What is mcp-secure-access-community AGENTS.md?

Repository instructions for AI coding assistants working on a Python server that lets compatible clients call Cisco Secure Access through a curated set of API tools.

Use them when developing or reviewing the cisco-secure-access-mcp repository, including its admin, deployment, investigation, policy, and reporting tools.

They give coding assistants the project context, supported transports, authentication approach, and API conventions needed to make suitable changes.

How sdntechforum/mcp-secure-access-community configures Codex and Open

Reuse

Borrowing it

Nothing to install: this file belongs to sdntechforum/mcp-secure-access-community. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/sdntechforum/mcp-secure-access-community/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/sdntechforum/mcp-secure-access-community

Made for: Codex, 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/sdntechforum/mcp-secure-access-community/agents-md/github.svg)](https://agentmods.dev/instructions/sdntechforum/mcp-secure-access-community/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/sdntechforum/mcp-secure-access-community/agents-md"><img src="https://agentmods.dev/badge/instructions/sdntechforum/mcp-secure-access-community/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/sdntechforum/mcp-secure-access-community/agents-md"><img src="https://agentmods.dev/badge/instructions/sdntechforum/mcp-secure-access-community/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,037 This file is loaded in full into every session.

When invoked 3,037 The same file — it is already loaded in full.

Security scan C 2 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.03037	$0.03037
Opus 5.5	$0.01215	$0.01215
Sonnet 5.5	$0.00607	$0.00607
Haiku 4.5	$0.00304	$0.00304

Measured 2mo ago against content hash e53140c77750, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

mcp-secure-access-community AGENTS.md scanned grade C with 2 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 2mo 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -LsSf https://astral.sh/uv/install.sh | sh

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -LsSf https://astral.sh/uv/install.sh | sh

AGENTS.md · 261 lines

How it starts

The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — cisco-secure-access-mcp

AGENTS.md is a simple, open format for guiding AI agents that work with this repository (VS Code, GitHub Copilot, Cursor, Codex, Gemini CLI, etc.).

This repository implements a community Model Context Protocol (MCP) server for Cisco Secure Access. It lets MCP-compatible AI clients call the Secure Access REST API through a curated catalog of tools grouped by Cisco's own resource categories (admin_*, deploy_*, investigate_*, policy_*, report_*).

What this server does

Item	Detail
Project	`cisco-secure-access-mcp`
Language / runtime	Python 3.10+
MCP framework	`mcp` (FastMCP high-level API)
Default transport	stdio (recommended for local IDE clients)
Optional transport	Streamable HTTP (off by default; requires bearer auth + origin checks)
API target	Cisco Secure Access REST API, base `https://api.sse.cisco.com`
Auth	OAuth 2.0 Client Credentials Flow (RFC 6749 §4.4)
Multi-org / MSSP	Supported via `X-Umbrella-OrgId` header (env-driven)

API and SDK references for AI agents

When generating or modifying code in this repo, use these as your sources of truth:

OpenAPI spec — Authorization API: https://pubhub.devnetcloud.com/media/cloud-security-apis-in-eft/docs/secure-access/reference/auth/cisco_secure_access_token_authorization_api_2_0_0.yaml
Cisco Secure Access getting started: https://developer.cisco.com/docs/cloud-security/secure-access-api-getting-started/
Cisco Secure Access authentication: https://developer.cisco.com/docs/cloud-security/secure-access-api-authentication/
Reference Python SDK (not on PyPI; used as a behavioral reference, not a runtime dep): https://github.com/CiscoDevNet/cisco-secure-access-python-sdk
Postman examples: https://github.com/CiscoDevNet/cloud-security/tree/master/Cisco%20Secure%20Access/PostmanExamples
Product help (admin UX context): https://securitydocs.cisco.com/docs/csa/olh/119038.dita

Read the full file on GitHub · 261 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.

2mo ago First seen · 261 lines · 3,037 tokens per session scan C e53140c77750

Subscribe to this mod's changes

mcp-secure-access-community AGENTS.md is an instructions file published in the GitHub repository sdntechforum/mcp-secure-access-community (1 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 3,037 tokens to every session, about $0.0121 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Backend and APIs

mcp-secure-access-community AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-secure-access-community AGENTS.mdsdntechforum/mcp-secure-access-community	Instructions file	1	5mo ago	Apache-2.0	C	3,037	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

mcp-secure-access-community: Instructions file for Codex