openai-cookbook is a collection of example code and practical guides for completing common tasks with the OpenAI API. It is for developers building applications that call OpenAI models, with most examples written in Python. The catalogue add-ons provide reusable workflows for working with the cookbook and OpenAI API examples.
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.
git clone --depth 1 https://github.com/openai/openai-cookbookWrote 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/openai/openai-cookbook/bls-bls-mcp)<a href="https://agentmods.dev/mcp/openai/openai-cookbook/bls-bls-mcp"><img src="https://agentmods.dev/badge/mcp/openai/openai-cookbook/bls-bls-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.
<a href="https://agentmods.dev/mcp/openai/openai-cookbook/bls-bls-mcp"><img src="https://agentmods.dev/badge/mcp/openai/openai-cookbook/bls-bls-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
bls-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 yesterday.
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
{
"bls-mcp": {
"type": "http",
"url": "http://127.0.0.1:8000/mcp",
"default_tools_approval_mode": "approve"
}
}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.
- yesterday First seen · 7 lines scan A 9e77c0df042c
bls-mcp is an MCP server published in the GitHub repository openai/openai-cookbook (76,544 stars, last pushed yesterday), 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 2026-10-10.
Other mcp servers, from other repositories
dext
MCP server "dext" as configured in bidule995/dext-codex-connector. Runs ./plugin/runtime/dext-fixture-stdio.mjs with node.
tgfmcp
TypeScript stdio MCP server and CLI for Telegram bots. Runs locally from the tgfmcp npm package.
cursor-chatgpt-web
MCP server "cursor-chatgpt-web" as configured in Rakeem-C/cursor-chatgpt-web. Runs locally from the cursor-chatgpt-web npm package.
openai-ads-mcp
Typed MCP server for OpenAI Ads and ChatGPT Ads via the Advertiser API. Runs locally from the openai-ads-mcp Python package.
mcp-llm-gateway
MCP-compatible LLM gateway that proxies completion requests to downstream OpenAI-compatible providers. Runs locally from the mcp-llm-gateway Python package.
neon
Neon's hosted MCP server: lets the agent create and manage Neon Postgres projects, branches and databases and run SQL. Remote server at mcp.neon.tech.