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.
npx agentmods add mcp/nexenio/bifrost-plugin/bifrostgit clone --depth 1 https://github.com/neXenio/bifrost-pluginWrote 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.
[](https://agentmods.dev/mcp/nexenio/bifrost-plugin/bifrost)<a href="https://agentmods.dev/mcp/nexenio/bifrost-plugin/bifrost"><img src="https://agentmods.dev/badge/mcp/nexenio/bifrost-plugin/bifrost.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
bifrost 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 3d 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.
What it actually says
{
"bifrost": {
"type": "http",
"url": "${user_config.gateway_url}",
"headers": {
"x-bf-vk": "${user_config.virtual_key}"
},
"oauth": {
"authServerMetadataUrl": "https://idms.nexenio.com/realms/nexenio/.well-known/openid-configuration",
"clientId": "${user_config.oauth_client_id}",
"callbackPort": 51789
}
}
}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.
- 3d ago First seen · 14 lines scan A 0c584b6d227a
bifrost is an MCP server published in the GitHub repository neXenio/bifrost-plugin (2 stars, last pushed 15d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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.
Other mcp servers, from other repositories
gomodel
MCP server "gomodel" as configured in ENTERPILOT/GoModel. Runs in Docker (docker.io/enterpilot/gomodel:0.1.83). Needs 2 environment variables to run.
tool_search
GitHub Copilot, OpenAI Codex, OpenCode Go, and third-party AI provider gateway with OpenAI and Anthropic API compatibility. Runs locally from the @jeffreycao/copilot-api npm package.
unified-ai-system
MCP server "unified-ai-system" as configured in happy520ai/unified-ai-system. Runs in Docker (ghcr.io/happy520ai/unified-ai-system/mcp-server@sha256:751a0d32acd2d6b1da6ad9ac67987fbd1ff36ce26b7160014d8605f18b7907b3).
inferrail
A self-hosted gateway that sits between your app and OpenAI, turning every request into an attributable cost receipt — without persisting prompts or responses in its own local records. Runs locally from the inferrail Python package.
enterprise-gateway
MCP server "enterprise-gateway", hosted remotely at localhost, as configured in datacline/secure-mcp-gateway.
council
Multi-model consensus: 2-6 frontier LLMs answer, an independent judge synthesises one answer. Runs locally from the tokonomix-council-mcp npm package. Needs 1 environment variable to run.