP registry as ai.spideriq/publish. SpiderIQ Publish: content platform MCP (pages, posts, templates, components, domains, media). This page covers its npm package (@spideriq/mcp-publish).

Is the ai.spideriq/publish MCP server safe to use?

ai.spideriq/publish scores 67 out of 100 on VerifyMCP. We recorded 2 known advisories against it as of 25 September 2026. It declares no install or post-install scripts. 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 ai.spideriq/publish MCP server expose?

ai.spideriq/publish exposes 156 tools: request_access, check_access_status, get_auth_status, logout, list_workspaces, and 151 more. Their descriptions and schemas cost roughly 36,639 tokens of context every time the server is loaded.

Is the ai.spideriq/publish MCP server still maintained?

ai.spideriq/publish is still listed as active in the MCP registry. We last reached this channel on 25 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the ai.spideriq/publish MCP server under?

ai.spideriq/publish declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.