MCP server · Silmaril

silmaril-firewall

Hosted, read-only, tenant-scoped MCP server that lets an agent read Silmaril Firewall security evidence (findings, metrics, suspicious users, investigation packets, traces) from an authorized tenant. Backed by Silmaril's firewall-ui API; does not connect directly to customer AWS, databases, traces, or runtime infrastructure.

Open endpoint → Silmaril provider profile

One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.

Provider: Silmaril Type: Hosted endpoint Transport: http Host: firewall-mcp.silmaril.dev

Endpoint

https://firewall-mcp.silmaril.dev/mcp

Hosted endpoint · transport http

Connect

This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):

# mcp client config (e.g. .mcp.json / mcp settings) { "mcpServers": { "silmaril": { "url": "https://firewall-mcp.silmaril.dev/mcp" } } }

For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:

# Add to claude_desktop_config.json { "mcpServers": { "silmaril": { "command": "npx", "args": ["-y", "mcp-remote", "https://firewall-mcp.silmaril.dev/mcp"] } } }

If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:

curl -i -X POST https://firewall-mcp.silmaril.dev/mcp \ -H "Content-Type: application/json" -H "Accept: application/json, text/event-stream" \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

Tools

list_firewalls — Discover available firewall deployments the account can access.
get_firewall — Inspect a deployment's runtime, freshness, warnings, and capabilities.
get_schema — Confirm available time ranges, limits, filters, and suspicious-user defaults.
get_metrics — Return firewall metrics for posture and trend questions.
get_finding_totals — Return finding totals over a time window.
group_findings — Group findings for posture and trend analysis.
list_findings — Return compact finding previews.
list_suspicious_users — Review user-level abuse and bot-farming correlation.
get_investigation_packet — Assemble evidence before opening full payloads or traces.
get_finding — Return a full finding payload (requires detail access).
get_finding_trace — Return a full finding trace (requires detail access).

About MCP

The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.

Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.