Rendex: Rendering API for Images, PDFs & Content Extraction MCP server
io.github.copperline-labs/rendex-mcpcopperline-labsstreamable-httpv1.8.2Scanned
Render HTML, Markdown, or URLs to images, PDF, or branded artifacts; extract and watch pages.
13 tools: 2 can delete or cancel things, 8 change things and 3 only read.
- Reads private data · 0
- Reads text others write · 8
- Can send data out · 5
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
2 tools here can delete or cancel things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Rendex: Rendering API for Images, PDFs & Content Extraction MCP server can do
The Rendex: Rendering API for Images, PDFs & Content Extraction MCP server is published by the GitHub account copperline-labs. It has 13 tools. It can delete or cancel things (2 tools: watch_delete and watch_update) and create or change data (8 tools: rendex_extract, rendex_render_link, render_artifact, rendex_account and 4 more). 3 tools only read.
8 tools bring in text other people can write (rendex_screenshot, rendex_extract, rendex_render_link and 5 more); 5 tools can send data out of your system (rendex_screenshot, rendex_extract, rendex_render_link and 2 more).
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 16, 2026, version 1.8.2.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
13 tools
Deletes or cancels 2Claude Code: deny
watch_deleteDelete a watch and its run history.No findings
Why it is in this group
- The name "watch_delete" says "delete": a word for removing or ending something.
- The description says "Irreversible".
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Delete a watch and its run history. Irreversible.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
watch_updateUpdate a watch in place — pause/resume (paused), re-point (url), change schedule/diff/notify settings, or turn a channel off (webhookUrl/notifyEmail = null).No findings
Why it is in this group
- The name "watch_update" says "update": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Update a watch in place — pause/resume (paused), re-point (url), change schedule/diff/notify settings, or turn a channel off (webhookUrl/notifyEmail = null). Only the fields you send change; renderParams is deep-merged over the existing config. A scope change (url/selector/fullPage/size/device) re-baselines on the next check. Returns the updated watch as JSON.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
Changes things 8Claude Code: ask
render_artifactUse this when the user asks to make or create a branded report, invoice, summary, release notes, or document — or to 'turn this Markdown/HTML into a PDF and PNG' (optionally with a…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Use this when the user asks to make or create a branded report, invoice, summary, release notes, or document — or to 'turn this Markdown/HTML into a PDF and PNG' (optionally with a logo or accent color). Turns Markdown or HTML into a branded, downloadable artifact — a PDF, a PNG, and a hosted share page — in one call. Apply a logo, accentColor, font, header, and footer. Returns hosted URLs { pdfUrl, pngUrl, shareUrl, expiresAt }. Each requested format costs 1 render credit.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
rendex_accountCheck the Rendex account: which plan it's on, how many render credits have been used vs.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Check the Rendex account: which plan it's on, how many render credits have been used vs. the monthly limit (and when it resets), the per-minute rate limit, and a one-tap link to upgrade to a higher tier. Use this whenever the user asks about their usage, remaining quota, current plan, or how to get more renders / stop hitting limits. Read-only — costs no credits.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
rendex_extractUse this when the user asks to read, extract, get the text/content/article of, or summarize a webpage/URL.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Use this when the user asks to read, extract, get the text/content/article of, or summarize a webpage/URL. Extracts clean reader-mode content from any webpage as Markdown, JSON, or HTML. Runs a full Chromium render pass, so it captures content after JavaScript runs, including single-page apps (SPAs). Strips nav, ads, and boilerplate, returning the article body plus title, byline, and excerpt. Great for feeding page content to an LLM, summarization, or RAG ingestion. Costs 1 render credit per call.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
rendex_render_linkUse this when the user wants a reusable, HOSTED image URL — an og:image or a link to embed in an <img> tag — rather than the image bytes.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "rendex_render_link" says "link": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Use this when the user wants a reusable, HOSTED image URL — an og:image or a link to embed in an <img> tag — rather than the image bytes. Renders a URL, raw HTML, or Markdown and gives back a signed, hosted, edge-cached image URL instead of the bytes — ideal for dynamic OG images: drop the URL into <meta property="og:image"> or an <img> tag and Rendex serves a cached copy on every share. Takes the same options as rendex_screenshot, plus an optional expiresIn. Returns { url, expiresAt, format, cacheTtl } as JSON. Costs 1 render credit per fresh render; cached repeat hits don't re-charge.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
watch_createUse this when the user asks to monitor, watch, or track a webpage for changes, or to be alerted/notified when a page changes.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "watch_create" says "create": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Use this when the user asks to monitor, watch, or track a webpage for changes, or to be alerted/notified when a page changes. Creates a Rendex Watch — monitors a URL on a schedule and notifies when it changes (real-Chrome visual diff with a highlighted overlay, an extracted-text diff, or both). An active watch captures its baseline immediately. Returns the created watch as JSON.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
watch_runRun an immediate check now (charges 1 credit).Reads text others writeNo findings
Why it is in this group
- The name "watch_run" says "run": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Run an immediate check now (charges 1 credit). Returns the queued run; poll watch_runs for the result or receive a watch.changed webhook.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
watch_runsRead a watch's run history (newest first), paged.1 finding
Why it is in this group
- The name "watch_runs" says "run": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "watch_runs" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "watch_runs" says "run": a word for a change.
