Claude MarketplacesSubmit
krishnagauss avatar

GEO Shield

krishnagauss/mcp_websafe

Detects hidden AI prompt injection, AI recommendation poisoning, sneaky redirects and hidden spam.

tools
3
transport
STDIO
env vars
3
last updated
Nov 12, 2026
View on GitHub

Tools

3 tools

Public tool metadata for what this MCP can expose to an agent.

geo_scan_urlFetches one URL (SSRF-protected, no JS execution), reconstructs redirects, runs all rules.

Fetches one URL (SSRF-protected, no JS execution), reconstructs redirects, runs all rules.

No parameter schema in public metadata yet.

geo_trace_redirectsHop-by-hop redirect chain (3xx + Refresh), each hop re-validated; reports declared meta/JS redirects on the final page.

Hop-by-hop redirect chain (3xx + Refresh), each hop re-validated; reports declared meta/JS redirects on the final page.

No parameter schema in public metadata yet.

geo_get_reportFull stored report as markdown or json.

Full stored report as markdown or json.

No parameter schema in public metadata yet.

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Configuration

GEO_SHIELD_DB_PATH

SQLite file for stored scans (default ~/.geo-shield/geo-shield.db).

GEO_SHIELD_RETENTION_DAYS

Days to keep stored scans (default 30, 0 = forever).

GEO_SHIELD_ALLOWED_PORTS

Extra destination ports to allow besides 80 and 443, comma separated.

Readme

GEO Shield MCP

npm License: MIT

A defensive, read-only MCP server that lets AI agents (Claude, Gemini CLI, Cursor, VS Code Copilot, Codex and others) inspect websites for manipulation aimed at search engines and AI assistants: sneaky and open redirects, hidden text and links, injected spam, hijacked metadata, hidden prompt-injection text, and "Summarise with AI" links whose prefilled prompts try to plant instructions in a visitor's assistant ("AI recommendation poisoning").

Every finding is produced by a deterministic rule and backed by evidence: location, visibility state, an excerpt, severity and confidence (kept separate), remediation, and false-positive notes. Scanned content is always treated as untrusted data.

Status: Milestone 1. geo_scan_url, geo_trace_redirects and geo_get_report are implemented and tested. See Pending for later phases.

Install

View the full README on GitHub

Details

Repository
github.com/krishnagauss/mcp_websafe
Category
AI & LLM Tools
Package
geo-shield-mcp
Transport
STDIO
Registry
MCP registry, active

Related AI & LLM Tools MCP servers

View all
1kubyer avatarSTRUGGL Hybrid Coachkubyer/struggl-mcpZero-LLM-Math sports science calculators (Hyrox, 1RM/RPE, Zone 2, MEV/MRV) & workout ledger.0stars
2larrylemonbot avatarSignal Desk by LarryBuildsAIlarrylemonbot/signal-desk-mcp-serverOne-to-three-cent spend routing, lead research, token-risk, and agent-tool comparison preflights.0stars
3lmaniraruta avatarAgentstorefrontlmaniraruta/agentstorefront-mcpMCP for AgentStorefront — discover, price, and subscribe to paid agent services.0stars
4luuow avatarMeridian Skillsluuow/meridian-mcpRoutes AI tasks to dynamic LLM-generated skills via an orbital classifier.0stars
5major avatarPerformance Co-Pilotmajor/pcp-mcpQuery system performance metrics via MCP - CPU, memory, disk I/O, network, processes0stars
6marketinglior-pixel avatarAgentBillio.github.marketinglior-pixel/agentbill-mcpOne spend ceiling per agent job, as MCP tools. Bound to a task_ref you pass, not a calendar month.0stars