infobro AI tools directory MCP server
ai.infobro/directoryinfobro.aistreamable-httpv1.0.0Scanned
List your AI tool on infobro.ai: sign up by email code, submit or claim a listing, pay and track it.
15 tools: 1 do something that can't be undone, 8 change things and 6 only read.
- Reads private data · 1
- Reads text others write · 15
- Can send data out · 2
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. 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 infobro AI tools directory MCP server can do
The infobro AI tools directory MCP server is published by infobro.ai, a domain the MCP Registry verified. It has 15 tools. It can do things that cannot be undone, such as sending, paying or publishing (create_payment) and create or change data (8 tools: start_signup, verify_signup, submit_tool, my_tools and 4 more), but cannot delete data. 6 tools only read.
1 tool reads private data (find_tool); 15 tools bring in text other people can write (start_signup, verify_signup, find_tool and 12 more); 2 tools can send data out of your system (prefill_from_url and submit_tool). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
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 18, 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
Can't be undone 1Claude Code: ask
create_paymentReturns a payment page for an order (card or crypto, depending on what is enabled).Reads text others writeNo findings
Why it is in this group
- The name "create_payment" says "create": a word for a change.
- The name "create_payment" also says "payment": a word that usually means money moves, which cannot be taken back.
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 Returns a payment page for an order (card or crypto, depending on what is enabled). The owner pays there; an assistant that can pay may pay itself.
Annotations the server declares
- title: Get the payment link
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
Changes things 8Claude Code: ask
login_linkA one-time link (15 minutes) that signs the owner into their infobro dashboard in the browser.Reads text others writeNo findings
Why it is in this group
- The name "login_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.
Description, as the server wrote it A one-time link (15 minutes) that signs the owner into their infobro dashboard in the browser.
Annotations the server declares
- title: Sign-in link for the owner
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
my_toolsThe account’s listings: review status, editor notes, plan, unpaid orders, views and clicks.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.
- 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.
Description, as the server wrote it The account’s listings: review status, editor notes, plan, unpaid orders, views and clicks.
Annotations the server declares
- title: My listings
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
start_claimFree.Reads text others writeNo findings
Why it is in this group
- The name "start_claim" says "start": 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 Free. Gives a meta tag or a DNS TXT record that proves the website is the owner’s. Add it, then call verify_claim.
Annotations the server declares
- title: Claim an existing listing
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
start_signupStep 1 for a new assistant.Reads text others writeNo findings
Why it is in this group
- The name "start_signup" says "start": 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 Step 1 for a new assistant. Emails a 6-digit code to the product owner. Works for new and existing accounts. Then call verify_signup.
Annotations the server declares
- title: Create or connect an account
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
submit_toolCreates the listing as an unpaid draft and an order for the chosen plan.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "submit_tool" says "submit": 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 Creates the listing as an unpaid draft and an order for the chosen plan. It goes to editor review once paid (create_payment). Write plain facts; no hype words, no claims you can’t back.
Annotations the server declares
- title: Submit a new listing
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
update_toolChanges fields of one of the account’s listings.Reads text others writeNo findings
Why it is in this group
- The name "update_tool" says "update": 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 Changes fields of one of the account’s listings. Only the fields you pass change. Live listings change after an editor’s check.
Annotations the server declares
- title: Edit a listing
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
verify_claimLooks for the meta tag or DNS record and, if found, moves the listing to the account.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 Looks for the meta tag or DNS record and, if found, moves the listing to the account.
Annotations the server declares
- title: Check the claim
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
verify_signupStep 2.Reads text others writeNo findings
Why it is in this group
- The input takes a statement or command to run (input.code), which can change anything it can reach.
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 Step 2. Checks the code from the email and returns an API key that acts for the account.
Annotations the server declares
- title: Confirm the email code
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
Only reads 6Show 6 read-only tools
find_toolIs this product already in the infobro directory?Reads private dataReads text others writeNo findings
Why it is in this group
- The name "find_tool" says "find": a word for reading.
What it can reach
- private-dataThe description's first sentence says "directory": it reads files.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Is this product already in the infobro directory? Search by website address or name.
Annotations the server declares
- title: Find a listing
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
list_categoriesCategory slugs to use in submit_tool.Reads text others writeNo findings
Why it is in this group
- The name "list_categories" says "list": a word for reading.