Description, as the server wrote it Read a watch's run history (newest first), paged. Each run includes changed, diffScore, and signed before/after/overlay image URLs. Returns { items, nextCursor }.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
watch_testDry-run a watch config BEFORE creating it — render the proposed config once and report what was captured + whether the page is reachable (and the text a text-watch would compare).Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Dry-run a watch config BEFORE creating it — render the proposed config once and report what was captured + whether the page is reachable (and the text a text-watch would compare). Creates no watch, no baseline, no diff. Use this to validate a selector/scope/identity first. Returns JSON.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Only reads 3Show 3 read-only tools
rendex_screenshotUse this when the user asks to screenshot, capture, or take a picture of a webpage/URL, or to render raw HTML or Markdown to an image or PDF.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "rendex_screenshot" says "screenshot": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "webpage": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Use this when the user asks to screenshot, capture, or take a picture of a webpage/URL, or to render raw HTML or Markdown to an image or PDF. Captures a screenshot or PDF of any webpage, raw HTML, or Markdown. Supports full-page capture, dark mode, ad blocking, custom viewports, CSS/JS injection, cookie/header injection, PDF output, HTML and Markdown rendering, and progressive fallback for heavy sites. Returns partial renders on timeout by default (bestAttempt mode). Costs 1 render credit per call. Cookie/header injection requires Starter+; geo-targeting requires Pro+.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
watch_getFetch one watch by ID, including its current baseline image URL and status.Reads text others writeNo findings
Why it is in this group
- The name "watch_get" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "fetch" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Fetch one watch by ID, including its current baseline image URL and status. Returns JSON.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
watch_listList your watches (newest first), optionally filtered by status and paged.No findings
Why it is in this group
- The name "watch_list" says "list": a word for reading.
Description, as the server wrote it List your watches (newest first), optionally filtered by status and paged. Returns { items, nextCursor }.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write8
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out5
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:03 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 10
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://mcp.rendex.dev/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://mcp.rendex.dev
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 10 tools that change things (2 destructive, 8 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.rendex.dev/mcp: tools/list returned 13 tools to an anonymous client, including watch_delete (destructive), watch_update (destructive), rendex_extract (write), rendex_render_link (write), render_artifact (write) and 5 more
Findings
Matches of fixed checks, with the text they matched.
- Warnwatch_runs
The server marks "watch_runs" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "watch_runs" says "run": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools6 changed.~6 changedView diff
- Changed:render_artifactChanges thingsdescriptionannotations
- Changed:rendex_extractChanges thingsdescription
- Changed:rendex_render_linkChanges thingsdescriptionannotations
- Changed:rendex_screenshotOnly readsdescription
- Changed:watch_createChanges thingsdescription
- Changed:watch_updateDeletes or cancelsannotations
Install
Pinned to version 1.8.2. Values in angle brackets are yours to fill in.
claude mcp add --transport http rendex https://mcp.rendex.dev/mcpclaude mcp add --transport http rendex https://mcp.rendex.dev/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__rendex__watch_list",
"mcp__rendex__watch_get"
],
"ask": [
"mcp__rendex__rendex_screenshot",
"mcp__rendex__rendex_extract",
"mcp__rendex__rendex_render_link",
"mcp__rendex__render_artifact",
"mcp__rendex__rendex_account",
"mcp__rendex__watch_create",
"mcp__rendex__watch_test",
"mcp__rendex__watch_run",
"mcp__rendex__watch_runs"
],
"deny": [
"mcp__rendex__watch_delete",
"mcp__rendex__watch_update"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as rendex. Review it before you use it.
Capability tags behind 8 rules
- mcp__rendex__rendex_screenshot untrusted-input, outbound
- mcp__rendex__rendex_extract untrusted-input, outbound
- mcp__rendex__rendex_render_link untrusted-input, outbound
- mcp__rendex__render_artifact untrusted-input
- mcp__rendex__watch_create untrusted-input, outbound
- mcp__rendex__watch_test untrusted-input, outbound
- mcp__rendex__watch_get untrusted-input
- mcp__rendex__watch_run untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.copperline-labs/rendex-mcp/verify?hash=8b3d0618cf8e74e08495a0a9d4789281ebaab0c38df2a22e64a50d62e870cd0f" | jq -e '.changed == false'Pinned hash 8b3d0618cf8e, from Nov 16, 2026, 14:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.copperline-labs/rendex-mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.copperline-labs/rendex-mcp)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:28 UTC.
Rendex: Rendering API for Images, PDFs & Content Extraction MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Rendex: Rendering API for Images, PDFs & Content Extraction MCP server safe?
- No scan can promise that. What its definitions show: 13 tools, 10 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Rendex: Rendering API for Images, PDFs & Content Extraction MCP server delete data?
- Yes. 2 tools can delete, cancel or revoke something: watch_delete and watch_update.
Can the Rendex: Rendering API for Images, PDFs & Content Extraction MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Rendex: Rendering API for Images, PDFs & Content Extraction MCP server have?
- 13 tools: 2 destructive, 8 write, 3 read. watch_delete, watch_update, rendex_extract, rendex_render_link, render_artifact, rendex_account, watch_create, watch_test and 5 more.
Does the Rendex: Rendering API for Images, PDFs & Content Extraction MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Rendex: Rendering API for Images, PDFs & Content Extraction MCP server send data to outside services?
- 5 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): rendex_screenshot, rendex_extract, rendex_render_link, watch_create and watch_test.
Has the Rendex: Rendering API for Images, PDFs & Content Extraction MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 16, 2026. Every change is on this page and in its Atom feed.