fyi
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Endpoint
Hosted endpoint · transport http
Connect
This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):
For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:
If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:
Tools
demand.search— Find products to buy for the user across many sources; ephemeral, persists nothing. Inputs title, description, price_cents, price_currency, category, vertical, mode, location, constraints, cursor, client_ref.demand.find_vehicle— Find a specific car, truck, SUV or van from live dealer inventory; returns VIN, dealer, distance, mileage, accident/owner history. Inputs query, make, model, trim, year_min, year_max, price_max_cents, mileage_max, zip, radius_miles, condition, fuel.demand.price_check— Whether the asking price on one specific car is a good deal — percentile, median, typical range and sample size over comparable live listings; returns insufficient_data rather than guessing.demand.request_introduction— Ask a specific dealer a question about one car from demand.find_vehicle; iwant.fyi emails the dealer via a per-introduction reply address. Sends a real message — irreversible.demand.introduction_status— Poll whether the dealer has answered an introduction and read the reply.demand.list_verticals— Spec 8.2: verticals with first-class spec vocabulary (tools, auto_parts) and their supported_spec_keys.demand.list_constraints— Spec 8.2: the constraint vocabulary (pricing, condition, time, brand, location, vertical_specs, negotiable_and_auto_accept) plus the x_ extension namespace rule.demand.health— Spec 8.2: liveness/readiness, protocol version, active supply sources (autodev, klarna, native, shopify; acp pending).demand.capabilities— Spec 8.2 (v1.1): supported versions, features (webhooks, idempotency, failure_transparency, error_taxonomy, capabilities, http_fallback), limits, and the full tool list.demand.ask— Plain-language request; one clarifying question at most; ranked matches. The MCP twin of the A2A message/send surface. Inputs message, conversation_id.demand.create_want— Spec 8.1 (required): persist a Want and return matched supply in the same call. Accepts client_token for idempotency (v1.1 8.4). Needs a claimed key to post on a human's behalf.demand.get_want— Spec 8.1 (required): retrieve a Want by id with its current matches.demand.record_outcome— Spec 8.1 (required): report viewed / clicked / started_checkout / purchased / abandoned / not_purchased for attribution. Idempotent.demand.create_watch— Spec 16 (v1.1): register a Standing Want that re-matches on a schedule and notifies an https webhook; returns the whsec_ signing secret exactly once.demand.list_watches— List the caller's Standing Wants.demand.cancel_watch— Cancel a Standing Want (the reversal path for demand.create_watch).demand.declare_supply— Hand over a seller catalog by domain (Shopify / product JSON-LD sites indexed automatically) or feed_url (schema.org JSON-LD, ACP JSONL, CSV, XML); returns supply_source_id, verification tier, listings ingested.demand.subscribe_supply— Have matching buyer wants pushed to a signed webhook or the seller's A2A endpoint; pushed wants carry unlock_url and an x402 unlock block.browse_wants— Search and filter active wants by category, location, price. (Legacy alias; the public REST twin listWants needs no key.)get_want— Get want details with responses.create_want— Post a new want with optional structured constraints; claim_required until the key is claimed.respond_to_want— Submit a seller offer to an existing want.search_listings— Search the supply directory (native listings + Shopify Catalog).create_listing— List a product or service for sale.search_products— Search across all connected external marketplaces.my_agent_profile— View agent profile, trust score, transaction stats and active API keys.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.