ToolSnap MCP
Context-efficient MCP server for AI agents. fetch_extract reduces token usage by a median 98.1% (53,820 → 2,001 tokens) vs raw HTML — saves ~$0.156/call at Sonnet pricing. Pay $0.02 USDC on Base via x402. First call free per wallet. 10 always-free utility tools included.
README
ToolSnap MCP
Context-efficient microtools for AI agents. Pay per call with USDC on Base.
Live endpoint: https://mcp.toolsnap.app/mcp
Server card: /.well-known/mcp.json
Pricing: /.well-known/pricing.json
Docs: toolsnap.app/agents
Why
The biggest cost for AI agents isn't generation — it's context. When an agent loads a raw webpage to extract information it can burn 50,000+ tokens on HTML boilerplate. ToolSnap MCP moves that work server-side.
Benchmark (11 real pages, June 2026):
| Raw HTML | Extracted | Saving | |
|---|---|---|---|
| Median tokens | 53,820 | 2,001 | 98.1% |
| Cost @ Sonnet ($3/M) | $0.162 | $0.006 | $0.156/call |
| Break-even page size | — | — | 26 KB |
The tool costs $0.02 USDC → 7.8× ROI on a typical page.
Connect
Claude Desktop
{
"mcpServers": {
"toolsnap": {
"url": "https://mcp.toolsnap.app/mcp",
"transport": "streamable-http"
}
}
}
Direct MCP call
curl -X POST https://mcp.toolsnap.app/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
Tools
Paid (x402)
| Tool | Description | Price |
|---|---|---|
fetch_extract |
Fetch a URL → clean text. 98.1% median token reduction. | $0.02 USDC |
First call free per wallet address. After that, your agent pays $0.02 USDC on Base using x402 v2 (EIP-3009 transferWithAuthorization). No API key, no subscription — pay only when you call.
Free (always)
| Tool | Description |
|---|---|
pricing |
Machine-readable pricing menu + ROI. Call this first. |
uuid_generate |
1–100 random UUID v4 values |
hash_text |
SHA-256 / SHA-1 / SHA-512 (hex) |
base64_encode |
UTF-8 → Base64 |
base64_decode |
Base64 → UTF-8 |
url_encode |
Percent-encode (encodeURIComponent) |
url_decode |
Decode percent-encoded string |
json_format |
Parse + pretty-print or minify JSON |
timestamp_convert |
Unix ↔ ISO 8601 (auto-detects direction) |
text_stats |
Chars, words, lines, sentences |
Payment (x402)
When an agent calls fetch_extract without payment, the server returns:
{
"jsonrpc": "2.0",
"id": 1,
"error": {
"code": 402,
"message": "Payment required",
"data": {
"x402Version": 2,
"accepts": [{
"scheme": "exact",
"network": "eip155:8453",
"amount": "20000",
"asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913"
}]
}
}
}
An x402-enabled client reads accepts[0], signs an EIP-3009 TransferWithAuthorization, and retries with _meta["x402/payment"] set. See x402 spec.
Run locally
npm install
cp .dev.vars.example .dev.vars # fill in wallet secrets
npm run dev
# Worker at http://localhost:8787
Type-check
npm run typecheck
Deploy
npm run deploy
Stack
- Runtime: Cloudflare Workers (edge, 0 ms cold start)
- Protocol: MCP streamable-http (JSON-RPC 2.0)
- Payment: x402 v2 · EIP-3009 on Base mainnet · USDC
- Verification: off-chain EIP-712 signature recovery (viem)
- Settlement: on-chain
transferWithAuthorizationvia relayer wallet - Anti-replay: Cloudflare KV nonce store (7-day TTL)
- First-call-free: KV key
first_free:{address}, verified but not settled
Contributing
PRs welcome for new free tools in src/tools/. Follow the pattern in src/tools/text-stats.ts and add the tool to src/tools/index.ts.
For paid tools or changes to the x402 payment logic, open an issue first.
Do not commit wallet private keys, .dev.vars, or any secrets.
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。