What is free_web_mcp AGENTS.md?

A set of AGENTS.md instructions for working on the free_web_mcp project, a pnpm monorepo that gives AI agents web access and verifies web-page claims with stored evidence.

It helps agents navigate the dashboard, evidence engine, blockchain code, MCP server, tests, and development scripts while following the repository’s layering rules.

It gives coding agents the project’s current status, technology choices, folder layout, and required boundaries so they can make changes that fit the existing codebase.

How chenxuyaun/free_web_mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to chenxuyaun/free_web_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.

Copy the file

curl -O https://raw.githubusercontent.com/chenxuyaun/free_web_mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/chenxuyaun/free_web_mcp

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/chenxuyaun/free_web_mcp/agents-md/github.svg)](https://agentmods.dev/instructions/chenxuyaun/free_web_mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/chenxuyaun/free_web_mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/chenxuyaun/free_web_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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/chenxuyaun/free_web_mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/chenxuyaun/free_web_mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,107 This file is loaded in full into every session.

When invoked 1,107 The same file — it is already loaded in full.

Security scan A 0 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	$0.01107	$0.01107
Opus 5.5	$0.00443	$0.00443
Sonnet 5.5	$0.00221	$0.00221
Haiku 4.5	$0.00111	$0.00111

Measured 1mo ago against content hash 6f7d74cb5854, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

free_web_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 1mo 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 · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

项目状态

Free Web MCP — Verifiable Web Evidence Network：给 AI Agent 免费网页访问，对网页来源的断言做证据化验证，并把证据指纹 SHA-256 锚定到 BNB Smart Chain Testnet。双栈 pnpm monorepo。

当前进度（v0.5.14，V1-V16 已完成）：六核心对象 + Claim 状态机 + 乐观验证（staking/slashing）+ Brier/Log 双评分声誉 + 独立性加权共识（model/searchProvider/sources/policy 四维相关性）+ oracle ladder 动态升级（knife-edge → DISPUTED 可继续 attest，决定性后 RESOLVED）+ 挑战 bond 经济结算 + 链上 resolution 验证 + 14 个 MCP 工具（agent 全程参与验证 + 取引用信封）+ citation envelope UI + e2e 协议流程测试。全部线上部署验证（yuncai.site）。

技术栈

层	技术
前端/Dashboard	Next.js 14 / React 18 / Tailwind / better-sqlite3 / lucide
证据引擎	TypeScript（`packages/evidence`）+ Vitest
链上	Solidity 0.8.24 / Foundry / viem（`packages/blockchain` + `contracts/`）
MCP Server	Python 3.12 / FastMCP / DuckDuckGo（`apps/mcp-server`，uv 管理）
包管理	pnpm workspace + uv（Python 侧独立）

apps/
  web/            Next.js dashboard + API 路由（evidence/claims/verify/demo/anchor/health）
  mcp-server/     Python MCP server（13 工具，56 测试）
packages/
  evidence/       protocol.ts（六核心对象+独立性+评分规则）/ resolution.ts（乐观解析引擎）/ claims/engine/hash/package（TS，56 vitest）
  blockchain/     viem client for EvidenceRegistry（chains/registry）
contracts/        EvidenceRegistry.sol + forge test
scripts/          seed-demo.ts、demo.ts（pnpm demo）
docs/             ｜examples/ ｜e2e/（Playwright）｜.github/workflows/ci.yml

分层规则（必须遵守）

MCP 工具层（apps/mcp-server/src/free_web_mcp/mcp/tools.py）绝不直接碰存储或链——extract_claims/find_counter_evidence 是本地纯函数，create_evidence_record/get_evidence 走 dashboard API（MCP_SERVER_URL 环境变量）。
Dashboard API 层拥有 SQLite（apps/web/lib/db.ts）和链上签名器（apps/web/lib/blockchain.ts）。
链上写操作必须：服务端 signer（WALLET_PRIVATE_KEY 只从 env 读）+ 请求显式 {confirm:true} + 限流。
SSRF 防护在 apps/mcp-server/src/free_web_mcp/web/client.py：拒绝 localhost/私网/链路本地地址。
私钥永不入代码/日志/前端/MCP 输出。

关键命令

pnpm install                        # Node 依赖
cd apps/mcp-server && uv sync       # Python 依赖

# 三个终端跑起来
cd apps/mcp-server && uv run --no-sync free-web-mcp --transport http --host 127.0.0.1 --port 8765
pnpm dev                            # dashboard :3000
anvil --port 8545                   # 本地链（锚定用）

pnpm demo                           # CLI 演示（需 8765 + dashboard 在跑）
cd contracts && forge test          # 合约测试
pnpm -r test && pnpm -r typecheck   # Node 测试/类型
cd apps/mcp-server && uv run pytest -q   # Python 测试

Read the full file on GitHub · 68 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.

1mo ago Changed · +119 tokens per session 6f7d74cb5854
2mo ago First seen · 68 lines · 988 tokens per session scan A 546eb004358e

Subscribe to this mod's changes

free_web_mcp AGENTS.md is an instructions file published in the GitHub repository chenxuyaun/free_web_mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,107 tokens to every session, about $0.0044 per session on Opus 5.5. 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.

free_web_mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
free_web_mcp AGENTS.mdchenxuyaun/free_web_mcp	Instructions file	0	1mo ago	MIT	A	1,107	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

free_web_mcp: Instructions file for Codex