Proofsource MCP server
co.proofsource/proofsourceproofsource.costreamable-httpv1.0.0Scanned
AI visibility: which buyer questions name your brand in ChatGPT, Perplexity, Claude, AI Overviews.
15 tools: 4 change things and 11 only read.
- Reads private data · 3
- Reads text others write · 10
- Can send data out · 0
- 2 findings
Tools listed without sign-in. Remote posture
With Anlyon
4 tools here change 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 Proofsource MCP server can do
The Proofsource MCP server is published by proofsource.co, a domain the MCP Registry verified. It has 15 tools. It can create or change data (4 tools: create_prompt, mark_fix_shipped, add_brand and get_report_link), but cannot delete data. 11 tools only read.
3 tools read private data (list_topics, get_visibility and see_example); 10 tools bring in text other people can write (list_brands, list_topics, get_visibility and 7 more).
The fixed checks matched 2 findings (tool-shadowing and annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.
Last scanned Nov 10, 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.
15 tools
Changes things 4Claude Code: ask
add_brandStart measuring a brand: does ChatGPT, Perplexity, Claude or Google AI mention it, and who does AI recommend instead?Reads text others writeNo findings
Why it is in this group
- The name "add_brand" says "add": 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 Start measuring a brand: does ChatGPT, Perplexity, Claude or Google AI mention it, and who does AI recommend instead? Give the brand's website (or its app store, Google Maps, YouTube or Instagram link). It reads the site, picks the buyer questions, and starts the first scan across the AI engines. Reading the site takes 1-2 minutes; if it is still running, call again with the same link and it picks up the same run, never a second one. Returns the brand_id; then use get_scan_status.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: false
- title: Check my brand in AI answers
create_promptAdds a buyer question to a topic so it is asked on every engine in the plan from the next run.No findings
Why it is in this group
- The name "create_prompt" says "create": a word for a change.
Description, as the server wrote it Adds a buyer question to a topic so it is asked on every engine in the plan from the next run. Counts toward the plan's question limit. Calling again with the same text returns the existing question, never a duplicate.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: false
- title: Track a new buyer question
get_report_linkA link to the brand's AI visibility report to share with a team or client: how often AI answers mention the brand, which competitors they name instead, and which sources they cite.Reads text others write1 finding
Why it is in this group
- The name "get_report_link" says "get": a word for reading.
- The description's first verb is "link": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe description's first sentence says "link" and "mention": it reads comments, which other people can write.
Findings
- Warn
The server marks "get_report_link" 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 "get_report_link" says "get": a word for reading.
Description, as the server wrote it A link to the brand's AI visibility report to share with a team or client: how often AI answers mention the brand, which competitors they name instead, and which sources they cite. Returns the newest finished report's own unlisted link. Reports are built automatically after a brand's first scan.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: Get a shareable AI visibility report
mark_fix_shippedRecords that a fix shipped, against a gap_id from list_fix_opportunities or a published content_draft_id, so get_fix_verification can measure whether it moved the brand's mention r…No findings
Why it is in this group
- The name "mark_fix_shipped" says "mark": a word for a change.
Description, as the server wrote it Records that a fix shipped, against a gap_id from list_fix_opportunities or a published content_draft_id, so get_fix_verification can measure whether it moved the brand's mention rate. Calling again with the same fix and description returns the existing record.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: false
- title: I shipped a fix
Only reads 11Show 11 read-only tools
get_changesWhat moved over the window: the daily mention-rate trend, how much the engines' answers changed, notable changes on competitors' websites, and new pages about the category.Reads text others writeNo findings
Why it is in this group
- The name "get_changes" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "mention": it reads comments, which other people can write.
Description, as the server wrote it What moved over the window: the daily mention-rate trend, how much the engines' answers changed, notable changes on competitors' websites, and new pages about the category.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: What changed in my AI visibility?
get_citationsThe websites AI answers cite for the brand's buyer questions, ranked by share of citations and by how many answers cite them, and where the brand's own site ranks.Reads text others writeNo findings
Why it is in this group
- The name "get_citations" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "website": it reads web pages, which anyone can write.
Description, as the server wrote it The websites AI answers cite for the brand's buyer questions, ranked by share of citations and by how many answers cite them, and where the brand's own site ranks.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: Which sources do AI answers cite?
get_competitorsThe competitors AI answers name for the brand's buyer questions, per engine, with each one's share of voice against the brand and how it changed over the window.No findings
Why it is in this group
- The name "get_competitors" says "get": a word for reading.
