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/markswendsen-code/mcp-tacobellWrote 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/markswendsen-code/mcp-tacobell/tacobell)<a href="https://agentmods.dev/mcp/markswendsen-code/mcp-tacobell/tacobell"><img src="https://agentmods.dev/badge/mcp/markswendsen-code/mcp-tacobell/tacobell.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
tacobell 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 6d 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.
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.
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.
- 6d ago First seen · 10 lines scan A 6c1ac83a8bcb
tacobell is an MCP server published in the GitHub repository markswendsen-code/mcp-tacobell (0 stars, last pushed 2mo 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.
Other mcp servers, from other repositories
mcp-starbucks
MCP server for Starbucks — let AI agents search the menu, customize drinks, find stores, and place mobile orders. Runs locally from the @striderlabs/mcp-starbucks npm package.
panera
MCP server for Panera Bread - browse menu, customize orders, place pickup. Runs locally from the @striderlabs/mcp-panera npm package.
chipotle
MCP server for Chipotle - let AI agents order burritos, bowls, and more. Runs locally from the @striderlabs/mcp-chipotle npm package.
buy123-vendor
MCP server "buy123-vendor" as configured in asgard-ai-platform/mcp-buy123-vendor. Runs mcp_server.py with .venv/bin/python.
instacart
MCP server for Instacart - let AI agents manage grocery shopping and place orders autonomously. Runs locally from the @striderlabs/mcp-instacart npm package. Needs 2 environment variables to run.
doordash
MCP server for DoorDash - let AI agents order food delivery autonomously with browser-based ordering. Runs locally from the @striderlabs/mcp-doordash npm package. Needs 3 environment variables to run.