FABRIC Testbed MCP Server — exposes FABRIC API operations as LLM-accessible tools
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"fabric-api-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# FABRIC API MCP Server [](https://www.python.org/downloads/) [](./LICENSE) [](https://modelcontextprotocol.io/) A production-ready **[Model Context Protocol (MCP)](https://modelcontextprotocol.io/)** server that lets LLM clients (Claude Desktop, Claude Code, VS Code Copilot, ChatGPT, Chatbox, etc.) **query, provision, and manage** resources on the **[FABRIC Testbed](https://fabric-testbed.net/)** — a nation-wide programmable network research infrastructure. ### Key features - **Two modes** — run locally (full-featured, SSH to VMs) or connect to a shared remote server - **30+ tools** — query sites/hosts/links, build slices, modify resources, manage SSH keys, reboot nodes, and more - **Stateless & secure** — no credentials stored; every call uses a Bearer FABRIC ID token (server mode) or local `fabric_rc` config (local mode) - **Declarative filter DSL** — powerful filtering, sorting, and pagination on all query tools - **Production-ready** — OpenResty reverse proxy, Prometheus metrics, Grafana dashboards, structured logging with per-request tracing - **Resource cache** — optional background refresh for sub-second topology queries --- ## Table of contents | Getting started | Reference | Operations | |:---|:---|:---| | [Quick install](#quick-install) | [Tools reference](#tools-reference) | [Deploy with Docker Compose](#deploy-with-docker-compose-server-mode) | | [MCP client configuration](#mcp-client-configuration) | [Filter DSL & examples](#filter-dsl) | [Monitoring & Metrics](#monitoring--metrics-server-mode-only) | | [Local mode setup](#local-mode-setup) | [Environment variables](#environment-variables) | [Adding new tools](#adding-new-tools) | | [Remote mode setup](#remote-mode-setup) | [Architecture & repo layout](#architecture) | [Security notes](#security-note…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.