bifrost-mcp-setup

bifrost-mcp-setup is a skill for Claude Code from neXenio/bifrost-plugin. It costs 114 tokens per session (1,287 once invoked), scanned B, original, MIT.

Instructions for manually connecting the Bifrost MCP server to Claude Code, Claude Desktop, or claude.ai. MCP is a way for an AI tool to connect to external services.

In plain words
What is it for?
Setting the Bifrost gateway URL and virtual key, registering the server in Claude Code, adding it through the Claude plugin interface, restarting the client, and checking the connection.
Why use it?
It provides a setup path when the automatic installer cannot run, such as without internet access or under a policy restriction. It also keeps the virtual key in your shell environment instead of saving it in configuration files.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the bifrost-plugin plugin — 5 skills, 5 commands, 5 hooks, 1 MCP server shipped together

Good fit Setting the Bifrost gateway URL and virtual key, registering the server in Claude Code, adding it through the Claude plugin interface, restarting the client, and checking the connection.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nexenio/bifrost-plugin/bifrost-mcp-setup
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 neXenio/bifrost-plugin --skill bifrost-mcp-setup
Clone the repo
git clone --depth 1 https://github.com/neXenio/bifrost-plugin

Made for: Claude Code.

Or install bifrost-plugin, the plugin that ships this one along with the rest of its 5 skills, 5 commands, 5 hooks, 1 MCP server.

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.

agentmods badge for bifrost-mcp-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/nexenio/bifrost-plugin/bifrost-mcp-setup.svg)](https://agentmods.dev/skills/nexenio/bifrost-plugin/bifrost-mcp-setup)
Your own site
<a href="https://agentmods.dev/skills/nexenio/bifrost-plugin/bifrost-mcp-setup"><img src="https://agentmods.dev/badge/skills/nexenio/bifrost-plugin/bifrost-mcp-setup.svg" alt="Measured on agentmods" height="20"></a>
Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,287 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00114 $0.01287
Opus 5 $0.00057 $0.00643
Sonnet 5 $0.00023 $0.00257
Haiku 4.5 $0.00011 $0.00129

Measured 7d ago against content hash c52384d56d59, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

bifrost-mcp-setup scanned grade B with 1 finding 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 7d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

treat it as a secret (`chmod 600` on macOS/Linux) and never commit it.
skills/bifrost-mcp-setup/SKILL.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Manual Bifrost MCP Setup

Use this when the automated installer (node bin/install.js / /bifrost-setup) can't run (no internet, policy restriction, etc.).

Note: if the plugin itself is installed and enabled, none of this is needed — the plugin's shipped .mcp.json registers the bifrost server automatically. This skill is for wiring the MCP server WITHOUT the plugin.

Step 1 — Set your gateway URL and virtual key

# Add to ~/.zshrc or ~/.bashrc (replace with your real values):
export BIFROST_URL=https://<your-gateway-host>/mcp
export BIFROST_VK=vk_<your-key>
source ~/.zshrc   # or ~/.bashrc

Never commit the VK. It belongs in your shell env only.

Step 2 — Register the server with the Claude Code CLI

claude mcp add --scope user --transport http bifrost \
  "${BIFROST_URL}" --header 'x-bf-vk: ${BIFROST_VK}'

The single-quoted ${BIFROST_VK} is stored as a runtime template — Claude Code resolves it from your shell env on every launch, so the key itself is never written to disk. Re-running the command replaces the same entry (idempotent).

Step 3 — Restart Claude Code

MCP registration changes take effect only after a CC restart.

Step 4 — Verify

# Confirm the entry is present:
claude mcp get bifrost

# Confirm env vars are set:
echo "URL: ${BIFROST_URL:-NOT SET}"
echo "VK: ${BIFROST_VK:+set (${#BIFROST_VK} chars)}${BIFROST_VK:-NOT SET}"

If your gateway exposes a skill server, then inside Claude Code call mcp__bifrost__<skills-server>-skill_search with "test" — if it returns results, the gateway is live.

Uninstall

claude mcp remove --scope user bifrost

Claude Desktop

Desktop has no shell, so ${BIFROST_URL} and ${BIFROST_VK} never resolve there, and it does not read this project's .mcp.json. The supported path is installing the plugin itself, which prompts for the gateway URL, virtual key, and OAuth client ID at install time and stores them as plugin config. The bundled .mcp.json reads those back as ${user_config.gateway_url} and so on.

Read the full file on GitHub · 125 lines

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.

  1. 7d ago First seen · 125 lines · 114 tokens per session scan B c52384d56d59

Subscribe to this mod's changes

bifrost-mcp-setup is a skill published in the GitHub repository neXenio/bifrost-plugin (2 stars, last pushed 19d ago), licensed MIT. It adds 114 tokens to every session and 1,287 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

oatda-list-models

Use when the user wants to list available AI models from OATDA's 10+ providers. Filter by type (chat, image, video, audio) or by provider name, including speech, transcription, and translation models.

devcsde/oatda-skills · 52 tokens

oatda-compare-models

Use when the user wants to compare outputs from multiple LLM models side-by-side in a single request. Sends one prompt to multiple providers (OpenAI, Anthropic, Google, DeepSeek, etc.) in parallel via OATDA's /api/v1/compare endpoint and returns each model's response. Triggers on "compare models", "which model is…

devcsde/oatda-skills · 107 tokens

oatda-generate-image

Use when the user wants to generate images using AI models through OATDA's unified API. Supports DALL-E 3, GPT-Image-1, Google Imagen, MiniMax, Qwen, and xAI image models.

devcsde/oatda-skills · 53 tokens

oatda-generate-speech

Use when the user wants to generate speech/audio from text using OATDA's unified audio API. MCP generatespeech returns a short-lived signed AUDIOURL (download with curl, no login). HTTP /api/v1/llm/speech returns a file via curl --output. Supports OpenAI TTS, xAI grok-tts, voiceovers, and accessibility audio.

devcsde/oatda-skills · 84 tokens

oatda-generate-video

Use when the user wants to generate videos using AI models through OATDA's unified API. Supports MiniMax, Google Veo, Alibaba Wan, ZAI, and OpenAI Sora. Video generation is asynchronous.

devcsde/oatda-skills · 50 tokens

oatda-video-ad-creator

Create a branded video ad for the user's own product using OATDA APIs (TTS voiceover + AI video hook clip), Remotion, and ffmpeg. Triggers on "create video", "make ad", "Werbevideo", "promo video", "video ad".

devcsde/oatda-skills · 64 tokens