Borrowing it
Nothing to install: this file belongs to gabrielmahia/mpesa-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gabrielmahia/mpesa-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/gabrielmahia/mpesa-mcpWrote 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/instructions/gabrielmahia/mpesa-mcp/agents-md)<a href="https://agentmods.dev/instructions/gabrielmahia/mpesa-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/gabrielmahia/mpesa-mcp/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.
<a href="https://agentmods.dev/instructions/gabrielmahia/mpesa-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/gabrielmahia/mpesa-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00674 | $0.00674 |
| Opus 5 | $0.00337 | $0.00337 |
| Sonnet 5 | $0.00135 | $0.00135 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
mpesa-mcp AGENTS.md 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — mpesa-mcp
This file gives AI coding agents (Cursor, GitHub Copilot, Claude Code, Devin, etc.) the context needed to work reliably in this repository.
What this repo is
An MCP server that gives AI agents access to:
- M-Pesa Daraja API — STK Push payments, transaction status queries
- Africa's Talking — SMS to 20+ African telecom networks, airtime top-up
All tools handle real financial operations. Test in sandbox mode only.
Architecture
src/mpesa_mcp/
server.py ← All tool definitions and MCP server entry point
__init__.py ← Package version
tests/
test_smoke.py ← Basic import and tool registration tests
.well-known/
mcp.json ← MCP Server Cards discovery metadata
Single-file architecture — all tools are in server.py. The server uses FastMCP.
Tool annotations (critical)
All 5 tools declare MCP ToolAnnotations. Do not remove or change these without understanding the implications:
readOnlyHint: Trueon query tools — clients auto-approve thesedestructiveHint: Trueon write tools — clients show confirmation dialogs- Removing
destructiveHint: Truefrom payment/SMS tools is a safety issue
Environment variables
# M-Pesa (Daraja)
MPESA_CONSUMER_KEY=
MPESA_CONSUMER_SECRET=
MPESA_SHORTCODE=174379 # sandbox default
MPESA_PASSKEY= # from Daraja portal
MPESA_CALLBACK_URL= # must be public HTTPS
MPESA_ENVIRONMENT=sandbox # or: production
# Africa's Talking
AT_API_KEY=
AT_USERNAME=sandbox # or: your production username
Development
pip install -e ".[dev]"
pytest tests/ -v
Phone number handling
M-Pesa accepts Kenyan numbers in multiple formats. The server normalizes all to 254XXXXXXXXX:
0712345678→254712345678+254712345678→254712345678254712345678→ unchanged
Do not bypass this normalization — Daraja rejects other formats silently.
Testing
Always test against Daraja sandbox (default). Sandbox STK Push sends a simulated prompt to the phone — no real money moves.
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.
- 10d ago First seen · 89 lines · 674 tokens per session scan A 41a11d5b6bd4
mpesa-mcp AGENTS.md is an instructions file published in the GitHub repository gabrielmahia/mpesa-mcp (4 stars, last pushed 10d ago), licensed MIT. It adds 674 tokens to every session, about $0.0034 per session on Opus 5. 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.