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.
npx agentmods add instructions/adrianba/edge-browser-mcp/agents-mdgit clone --depth 1 https://github.com/adrianba/edge-browser-mcpWhat 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 | $0.03580 | $0.03580 |
| Opus 5 | $0.01790 | $0.01790 |
| Sonnet 5 | $0.00716 | $0.00716 |
| Haiku 4.5 | $0.00358 | $0.00358 |
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.
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/httpsonly).
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[...]) andfrom __future__ import annotations. - Package/run tool: uv (Astral). Always use
uv—uv run,uv sync,uv add. Do not callpip/pythondirectly 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 pointedge-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
EdgeHistoryErrorfor all expected, user-facing failures (unknown profile, bad date, unreadable DB). The server layer convertsEdgeHistoryErrortoValueErrorso FastMCP returns a clean tool error instead of leaking internals/tracebacks. Never let rawsqlite3/OSErrorescapeedge.py.
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.
- 2d ago First seen · 255 lines · 3,580 tokens per session scan A 23bbfb5c8ce0
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.
Other instructions, from other repositories
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
agentic-playwright selectors.instructions.md
Instructions for idavidov13/agentic-playwright, covering selector strategy, critical, instructions, phase 1: open and authenticate and phase 2: explore like a user.
scrapai-cli CLAUDE.md
Instructions for discourselab/scrapai-cli, covering claude.md, 1. who you are, 2. hard rules, 3. tools and 4. before you start: confirm the project.
chromeboost CLAUDE.md
Instructions for lordamdal/chromeboost, covering chromeboost — repo-developer guide, what chromeboost is, repository layout, development commands and tests/antibot/ (run locally; not in ci).
skills CLAUDE.md
Instructions for aemcoder/skills, covering claude.md, repository structure, slicc browser automation conventions, stateless tab targeting (since slicc pr #188) and tab-new returns a targetid.
xgrower-extension CLAUDE.md
Instructions for JoyyyceD/xgrower-extension, covering x grower extension — architecture notes, architecture, key files, auth flow and quota system.