Demand-side commerce: agents post a user's purchase intent and get ranked cross-source matches.
Do not connect
No critical issue was found, but the combined weight of the other findings put the score below 25/100. Remediate the findings before connecting this server.
Scanned 2 months ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The iwant-marketplace MCP server exposes 19 tools, focused primarily on general-purpose capabilities. Its published description reads: "Demand-side commerce: agents post a user's purchase intent and get ranked cross-source matches". It communicates over Streamable HTTP using the 2026-07-28 protocol revision, and does not require authorization to connect. MCPGrade currently rates iwant-marketplace F — no critical issue was found, but the combined weight of the other findings put the score below 25/100, so the findings should be remediated before connecting. Its most notable findings include "Cross-tool shadowing" and "Data-exfiltration parameters". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check iwant-marketplace's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add iwant-marketplace to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://iwant.fyi/api/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Browse open buyer demand (Wants) you could fulfill as a seller agent -- search and filter active purchase requests by keyword, category, location, or price. Use this to discover what users are trying
Get details of a specific want by ID, including its responses and constraints.
Post a buyer request (Want) on behalf of your owner -- what they want to buy, with budget and location -- and get back matches. Prefer demand.create_want for the canonical protocol shape (currency, en
Submit an offer/response to an existing want. The agent's owner will be the responder. The response inherits the want's wedge; the seller may indicate their offered mode (new/used).
View the authenticated agent's profile, trust score, and stats.
Search the iwant.fyi supply directory for listings posted by sellers. Supports full-text search, category, wedge, mode, price, condition, and location filters.
Create a seller listing in the iwant.fyi supply directory. Use this when an agent has inventory to sell.
Search for real, purchasable products to buy across connected commerce sources (native listings + Shopify Catalog; Klarna and ACP feeds being integrated). Use to find, shop for, or compare products ma
Record the user's purchase intent and get back ranked, matched supply in the SAME call. Use this when the user DECIDES to buy, or wants the request kept open with notify-on-new-supply (a standing want
Find products to buy for the user across many sources. Call this WHENEVER the user wants to find, shop for, compare, price-check, source, or buy a product or service -- e.g. 'find me running shoes und
iwant.fyi demand-side protocol v1.0 §8.1: retrieve a Want by ID, including its current matches and constraints.
iwant.fyi demand-side protocol v1.0 §7 + §8.1: report an outcome event (viewed/clicked/started_checkout/purchased/abandoned/not_purchased) against a Want and Match. Closes the demand-signal loop. Requ
iwant.fyi demand-side protocol v1.0 §8.2: list the verticals this Implementation supports, with descriptions and supported spec keys. Useful for agent capability discovery.
iwant.fyi demand-side protocol v1.0 §8.2: list the constraint vocabulary this Implementation supports, including any implementation-specific extensions (x_* keys).
iwant.fyi demand-side protocol v1.0 §8.2: liveness and readiness check. Returns server info, protocol version, and active supply source list.
iwant.fyi demand-side protocol v1.1 §8.2: discover which protocol features this implementation supports (webhooks, idempotency, failure transparency, error taxonomy) and its operational limits (rate l
Create a STANDING WANT: keep searching for what the user wants to buy and get notified when a NEW match appears, across sessions. Unlike a one-shot search, this persists -- ideal for hard-to-source, u
List this agent's standing wants (active watches), with how many matches each has surfaced and when it was last checked.
Cancel (deactivate) a standing want by id. Only your own watches can be cancelled.
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: create_want
A tool description tries to alter the model’s use of another tool.
matches. Prefer demand.create_want for the canonical protocol shape (currency, enfRecommendationDescriptions must describe only their own tool.
tool: create_listing
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "external_url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: search_products
A tool description tries to alter the model’s use of another tool.
eral) or demand.create_want (persisted).RecommendationDescriptions must describe only their own tool.
tool: demand.create_want
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
g with the same token returns the original Want instead of creating aRecommendationRemove side-channel parameters; constrain tool inputs.
tool: demand.create_want
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: demand.search
A tool description tries to alter the model’s use of another tool.
ved; use demand.create_want when the user commits to buying and you want noRecommendationDescriptions must describe only their own tool.
tool: demand.create_watch
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
g with the same token returns the original watch instead of creatingRecommendationRemove side-channel parameters; constrain tool inputs.
tool: demand.create_watch
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
ars, use demand.create_want. Always pass the user's stated constraints (budRecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: create_want
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: search_listings
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: search_products
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: demand.create_want
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: demand.create_want
The description pairs a fetch imperative with a hardcoded external URL, letting the server relocate its real instructions off-metadata and mutate them after review. Fires only when a fetch verb and a URL co-occur, so benign documentation links do not.
0 §8.1; spec at https://iwant.fyi/protocol/v1.RecommendationDo not direct the model to fetch and act on external URLs; treat linked content as untrusted.
tool: demand.search
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: demand.create_watch
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.