Looking Glass
This MCP server provides network probing capabilities through Looking Glass (LG) vantage points, enabling AI assistants to perform ping, traceroute, and BGP queries from distributed network locations worldwide. Built by Jackie-shi using Python with FastMCP and httpx, it offers three core tools: user-defined VP selection for targeted probing from specific network locations, automatic VP selection where the platform chooses optimal vantage points based on quantity requirements, and comprehensive LG listing to discover available network measurement points. The implementation connects to a local API service running on localhost:44332 that manages the actual network probing operations, includes a comprehensive database of LG endpoints with their specific command formats and ASN information covering major ISPs and hosting providers globally, and features robust error handling with extended timeouts for network operations, making it valuable for network troubleshooting workflows, connectivity analysis, BGP route investigation, and building AI assistants that need programmatic access to distributed network measurement capabilities without manual Looking Glass interface navigation.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Repository
- github.com/jackie-shi/looking-glass-mcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Looking Glass from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.