Loading…
Russian web data access for AI agents, fetching content from Russian websites and APIs through a Russian IP.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 1 month 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 russia-access MCP server exposes 9 tools, focused primarily on web and network capabilities. Its published description reads: "Russian web data access for AI agents, fetching content from Russian websites and APIs through a Russian IP". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates russia-access F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Data-exfiltration parameters" and "Cross-tool shadowing". 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 russia-access's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add russia-access to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://ruscrape.com/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.
Give a URL of ANY website or API — get its content (HTML/JSON) fetched through an IP of the chosen country (country='ru','us','de','gb',...). Flagship tool — URL in, content out, no proxy setup. Speci
Russia specialization of fetch_web (country='ru'): content of any Russian site/API through a Russian IP (Wildberries, Ozon, Yandex Market, gov registries, banks). residential=true for hard antibot.
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: fetch_web
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: fetch_web
A tool description tries to alter the model’s use of another tool.
ufficient (then topup_balance and retry).RecommendationDescriptions must describe only their own tool.
tool: fetch_ru
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: fetch_ru
A tool description tries to alter the model’s use of another tool.
ecialization of fetch_web (country='ru'): content of any Russian site/APIRecommendationDescriptions must describe only their own tool.
tool: get_ru_proxy
A tool description tries to alter the model’s use of another tool.
(then call topup_balance and retry). Idempotent per agent.RecommendationDescriptions must describe only their own tool.
tool: run_code
Tools that execute commands / write files / make arbitrary requests are exposed without annotations or guards.
/ javascript / bash) in an isolated sandbox (no network, CPU/RAM/tiRecommendationAnnotate destructive tools and require human approval.
tool: run_code
A tool description tries to alter the model’s use of another tool.
ufficient (then topup_balance and retry).RecommendationDescriptions must describe only their own tool.
tool: run_code
An exec/shell/run-code tool exposes a command/code/args parameter that is a free-form string with no enum/pattern guard — a direct command-injection / RCE surface. A tool constraining the command to an `enum` of allowed operations does not fire.
unconstrained command parameter "code"RecommendationReplace the free-form command with a fixed `enum` of allowed operations (or structured, escaped arguments) and require explicit human approval.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
. Flagship tool fetch_ru(agent_id, url): give a URL of any Russian websiRecommendationDescriptions 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: fetch_web
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "fetch_web"RecommendationScope 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.
Get a Russian IP proxy to access RU-only sites (Wildberries, Ozon, gov registries, banks) that block foreign IPs. Charged from agent balance; returns payment_required if insufficient (then call topup_
Run agent code (python / javascript / bash) in an isolated sandbox (no network, CPU/RAM/time limits) and get stdout/stderr/exit_code back. Charged from agent balance; returns payment_required if insuf
Check if a domain is available (.com/.ru/.рф). Free, no balance needed.
Get agent balance in minor units (kopecks).
Help improve this service: tell us what you need. question is one of: need_data (which Russian data sources you need), why_no_pay (if you didn't pay: price/payment_friction/ just_exploring/not_now), m
Top up agent balance. rail: usdc (x402) or rub (YooKassa). Returns pay_url to complete payment.
Register a .ru/.рф domain (secondary service). Charged from balance.