Security-first web access for Claude. Sanitizes pages, blocks injection, redacts PII.
How Visus-MCP helps your MCP-compatible AI agents become EU AI compliant ready "What the web shows you, Lateos reads safely." -- The EU AI Act (Regulation (EU) 2024/1689) is the world's first comprehensive AI law, effective from August 2024. It regulates AI systems based on risk levels, with stringent requirements for general-purpose AI (GPAI) like MCP-compatible agents that process web content.…
Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.
forge verify visus-mcpVerification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.
visus_context_scanNo description publishedThis tool published no description. Forge does not invent one.
visus_db_verifyNo description publishedThis tool published no description. Forge does not invent one.
visus_fetch_structuredNo description publishedThis tool published no description. Forge does not invent one.
visus_fetchNo description publishedThis tool published no description. Forge does not invent one.
visus_get_ledger_proofNo description publishedThis tool published no description. Forge does not invent one.
visus_scan_mcpNo description publishedThis tool published no description. Forge does not invent one.
comment_injectionNo description publishedThis tool published no description. Forge does not invent one.
direct_instruction_injectionNo description publishedThis tool published no description. Forge does not invent one.
role_hijackingNo description publishedThis tool published no description. Forge does not invent one.
system_prompt_extractionNo description publishedThis tool published no description. Forge does not invent one.
privilege_escalationNo description publishedThis tool published no description. Forge does not invent one.
context_poisoningNo description publishedThis tool published no description. Forge does not invent one.
data_exfiltrationNo description publishedThis tool published no description. Forge does not invent one.
base64_obfuscationNo description publishedThis tool published no description. Forge does not invent one.
unicode_lookalikesNo description publishedThis tool published no description. Forge does not invent one.
zero_width_charactersNo description publishedThis tool published no description. Forge does not invent one.
glassworm_unicode_clustersNo description publishedThis tool published no description. Forge does not invent one.
html_script_injectionNo description publishedThis tool published no description. Forge does not invent one.
data_uri_injectionNo description publishedThis tool published no description. Forge does not invent one.
markdown_link_injectionNo description publishedThis tool published no description. Forge does not invent one.
url_fragment_hashjackNo description publishedThis tool published no description. Forge does not invent one.
social_engineering_urgencyNo description publishedThis tool published no description. Forge does not invent one.
instruction_delimiter_injectionNo description publishedThis tool published no description. Forge does not invent one.
multi_language_obfuscationNo description publishedThis tool published no description. Forge does not invent one.
reverse_text_obfuscationNo description publishedThis tool published no description. Forge does not invent one.
leetspeak_obfuscationNo description publishedThis tool published no description. Forge does not invent one.
jailbreak_keywordsNo description publishedThis tool published no description. Forge does not invent one.
token_smugglingNo description publishedThis tool published no description. Forge does not invent one.
system_message_injectionNo description publishedThis tool published no description. Forge does not invent one.
conversation_resetNo description publishedThis tool published no description. Forge does not invent one.
memory_manipulationNo description publishedThis tool published no description. Forge does not invent one.
capability_probingNo description publishedThis tool published no description. Forge does not invent one.
chain_of_thought_manipulationNo description publishedThis tool published no description. Forge does not invent one.
hypothetical_scenario_injectionNo description publishedThis tool published no description. Forge does not invent one.
ethical_overrideNo description publishedThis tool published no description. Forge does not invent one.
output_format_manipulationNo description publishedThis tool published no description. Forge does not invent one.
negative_instructionNo description publishedThis tool published no description. Forge does not invent one.
credential_harvestingNo description publishedThis tool published no description. Forge does not invent one.
time_based_triggersNo description publishedThis tool published no description. Forge does not invent one.
code_execution_requestsprivilegedNo description publishedThis tool published no description. Forge does not invent one.
0 of 40 tools published a description.
Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.
How Visus-MCP helps your MCP-compatible AI agents become EU AI compliant ready "What the web shows you, Lateos reads safely." -- The EU AI Act (Regulation (EU) 2024/1689) is the world's first comprehensive AI law, effective from August 2024. It regulates AI systems based on risk levels, with stringent requirements for general-purpose AI (GPAI) like MCP-compatible agents that process web content. Art. 9 (Risk Management): Identify and mitigate systemic risks, including prompt injection and data…
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
This package was last scanned before Forge began storing the resolved tree. The next scan will record it.