A setup guide for Fusion MCP, a managed service that gives coding assistants Fusion-aware retrieval and workflow support. MCP is a standard way for an AI client to use external tools.

Use it to set up, verify, or troubleshoot Fusion MCP, primarily with VS Code. It also explains the service's retrieval capabilities and the need for an available Equinor Entra account.

It explains the required accounts, client settings, and verification steps so developers can use Fusion information in Copilot workflows without running local infrastructure in most cases.

fusion-mcp — Skill for Claude Code and Codex by equinor

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add equinor/fusion-skills --skill fusion-mcp

Clone the repo

git clone --depth 1 https://github.com/equinor/fusion-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/equinor/fusion-skills/fusion-mcp/github.svg)](https://agentmods.dev/skills/equinor/fusion-skills/fusion-mcp)

Your own site

<a href="https://agentmods.dev/skills/equinor/fusion-skills/fusion-mcp"><img src="https://agentmods.dev/badge/skills/equinor/fusion-skills/fusion-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/equinor/fusion-skills/fusion-mcp"><img src="https://agentmods.dev/badge/skills/equinor/fusion-skills/fusion-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,163 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

Socket pass 9 May 2026
Snyk warn 9 May 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00028	$0.01163
Opus 5	$0.00014	$0.00581
Sonnet 5	$0.00006	$0.00233
Haiku 4.5	$0.00003	$0.00116

Measured 10d ago against content hash bb4776ee0430, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

fusion-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/.experimental/fusion-mcp/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fusion MCP Setup Guide

When to use

Use when a user asks:

what Fusion MCP is
what it can do
how to install/configure it
how to verify it is working
how to troubleshoot a failing Fusion MCP setup

Typical triggers:

"what is fusion mcp"
"help me set up fusion mcp"
"how do I use fusion mcp with copilot"

When not to use

Implementing product features unrelated to MCP setup
Making destructive environment changes without user confirmation
Assuming private repository details not visible
Answering source-backed questions about Fusion Framework APIs, EDS components, or the skill catalog — once MCP is running, use fusion-research for that

Required inputs

Collect before proposing setup steps:

user environment (OS, editor/runtime)
target client where MCP will run (VS Code is primary target)
whether user's Equinor Entra account is available

If details are missing, ask concise follow-up questions first.

Instructions

Explain what this MCP server provides:
- Fusion-oriented MCP capabilities for retrieval and workflow support
- hosted as a managed service — no local infrastructure required for most developers
- retrieval tools: search, search_framework, search_docs, search_eds, search_indexes, search_backend_code
- tool surface may evolve over time
Guide user to set up the hosted production server — the only recommended path:
- no Docker, no API keys, no local clone needed
- VS Code authenticates via Microsoft Entra (Equinor account)
- use the one-click install link for prod (see references/vscode-mcp-config.md)
- or manual config with "type": "http" and server URL (see references/vscode-mcp-config.md)
- don't suggest local Docker, GHCR, or self-hosted alternatives unless user has explicit operational need
Describe the authentication flow:
- on first tool invocation VS Code prompts sign in with Equinor Entra account
- tokens managed automatically; silent renewal when possible, interactive prompt when needed
- access controlled by existing Fusion role assignments
Provide a lightweight MCP smell test:
- run initialize and confirm successful response
- run tools/list and confirm at least one tool returned
- run one non-destructive tools/call against an available tool
- pass criteria: call response is non-empty (content or structuredContent contains data)
- note: don't hard-code a fixed tool list; tool inventory can change between versions
Troubleshoot in documented order:
- Entra sign-in prompt not appearing → verify oauth.clientId in config and that VS Code is signed in with an Equinor account
- 401 Unauthorized → re-authenticate via VS Code account settings; ensure Equinor Entra account is active
- tools/list returns empty or tool call fails → verify MCP server entry is selected/enabled in VS Code and retry after reloading
- partial tool behavior → check VS Code Output > Copilot for error details and restart the MCP server
When MCP setup fails or user asks to file a bug, produce a bug report draft from assets/bug-report-template.md.
- default target repository: equinor/fusion-mcp
- include concrete repro steps, expected vs actual behavior, and troubleshooting already attempted
- include non-sensitive environment details (OS, VS Code version, MCP server URL, Entra account type)
- never include secrets, tokens, or raw credential values
For uncertainty or repo-private constraints, state assumptions explicitly and link to authoritative docs instead of guessing.

Read the full file on GitHub · 115 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

10d ago First seen · 115 lines · 28 tokens per session scan A bb4776ee0430

Subscribe to this mod's changes

fusion-mcp is a skill published in the GitHub repository equinor/fusion-skills (1 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 1,163 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens