agentmods.dev

bay-run

bay-run is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from barneywohl/bay-run. Its token cost is not measured, scanned A, original, no licence file.

A remote server offering OpenAI-compatible AI inference through three MCP tools. Inference means running a model to produce an answer, and signed provenance receipts record where results came from.

In plain words
What is it for?
Use it when an assistant needs to call the service's three inference tools and receive provenance receipts.
Why use it?
It provides access to the stated AI inference service along with signed records of result provenance.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it.

not rated 0repo 9d ago A scan tokens not measured no licence

Good fit Use it when an assistant needs to call the service's three inference tools and receive provenance receipts.

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/barneywohl/bay-run/bay-run
View source ↗ barneywohl/bay-run run.huggingbay.xyz
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.

Clone the repo
git clone --depth 1 https://github.com/barneywohl/bay-run

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

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 bay-run

README.md
[![agentmods](https://agentmods.dev/badge/mcp/barneywohl/bay-run/bay-run.svg)](https://agentmods.dev/mcp/barneywohl/bay-run/bay-run)
Your own site
<a href="https://agentmods.dev/mcp/barneywohl/bay-run/bay-run"><img src="https://agentmods.dev/badge/mcp/barneywohl/bay-run/bay-run.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown No closer match found in the catalogue.
Security

Grade A, and why

bay-run 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 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.

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.

server.json · 6 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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 · 6 lines scan A 839fffdd7d5b

Subscribe to this mod's changes

bay-run is an MCP server published in the GitHub repository barneywohl/bay-run (0 stars, last pushed 9d ago), with no licence file. 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.

Data and AIagentsinferencellm-routermcpsmall-models
Related

Other mcp servers, from other repositories

huggingface

MCP server "huggingface", hosted remotely at hf.co, as configured in bearlike/Grove.

bearlike/Grove · not measured

gonka-mcp-server

A second opinion for AI agents: one prompt across several live Gonka models + roles, one call. Remote server at mcp.gogonka.com.

bystray/gonka-mcp-server · not measured

data-workers

Data Workers CLI — autonomous AI agent swarm for data engineering. Runs locally from the dw-claw npm package.

DataWorkersProject/dataworkers-claw-community · not measured

thinking-prompts

MCP server "thinking-prompts" as configured in zdrjson/thinking-prompts-skill. Runs locally from the thinking-prompts npm package.

zdrjson/thinking-prompts-skill · not measured

chroma_db_rag

MCP server "chromadbrag" as configured in laxmimerit/MCP-Mastery-with-Claude-and-Langchain. Launched with uv --directory D:\Courses\Udemy\MCP Mastery - Claude and LangChain\08 MCP RAG wi.

laxmimerit/MCP-Mastery-with-Claude-and-Langchain · not measured

research-assistant

A Model Context Protocol server for research assistance with ChromaDB vector storage. Runs locally from the research-assistant-mcp Python package. Needs 2 environment variables to run.

laxmimerit/MCP-Mastery-with-Claude-and-Langchain · not measured