Skip to content
mcp/harbor
Verified official

Garita MCP MCP

v1.0.0

io.github.garitalab5/garita-mcp

30 security tools + the Vigia agent to audit MCP servers before you connect.

transport:streamable-http tools:30
View source

Target client

run in your project directory 

claude mcp add --transport http garita-mcp https://garita-mcp-server.onrender.com/mcp

setup guides: Claude Code Claude Desktop Cursor VS Code Zed Windsurf Cline Gemini CLI Grok ChatGPT Claude.ai LangChain

Adds it for this project only. Append --scope user to make it available everywhere. Claude Code docs

audit_mcp_server

audit mcp server

simulate_approval

simulate approval

detect_poisoned_tool_descriptions

detect poisoned tool descriptions

check_known_vulnerabilities Read-only

check known vulnerabilities

detect_tool_rug_pull

detect tool rug pull

detect_poisoned_config_files

detect poisoned config files

check_package_authenticity Read-only

check package authenticity

detect_memory_poisoning

detect memory poisoning

detect_ssrf_risk

detect ssrf risk

detect_path_traversal_risk

detect path traversal risk

detect_command_injection_risk

detect command injection risk

detect_sql_injection_risk

detect sql injection risk

detect_token_passthrough_risk

detect token passthrough risk

detect_hardcoded_secrets_risk

detect hardcoded secrets risk

detect_insecure_deserialization_risk

detect insecure deserialization risk

detect_toxic_flow_risk

detect toxic flow risk

detect_ssti_risk

detect ssti risk

detect_dynamic_code_risk

detect dynamic code risk

detect_dns_rebinding_risk

detect dns rebinding risk

detect_missing_auth_risk

detect missing auth risk

detect_mcp_stdio_launch_risk

detect mcp stdio launch risk

detect_redos_risk

detect redos risk

detect_session_hijack_risk

detect session hijack risk

detect_oauth_audience_confusion_risk

detect oauth audience confusion risk

detect_unbounded_allocation_risk

detect unbounded allocation risk

detect_cross_client_leak_risk

detect cross client leak risk

detect_sampling_hijack_risk

detect sampling hijack risk

detect_output_schema_ssrf_risk

detect output schema ssrf risk

detect_excessive_agency_risk

detect excessive agency risk

detect_call_spoofing_risk

detect call spoofing risk

All 30 tools, one page each

Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. Check the server's own documentation before granting access.