edge-browser-mcp AGENTS.md

A set of AGENTS.md instructions for the edge-history-mcp project, which is a Python MCP server that reads Microsoft Edge browsing history on Windows.

In plain words
What is it for?
Use it when changing or testing the server, including its profile listing, per-visit history, and privacy-preserving domain summaries grouped by hour.
Why use it?
It documents the server’s architecture, conventions, project layout, and development workflow so an agent can work on the project consistently.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/adrianba/edge-browser-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/adrianba/edge-browser-mcp

Made for: Codex, OpenCode.

Per session 3,580 This file is loaded in full into every session.
When invoked 3,580 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.03580 $0.03580
Opus 5 $0.01790 $0.01790
Sonnet 5 $0.00716 $0.00716
Haiku 4.5 $0.00358 $0.00358

Measured 2d ago against content hash 23bbfb5c8ce0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

edge-browser-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 2d 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.

AGENTS.md · 255 lines

How it starts

The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for AI agents and human contributors working on edge-history-mcp. Read this before making changes; it captures the architecture, conventions, design decisions, and the build/test workflow.

What this project is

A stdio Model Context Protocol (MCP) server, written in Python, that exposes Microsoft Edge browsing history to MCP clients. It provides three tools:

  • list_profiles() — list Edge browsing profiles (friendly names).
  • get_history(profile, date, start_time=None, end_time=None, limit=10000, offset=0) — a paginated page of per-visit history entries for one profile on one day, with an optional intra-day time window.
  • get_history_summary(profile, date, start_time=None, end_time=None, group_by="hour", limit=10000, offset=0) — a privacy-preserving, domain-only aggregation of the same window, bucketed by local hour (no full URLs, query strings or fragments; http/https only).

It is read-only with respect to Edge's data and targets Windows + Edge.

Tech stack & conventions

  • Language: Python, requires-python = ">=3.12". Uses modern typing (X | None, list[...]) and from __future__ import annotations.
  • Package/run tool: uv (Astral). Always use uvuv run, uv sync, uv add. Do not call pip/python directly or hand-manage a venv.
  • MCP framework: official MCP Python SDK, FastMCP (mcp[cli]). Tools are plain functions decorated with @mcp.tool(); FastMCP derives the JSON schema from type hints and the docstring (Args section matters — it surfaces to clients).
  • Build backend: uv_build. Console script entry point edge-history-mcp = "edge_history_mcp.server:main".
  • Style: Comment only where clarification helps; rely on docstrings for the public API. Module-level docstrings explain the "why". Keep functions small and pure where possible (conversions are pure and unit-tested directly).
  • Errors: Raise EdgeHistoryError for all expected, user-facing failures (unknown profile, bad date, unreadable DB). The server layer converts EdgeHistoryError to ValueError so FastMCP returns a clean tool error instead of leaking internals/tracebacks. Never let raw sqlite3/OSError escape edge.py.

Read the full file on GitHub · 255 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.

  1. 2d ago First seen · 255 lines · 3,580 tokens per session scan A 23bbfb5c8ce0

Subscribe to this mod's changes

edge-browser-mcp AGENTS.md is an instructions file published in the GitHub repository adrianba/edge-browser-mcp (0 stars, last pushed 28d ago), licensed MIT. It adds 3,580 tokens to every session, about $0.0179 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.