Description, as the server wrote it The competitors AI answers name for the brand's buyer questions, per engine, with each one's share of voice against the brand and how it changed over the window.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: Who does AI recommend instead of me?
get_fix_verificationEach fix marked shipped for the brand with its mention rate before and after and a verdict: moved (beyond normal answer churn), within_noise, or awaiting_samples.Reads text others writeNo findings
Why it is in this group
- The name "get_fix_verification" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "mention": it reads comments, which other people can write.
Description, as the server wrote it Each fix marked shipped for the brand with its mention rate before and after and a verdict: moved (beyond normal answer churn), within_noise, or awaiting_samples. Fixes marked "Not a fix" are left out; auto-detected page changes carry source auto_detected.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: Did my fix work?
get_loopThe brand's loop, oldest first: each buyer question tracked, gap found, content draft created, fix published to the brand's site, fix shipped, change seen on the brand's own pages,…Reads text others writeNo findings
Why it is in this group
- The name "get_loop" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "mention": it reads comments, which other people can write.
Description, as the server wrote it The brand's loop, oldest first: each buyer question tracked, gap found, content draft created, fix published to the brand's site, fix shipped, change seen on the brand's own pages, and fix checked after it ships: a first check on day 28, re-checks on days 45, 60 and 75 and a final check on day 90 (whether it is still live and how citations, mentions and AI-referral traffic moved, each with its sample size; a horizon appears only once it has been measured). The first page also lists before_window: each question's newest draft, publish and shipped fix from before since, its current state. At most 90 days per call (the last N days is since = today minus N-1, today counted); page with next_cursor.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: What happened from question to verified fix?
get_scan_statusProgress of a brand's first scan after add_brand: the stage, how many AI answers are in out of how many expected, per engine, and when it should finish.No findings
Why it is in this group
- The name "get_scan_status" says "get": a word for reading.
Description, as the server wrote it Progress of a brand's first scan after add_brand: the stage, how many AI answers are in out of how many expected, per engine, and when it should finish. Once complete, use get_visibility for the results.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: Is my brand's scan done?
get_visibilityHow often ChatGPT, Perplexity, Claude and Google AI mention the brand when buyers ask about its category.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_visibility" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "chat": it reads messages.
- untrusted-inputThe description's first sentence says "chat": it reads messages, which other people can write.
Description, as the server wrote it How often ChatGPT, Perplexity, Claude and Google AI mention the brand when buyers ask about its category. by=engine (default): mention rate, share of voice, average position, citation share and sentiment per engine, with the change from the previous period. by=question: each buyer question's mention rate and rank. A brand measured in several locations also gets locations: each location's mention rate, change and the competitor AI names most there, weakest first.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: Is my brand mentioned in AI answers?
list_brandsThe brands this workspace tracks in AI answers, with ids and websites.Reads text others write1 finding
Why it is in this group
- The name "list_brands" says "list": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "website": it reads web pages, which anyone can write.
Findings
- Warn
The description contains "every other tool", wording about other tools or servers.
What this check looks forMatched text
description: "...ers, with ids and websites. Call first; every other tool takes a brand_id."
Description, as the server wrote it The brands this workspace tracks in AI answers, with ids and websites. Call first; every other tool takes a brand_id.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: List my tracked brands
list_fix_opportunitiesThe gaps that keep AI engines from citing or recommending the brand, each with its evidence and the suggested fix.No findings
Why it is in this group
- The name "list_fix_opportunities" says "list": a word for reading.
Description, as the server wrote it The gaps that keep AI engines from citing or recommending the brand, each with its evidence and the suggested fix. Gives the gap_id mark_fix_shipped needs.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: What should I fix to show up in AI answers?
list_topicsThe topics and buyer questions this workspace asks ChatGPT, Perplexity, Claude and Google AI for a brand.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "list_topics" says "list": a word for reading.
What it can reach
- private-dataThe description's first sentence says "chat": it reads messages.
- untrusted-inputThe description's first sentence says "chat": it reads messages, which other people can write.
