intentlink MCP server
io.github.whalefuntech/intentlinkwhalefuntechstreamable-httpv1.0.0Scanned
The best agent monetization tool: free search, clear rev-share, 10M+ commerce/travel/local offers.
3 tools: 3 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
Decide which of this server's tools your agent can use.
- 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 intentlink MCP server can do
The intentlink MCP server is published by the GitHub account whalefuntech. It has 3 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
None of its tools reads private data, brings in text other people write, or sends data 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.
Last scanned Nov 20, 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.
3 tools
Only reads 3Show 3 read-only tools
search_eventsSearch live ticketing/events (concerts, sports, theater) and get ranked event bundles.No findings
Why it is in this group
- The name "search_events" says "search": a word for reading.
Description, as the server wrote it Search live ticketing/events (concerts, sports, theater) and get ranked event bundles. Only `query` is required — a natural-language description of what the buyer wants (e.g. "taylor swift concert near LA this summer"). Add fields to narrow results: - keywords: exact terms — performer / team / show / venue (a precise lookup). - categories: e.g. ["Concerts"|"Sports"|"Theater"] (read the `events://categories` resource for valid values). - city / state: location (e.g. city="Los Angeles", state="CA"). country defaults to US. - date_from / date_to: explicit date window, YYYY-MM-DD (event dates are date-only). - when: fuzzy time — "this_weekend" | "this_week" | "this_month" | "next_7_days" | "next_30_days" (ignored if date_from/date_to are given). - min_price / max_price: ticket 'from' price band (USD). - sort: "relevance" (default) | "soonest" | "cheapest". - limit: max results (default 10). `agent_id` is REQUIRED: your registered, active agent id — the attribution + access key. A missing/blank or unregistered agent_id is rejected (no anonymous use). Returns {count, message, events:[{bundle_id,title,venue,city,next_date,price_min,..., sessions:[{date,price,buy_url,landing_url}]}]}. Each session's `buy_url` is ALREADY the trackable ticket link — hand it to the buyer directly. `landing_url` is the plain event page. When a date filter is given, `sessions` are the in-window dates.
search_productsSearch affiliate shopping products and get ranked recommendations.No findings
Why it is in this group
- The name "search_products" says "search": a word for reading.
Description, as the server wrote it Search affiliate shopping products and get ranked recommendations. Only `query` is required — a natural-language description of what the shopper wants (e.g. "a warm waterproof jacket for winter hiking"). Add fields to narrow results: - keywords: exact product terms. Use a SPECIFIC product type ("women running shoes", "stainless steel knife set"), not a bare generic noun ("shoes", "knife") — a generic keyword can surface the wrong audience. Audience/occasion go in `query`. - commerce_l2s: category ids to restrict to (read the `commerce://categories` resource for valid values — that taxonomy is for shopping only). - max_price / min_price: price band (USD). platforms: ["amazon"|"walmart"] (empty=all). - intent: ranking preset — "cheapest" | "best_discount" | "top_rated" | "best_value". - require_commission: only return products that pay a commission (default: server setting, normally on). Pass false to include zero/unknown-commission products. - limit: max results (default 10). `agent_id` is REQUIRED: your registered, active agent id. It is the attribution key and the access key — a missing/blank or unregistered agent_id is rejected (no anonymous use). Returns {count, products:[{offer_id,title,brand,price,rating,...,buy_url,product_url}]}. Each product's `buy_url` is ALREADY the trackable affiliate buy link — hand it to the shopper directly. (`product_url` is the plain product page.) There is no separate resolve/click step.
search_travelSearch travel offers and get trackable booking links for a given product type + city.No findings
Why it is in this group
- The name "search_travel" says "search": a word for reading.
Description, as the server wrote it Search travel offers and get trackable booking links for a given product type + city. REQUIRED: - type: which travel product — one of ["hotel","flights","bundle","airport_transfer","car_rental"]. - city: city name from the supported list — read the `travel://cities` resource for valid values (that city list is for travel only). Pass hotel.state (e.g. "NY") when the city name is ambiguous. - agent_id: your registered, active agent id — the attribution + access key. A missing/blank or unregistered agent_id is rejected (no anonymous use). HOTEL runs a live Trip.com search — pass the `hotel` object with the stay: check_in / check_out (YYYY-MM-DD), rooms, adults, children, state. If those are missing/invalid or the city can't be resolved, you get the hotel default links instead. Other types currently return curated default links (the `hotel` object is ignored for them). Returns {status, reason, message, links:{<type>:[{title, brand, platform, buy_url, product_url, ...}]}}. status is "ok" = a live hotel result; "fallback" = curated default links (see `reason`); "no_results" = nothing available for the type; "error" = the agent_id was rejected. Each `buy_url` is ALREADY the trackable booking link — hand it to the traveler directly. `product_url` is the plain merchant page.
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 untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- 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, 19:12 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
- 0
- 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
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.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http intentlink https://api.intentlink.io/mcp/claude mcp add --transport http intentlink https://api.intentlink.io/mcp/Run 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__intentlink__search_products",
"mcp__intentlink__search_travel",
"mcp__intentlink__search_events"
],
"ask": [],
"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 intentlink. Review it before you use it.
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.whalefuntech/intentlink/verify?hash=cb8ead4be9dc052bd5cf2df7d89190c9402f79e17bd11e73bed0f878821926bb" | jq -e '.changed == false'Pinned hash cb8ead4be9dc, from Nov 20, 2026, 18:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.whalefuntech/intentlink/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.whalefuntech/intentlink)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:51 UTC.
intentlink MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the intentlink MCP server safe?
- No scan can promise that. What its definitions show: 3 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.
Can the intentlink MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the intentlink 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 intentlink MCP server have?
- 3 tools: 3 read. search_products, search_travel and search_events.
Does the intentlink MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the intentlink MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the intentlink MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.