SparkAds MCP server
dev.sparkads/sparkadssparkads.devstreamable-httpv1.0.0Scanned
Manage your SparkAds slot: your stats, the free-hour grid, network totals, and your own creative.
5 tools: 1 can delete or cancel things and 4 only read.
- Reads private data · 0
- Reads text others write · 2
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here can delete or cancel things. Govern it.
- 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 SparkAds MCP server can do
The SparkAds MCP server is published by sparkads.dev, a domain the MCP Registry verified. It has 5 tools. It can delete or cancel things (1 tool: update_creative). 4 tools only read.
2 tools bring in text other people can write (get_my_stats and get_slot).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 15, 2026, version 1.0.0.
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.
5 tools
Deletes or cancels 1Claude Code: deny
update_creativeEdit this advertiser's ad card.No findings
Why it is in this group
- The name "update_creative" says "update": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Edit this advertiser's ad card. Pass only the fields to change; anything omitted keeps its current value. WRITE TOOL, and it costs something: saving resets the card's status to 'pending', so the ad STOPS running until a person approves it again. Say that to the user and get their agreement before calling this. Caps: name 40 characters, tagline 60, one-sentence body 160, url must be https, domain must be a bare hostname like myapp.com. House style: plain words, no exclamation marks, and the sentence says what the product does rather than why it is good.
Annotations the server declares
- title: Update Creative
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
Only reads 4Show 4 read-only tools
get_my_statsGet this advertiser's own ad performance for the last 30 days: impressions and clicks split by day, by app in the Spark network, and by traffic source, plus every creative they own…Reads text others writeNo findings
Why it is in this group
- The name "get_my_stats" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "get" and "review": it reads comments, which other people can write.
Description, as the server wrote it Get this advertiser's own ad performance for the last 30 days: impressions and clicks split by day, by app in the Spark network, and by traffic source, plus every creative they own with its review status. Read-only. Scoped to the API key holder; it cannot report on anyone else.
Annotations the server declares
- title: Get My Stats
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_network_pulseGet the whole network's last 24 hours: total impressions, total clicks, how many apps showed the carousel, and how many of the 24 hourly slots are taken.No findings
Why it is in this group
- The name "get_network_pulse" says "get": a word for reading.
Description, as the server wrote it Get the whole network's last 24 hours: total impressions, total clicks, how many apps showed the carousel, and how many of the 24 hourly slots are taken. This is the public inventory figure, the same one the SparkAds landing page prints, not this advertiser's own numbers. Read-only.
Annotations the server declares
- title: Get Network Pulse
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_slotGet the hour this advertiser holds: the UTC hour, the same hour on their target country's clock, the country itself, and the card that runs in it with its review status.Reads text others writeNo findings
Why it is in this group
- The name "get_slot" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "get" and "review": it reads comments, which other people can write.
Description, as the server wrote it Get the hour this advertiser holds: the UTC hour, the same hour on their target country's clock, the country itself, and the card that runs in it with its review status. Also reports whether the ad is actually live right now, which needs all three of a held hour, an approved card and a paying subscription. Read-only.
Annotations the server declares
- title: Get Slot
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_free_slotsList the UTC hours nobody has claimed yet, out of the 24 the network sells.No findings
Why it is in this group
- The name "list_free_slots" says "list": a word for reading.
Description, as the server wrote it List the UTC hours nobody has claimed yet, out of the 24 the network sells. Pass a country to also get each free hour on that country's clock and the best five ranked by local evening attention. Supported countries: GB, IE, PT, FR, DE, ES, IT, NL, BE, SE, NO, DK, PL, CH, AT, NG, FI, GR, RO, UA, EG, ZA, IL, SA, TR, RU, KE, AE, PK, IN, BD, TH, VN, ID, CN, SG, MY, PH, HK, TW, AU, JP, KR, NZ, BR, AR, US, CA, PE, CO, MX. Read-only; claiming an hour still happens on the website.
Annotations the server declares
- title: List Free Slots
- 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 or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- 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, 18:52 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
- 1
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 destructive). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://sparkads.dev/api/mcp/mcp: tools/list returned 5 tools to an anonymous client, including update_creative (destructive)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools5 changed.~5 changedView diff
- Changed:get_my_statsOnly readsannotations
- Changed:get_network_pulseOnly readsannotations
- Changed:get_slotOnly readsannotations
- Changed:list_free_slotsOnly readsannotations
- Changed:update_creativeDeletes or cancelsannotations
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http sparkads https://sparkads.dev/api/mcp/mcpclaude mcp add --transport http sparkads https://sparkads.dev/api/mcp/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__sparkads__get_my_stats",
"mcp__sparkads__get_slot",
"mcp__sparkads__list_free_slots",
"mcp__sparkads__get_network_pulse"
],
"ask": [],
"deny": [
"mcp__sparkads__update_creative"
]
}
}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 sparkads. Review it before you use it.
Capability tags behind 2 rules
- mcp__sparkads__get_my_stats untrusted-input
- mcp__sparkads__get_slot 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/dev.sparkads/sparkads/verify?hash=51b8c087e3cebf57d7cf03fcc17f72d4e75033ba4e765e3789810a469d365960" | jq -e '.changed == false'Pinned hash 51b8c087e3ce, from Nov 15, 2026, 04:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/dev.sparkads/sparkads/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/dev.sparkads/sparkads)Source: MCP Registry. Synced Oct 21, 2026, 18:12 UTC.
SparkAds MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the SparkAds MCP server safe?
- No scan can promise that. What its definitions show: 5 tools, 1 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the SparkAds MCP server delete data?
- Yes. 1 tool can delete, cancel or revoke something: update_creative.
Can the SparkAds 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 SparkAds MCP server have?
- 5 tools: 1 destructive, 4 read. update_creative, get_my_stats, get_slot, list_free_slots and get_network_pulse.
Does the SparkAds MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the SparkAds MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the SparkAds MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 15, 2026. Every change is on this page and in its Atom feed.