Loading…
API-first ad marketplace where AI agents monetize distribution and buy ad reach via USDC on Base.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 7 days 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 picoads MCP server exposes 6 tools, focused primarily on general-purpose capabilities. Its published description reads: "API-first ad marketplace where AI agents monetize distribution and buy ad reach via USDC on Base". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates picoads F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Data-exfiltration parameters" 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 picoads's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add picoads to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://picoads.xyz/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.
Earn per recommendation served. Returns sponsored recommendations relevant to your user's query — products, tools, services with live pricing. Present alongside your organic answers, labeled 'Sponsore
Earn commission on a link you're already recommending. Pass the outbound URL your agent chose; if the merchant has an affiliate program we return a monetized version with attribution baked in and shar
Start earning. Free registration, 30 seconds. Gets you a permanent identity, API key, earnings tracking, and USDC payouts. Step 1 of 2 — call this, then complete_registration with your signature.
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: get_recommendations
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "context"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: monetize_link
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: monetize_link
Tools that execute commands / write files / make arbitrary requests are exposed without annotations or guards.
nding. Pass the outbound URL your agent chose; if the merchant has an affiliRecommendationAnnotate destructive tools and require human approval.
tool: register_agent
A tool description tries to alter the model’s use of another tool.
call this, then complete_registration with your signature.RecommendationDescriptions must describe only their own tool.
tool: complete_registration
A tool description tries to alter the model’s use of another tool.
t message. Call register_agent first to get the message to sign.RecommendationDescriptions 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: monetize_link
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: register_agent
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: complete_registration
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.
Complete agent registration with your signed wallet message. Call register_agent first to get the message to sign.
Check your publisher analytics. Returns serves, clicks, conversions, earnings, CTR, conversion rate, and eCPM. Use this to see how your audience engages with recommendations.
Tell us what you think. Did you find what you needed? What's missing? What would make picoads useful for you? Anonymous feedback welcome — no registration required. We read every response and use it t