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 Category slugs to use in submit_tool.
Annotations the server declares
- title: Categories
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
list_plansListing plans with prices and what each includes.Reads text others writeNo findings
Why it is in this group
- The name "list_plans" says "list": a word for reading.
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 Listing plans with prices and what each includes. A new listing needs one of them. The owner decides, or tells you to decide for them.
Annotations the server declares
- title: Plans and prices
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
order_statusWhether an order is paid.Reads text others writeNo findings
Why it is in this group
- The name "order_status" says "status": a word for reading.
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 Whether an order is paid.
Annotations the server declares
- title: Order status
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
prefill_from_urlReads the product’s website and returns a draft (name, tagline, description, images) to improve and pass to submit_tool.Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "read": 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 name "prefill_from_url" says "url": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "read" and "website": 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 Reads the product’s website and returns a draft (name, tagline, description, images) to improve and pass to submit_tool.
Annotations the server declares
- title: Draft a listing from the website
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
whoamiWhich account the key belongs to.Reads text others writeNo findings
Why it is in this group
- The name "whoami" says "whoami": a word for reading.
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 Which account the key belongs to.
Annotations the server declares
- title: Account
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
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.
30 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write15
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out2
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__directory__find_tool"
]
}
}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 19, 2026, 17:22 UTC, unchanged since Nov 5, 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
- 9
- 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 9 tools that change things (1 irreversible, 8 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://infobro.ai/mcp: tools/list returned 15 tools to an anonymous client, including create_payment (irreversible), start_signup (write), verify_signup (write), submit_tool (write), my_tools (write) and 4 more
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.
Tools3 changed.~3 changedView diff
- Changed:list_plansOnly readsdescription
- Changed:submit_toolChanges thingsinputSchema
- Changed:update_toolChanges thingsinputSchema
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http directory https://infobro.ai/mcpclaude mcp add --transport http directory https://infobro.ai/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__directory__find_tool",
"mcp__directory__list_plans",
"mcp__directory__list_categories",
"mcp__directory__whoami",
"mcp__directory__order_status"
],
"ask": [
"mcp__directory__start_signup",
"mcp__directory__verify_signup",
"mcp__directory__prefill_from_url",
"mcp__directory__submit_tool",
"mcp__directory__create_payment",
"mcp__directory__my_tools",
"mcp__directory__update_tool",
"mcp__directory__start_claim",
"mcp__directory__verify_claim",
"mcp__directory__login_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 directory. Review it before you use it.
Capability tags behind 15 rules
- mcp__directory__start_signup untrusted-input
- mcp__directory__verify_signup untrusted-input
- mcp__directory__find_tool private-data, untrusted-input
- mcp__directory__list_plans untrusted-input
- mcp__directory__list_categories untrusted-input
- mcp__directory__whoami untrusted-input
- mcp__directory__prefill_from_url untrusted-input, outbound
- mcp__directory__submit_tool untrusted-input, outbound
- mcp__directory__create_payment untrusted-input
- mcp__directory__order_status untrusted-input
- mcp__directory__my_tools untrusted-input
- mcp__directory__update_tool untrusted-input
- mcp__directory__start_claim untrusted-input
- mcp__directory__verify_claim untrusted-input
- mcp__directory__login_link 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/ai.infobro/directory/verify?hash=24b585ff57bcbd3caf11a454efa756ce82f15dc0d54d8e318db8d779c079cab0" | jq -e '.changed == false'Pinned hash 24b585ff57bc, from Nov 18, 2026, 08:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.infobro/directory/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.infobro/directory)Source: MCP Registry. Synced Nov 4, 2026, 15:17 UTC.
infobro AI tools directory MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the infobro AI tools directory MCP server safe?
- No scan can promise that. What its definitions show: 15 tools, 9 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 infobro AI tools directory MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the infobro AI tools directory MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: create_payment.
What tools does the infobro AI tools directory MCP server have?
- 15 tools: 1 irreversible, 8 write, 6 read. create_payment, start_signup, verify_signup, submit_tool, my_tools, update_tool, start_claim, verify_claim and 7 more.
Does the infobro AI tools directory MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the infobro AI tools directory MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): prefill_from_url and submit_tool.
Has the infobro AI tools directory MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 18, 2026. Every change is on this page and in its Atom feed.