fabric-mcp
Enables interaction with Equinix Fabric via MCP protocol, providing 109 tools for managing Fabric resources with client-credentials authentication and governance.
README
fabric-mcp — aligned Equinix Fabric MCP server (self-hosted)
A local, self-hosted Python MCP server that reimplements the contract of the hosted
mcp.equinix.com/fabric server (109 tools, protocol-compatible) over the public Fabric REST v4
API — with client-credentials auth (no browser OAuth) and a governance layer that lets us
safely add destructive operations. Supersedes the fragile hosted-OAuth path (CIMD invalid_request,
Desktop timeouts, token-cache churn) and the old ungated equinix-fabric-python server.
Why
mcp.equinix.com/fabricis hosted + user-delegated OAuth → fights Claude Desktop's 60s timeout and Equinix's CIMD rejection. A local stdio server with client-credentials sidesteps all of it.- Full control: our own codebase, our own extensions, governed delete/deprovision.
Status (steps 1–3 done, no credentials needed)
- Contract (
contract/contract.json) — 109 official tools + 3 governed extensions, each with{authority, category, rest_hint, schema:pending, implemented_in_v1}. - Gap map (
contract/GAP.md) — vs the oldequinix-fabric-mcp/server.py(~15 covered, 94 to build). - Governance core (
governance/gate.py) — authority classifier + dry-run-before-write + confirm + destructive allow-list + two-key + protected-targets + audit. Self-tested.
Architecture
Claude Desktop / LiteLLM ──(stdio MCP)──► fabric-mcp (this server)
│ client-credentials (no browser)
├─ governance/gate.py (authority + approval + audit)
└─ REST ──► api.equinix.com/fabric/v4
Authority tiers: read-only = allowed+audited · write = dry-run→confirm · destructive = dry-run + allow-list + two-key + protected-target deny.
Remaining (needs credentials)
- Step 4 — implement the 94 REST wrappers (read-only → write → governed destructive), filling
per-tool input schemas from a fresh
tools/listdump or the Fabric v4 OpenAPI spec. - Step 5 — wire into Claude Desktop (local stdio, the working path) + optional LiteLLM route; live-test with the fresh key.
Credentials — drop point
This server authenticates with the Fabric REST API via OAuth2 client-credentials
(https://api.equinix.com/oauth2/v1/token, grant_type=client_credentials). Generate a fresh
API key pair in the Equinix portal (developer.equinix.com → your app → Consumer Key/Secret) and
put them in ~/Development/Equinix/fabric-mcp/.env (gitignored):
EQUINIX_CLIENT_ID=<consumer key>
EQUINIX_CLIENT_SECRET=<consumer secret>
FABRIC_MCP_MODE=mock # mock (default) | live
The server reads them from the environment only — never hardcoded, never committed. See .env.example.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.