Description, as the server wrote it The topics and buyer questions this workspace asks ChatGPT, Perplexity, Claude and Google AI for a brand. Gives the topic_id create_prompt needs.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: Which buyer questions are tracked?
see_exampleShows what Proofsource measures, without signing in: a real visibility card for one example brand (Tesla), from answers collected from ChatGPT, Perplexity, Claude and Google AI Ove…Reads private dataReads text others writeNo findings
Why it is in this group
- The description's first verb is "show": a word for reading.
What it can reach
- private-dataThe description's first sentence says "show" and "chat": it reads messages.
- untrusted-inputThe description's first sentence says "show" and "chat": it reads messages, which other people can write.
Description, as the server wrote it Shows what Proofsource measures, without signing in: a real visibility card for one example brand (Tesla), from answers collected from ChatGPT, Perplexity, Claude and Google AI Overviews. It shows how often AI answers mention the brand, per engine, which competitors they name instead, and sample answers. Use it when someone asks whether their brand shows up in AI answers and has not signed in. It always shows the example brand; to check their own brand they sign in.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: See an example AI visibility card
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 outbound.
- Reads private data3
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write10
- 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, 18:32 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
- 4
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://app.proofsource.co/.well-known/oauth-protected-resource/v1/mcp
- Authorization servers
- https://app.proofsource.co
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- yes
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://app.proofsource.co/v1/mcp: tools/list returned 15 tools to an anonymous client, including create_prompt (write), mark_fix_shipped (write), add_brand (write), get_report_link (write)
Findings
Matches of fixed checks, with the text they matched.
- Warnlist_brands
The description contains "every other tool", wording about other tools or servers.
What this check looks forMatched text
description: "...ers, with ids and websites. Call first; every other tool takes a brand_id."
- Warnget_report_link
The server marks "get_report_link" 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 "get_report_link" says "get": a word for reading.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools3 changed.~3 changedView diff
- Changed:add_brandChanges thingsinputSchema
- Changed:get_loopOnly readsdescription
- Changed:get_visibilityOnly readsdescription
Tools1 added.+1 addedView diff
- Added:get_loopOnly reads
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http proofsource https://app.proofsource.co/v1/mcpclaude mcp add --transport http proofsource https://app.proofsource.co/v1/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__proofsource__list_brands",
"mcp__proofsource__list_topics",
"mcp__proofsource__get_visibility",
"mcp__proofsource__get_competitors",
"mcp__proofsource__get_citations",
"mcp__proofsource__get_changes",
"mcp__proofsource__list_fix_opportunities",
"mcp__proofsource__get_fix_verification",
"mcp__proofsource__get_loop",
"mcp__proofsource__get_scan_status",
"mcp__proofsource__see_example"
],
"ask": [
"mcp__proofsource__create_prompt",
"mcp__proofsource__mark_fix_shipped",
"mcp__proofsource__add_brand",
"mcp__proofsource__get_report_link"
],
"deny": []
}
}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 proofsource. Review it before you use it.
Capability tags behind 10 rules
- mcp__proofsource__list_brands untrusted-input
- mcp__proofsource__list_topics private-data, untrusted-input
- mcp__proofsource__get_visibility private-data, untrusted-input
- mcp__proofsource__get_citations untrusted-input
- mcp__proofsource__get_changes untrusted-input
- mcp__proofsource__get_fix_verification untrusted-input
- mcp__proofsource__get_loop untrusted-input
- mcp__proofsource__add_brand untrusted-input
- mcp__proofsource__get_report_link untrusted-input
- mcp__proofsource__see_example private-data, 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/co.proofsource/proofsource/verify?hash=822244fead95be5fad35efdd1220a2515487d0383465c0a327db8c5ca8df5c82" | jq -e '.changed == false'Pinned hash 822244fead95, from Nov 10, 2026, 09:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/co.proofsource/proofsource/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/co.proofsource/proofsource)Source: MCP Registry · repository. Synced Oct 21, 2026, 17:47 UTC.
Proofsource MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Proofsource MCP server safe?
- No scan can promise that. What its definitions show: 15 tools, 4 of which can change, send or delete something, and 2 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 Proofsource MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Proofsource 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 Proofsource MCP server have?
- 15 tools: 4 write, 11 read. create_prompt, mark_fix_shipped, add_brand, get_report_link, list_brands, list_topics, get_visibility, get_competitors and 7 more.
Does the Proofsource MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Proofsource MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Proofsource MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 10, 2026. Every change is on this page and in its Atom feed.