Grabblist is an MCP server with 23 tools an agent can call, among them add_item, add_to_collection, ask_agent. It answers at https://mcp.grabbitapp.com/api/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 5 September 2026; the last check, on 18 October 2026, succeeded.
Save and organize web finds in persistent, user-controlled collections for AI assistants.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
add_item | Save an item to the user's Grabblist. Creates a static snapshot — Grabblist does not monitor prices or auto-update data. Only include fields with values available from the source. If no image is provided, the server attempts to fetch og:ima Inputs: url, title, price, currency, image, images |
add_to_collection | Add a saved item to a collection. Both the item and collection must already exist. Inputs: collection_id, item_id, reason |
ask_agent | Delegate a task to Grabblist's built-in AI assistant. The agent knows the user's Grabblist and can answer questions, compare items, give shopping advice, or analyze saved products. Use this when you want a second opinion or a specialized sh Inputs: message, model |
create_collection | Create a new collection (folder) in the user's Grabblist to organize saved items. Inputs: name, icon, color, description, budget, budget_currency |
delete_collection | Permanently delete a collection. Items inside are not deleted — they stay in the Grabblist. Inputs: id, reason |
delete_item | Remove one or more items from the user's Grabblist (soft-delete). Pass a single id or an array of ids for batch operations. Inputs: id, reason |
get_collection_activity | Get recent activity on a collection — additions, removals, edits. Inputs: collection_id, limit |
get_item | Get full details of a saved item by ID. Returns a static snapshot from the user's Grabblist. Inputs: id |
get_item_graph | Get all relations for an item — alternatives, complements, upgrades, duplicates. Returns the item and all connected items with their relation types. Inputs: id |
get_item_history | Get the change history for a saved item — who changed what and when. Inputs: item_id, limit |
get_wishlist | Get all saved items from the user's Grabblist. Each item is a static snapshot — data reflects the moment it was saved, not current prices. Inputs: limit, platform |
link_items | Create typed relations between items: alternative (A or B), complement (A and B together), upgrade (B replaces A), duplicate (same item different site), same_seller. Supports single pair (from_id, to_id, relation) or bulk (pairs array). Inputs: from_id, to_id, relation, pairs, reason |
list_collections | List all collections OR get a specific collection with its items. Without id: returns all collections with counts/values. With id: returns that collection's metadata and all items inside (with optional filters). Inputs: id, status, created_by, min_price, max_price, platform |
ping | Test connectivity to Grabblist and return service version. |
remove_from_collection | Remove one or more items from a collection. Pass a single item_id or an array of item_ids for batch removal. Items are NOT deleted — they stay in the Grabblist. Inputs: collection_id, item_ids, reason |
restore_item | Restore one or more deleted (archived) items back to the Grabblist. Pass a single id or an array of ids for batch restore. Inputs: id, reason |
search_saved | Search within the user's saved items by keyword Inputs: query, limit |
send_feedback | Send feedback, bug report, or feature request to the Grabbit team. Use this when you encounter parsing failures, missing features, broken URLs, or have improvement suggestions. The team reads these to improve the product. Be specific about Inputs: type, message, url, tool, error |
set_pinned_items | Set the pinned "Top Picks" items for a collection (max 3). Pinned items are highlighted on the share page. Inputs: collection_id, item_ids, reason |
unlink_items | Remove a relation between two items. Inputs: from_id, to_id, relation, reason |
update_collection | Update a collection's name, icon, description, budget, or sharing status. Only provide the fields you want to change — omitted fields stay unchanged. Set is_public=true to share (returns public URL), is_public=false to unshare. Inputs: id, name, icon, color, description, budget |
update_item | Edit fields on one or more saved items. Pass a single id or an array of ids for batch updates (same fields applied to all). For batch: attributes are REPLACED not merged, og:image fallback is skipped. Inputs: id, notes, status, item_type, category, target_price |
update_price | Manually update the price on a saved item. Records old and new price for comparison. This is a manual correction, not automatic price tracking. Inputs: id, price, source, reason |
Every block below points at https://mcp.grabbitapp.com/api/mcp. Pick your client and copy.
claude mcp add --transport http grabblist https://mcp.grabbitapp.com/api/mcp
{
"mcpServers": {
"grabblist": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.grabbitapp.com/api/mcp"]
}
}
}{
"mcpServers": {
"grabblist": {
"url": "https://mcp.grabbitapp.com/api/mcp"
}
}
}{
"servers": {
"grabblist": {
"type": "http",
"url": "https://mcp.grabbitapp.com/api/mcp"
}
}
}{
"context_servers": {
"grabblist": {
"url": "https://mcp.grabbitapp.com/api/mcp"
}
}
}{
"mcpServers": {
"grabblist": {
"serverUrl": "https://mcp.grabbitapp.com/api/mcp"
}
}
}{
"mcpServers": {
"grabblist": {
"url": "https://mcp.grabbitapp.com/api/mcp"
}
}
}name: Grabblist
version: 0.0.1
schema: v1
mcpServers:
- name: Grabblist
type: streamable-http
url: https://mcp.grabbitapp.com/api/mcp{
"mcpServers": {
"grabblist": {
"httpUrl": "https://mcp.grabbitapp.com/api/mcp"
}
}
}{
"mcpServers": {
"grabblist": {
"type": "http",
"url": "https://mcp.grabbitapp.com/api/mcp"
}
}
}{
"mcpServers": {
"grabblist": {
"url": "https://mcp.grabbitapp.com/api/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fmcp.grabbitapp.com%2Fapi%2Fmcp&type=streamable_http&id=grabblist&name=Grabblist
It answered our last check on 18 October 2026 in 311 ms. Over 10 checks since 5 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by grabbitapp.com and served from mcp.grabbitapp.com, the vendor's own domain: https://mcp.grabbitapp.com/api/mcp.
23, as returned by the server's own tools/list on 31 August 2026: add_item, add_to_collection, ask_agent, create_collection, delete_collection, delete_item, get_collection_activity, get_item, and 15 more.
It answered our last check on 18 October 2026 in 311 ms. Over 10 checks since 5 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp.grabbitapp.com/api/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: com.grabbitapp. Endpoint host: mcp.grabbitapp.com. ARD identifier: urn:air:com.grabbitapp:mcp:grabblist.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.