signalis-mcp
MCP server for Signalis, providing AI agents with pay-per-call global intelligence including Master Intelligence digests and Pulse narratives, with payments settled in USDC on Base via x402.
README
signalis-mcp
MCP server for Signalis — pay-per-call global intelligence for AI agents. Read the current Master Intelligence digest (narratives, signals, markdown analysis), poll for new digests, and drill into the AI-business Pulse layer: active narratives with lifecycle stage and momentum, per-narrative detail with source attribution, historical narrative digests, and raw scraped content. Pay per call with USDC on Base via x402 — no signup, no accounts, no API keys.
- 5 free tools — no wallet, no API key (incl. digest feedback).
- 5 paid tools — flat per-call USD prices, settled in USDC on Base Mainnet via x402.
Try before you pay: the free get_sample tool returns a recent digest so you can learn the
exact response shape first.
Quick start
Free tier (no wallet)
{
"mcpServers": {
"signalis": {
"command": "npx",
"args": ["-y", "signalis-mcp"]
}
}
}
You get get_brief, get_index, get_sample, get_latest, submit_feedback.
Paid tier (with wallet)
Add an EVM wallet private key (0x-prefixed) that holds USDC on Base Mainnet:
{
"mcpServers": {
"signalis": {
"command": "npx",
"args": ["-y", "signalis-mcp"],
"env": { "PRIVATE_KEY": "0x..." }
}
}
}
The paid tools then settle each call automatically.
Install snippets
Claude Code:
claude mcp add signalis -- npx -y signalis-mcp
# with a wallet:
claude mcp add signalis --env PRIVATE_KEY=0x... -- npx -y signalis-mcp
Claude Desktop / Cursor: add the JSON block above to your MCP config
(claude_desktop_config.json or .cursor/mcp.json).
Tools
Free tools
| Tool | Endpoint | Description |
|---|---|---|
get_brief |
GET /v1/intelligence/brief |
Current Master Intelligence brief — title, executive summary, sentiment. |
get_index |
GET /v1/intelligence/index |
Poll target — current digest id, updatedAt, nextExpected. |
get_sample |
GET /v1/intelligence/sample |
Recent digest sample showing the response structure. |
get_latest |
GET /v1/intelligence/latest |
Full Master Intelligence Digest — narratives, signals, markdown analysis. |
submit_feedback |
POST /v1/intelligence/feedback |
Submit quality feedback on a master digest. |
Paid tools
| Tool | Endpoint | Price (USD) | Description |
|---|---|---|---|
get_intelligence_history |
GET /v1/intelligence/history |
$0.03 | Historical Master Intelligence digests (1–168h lookback). Optional hours, limit. |
get_pulse_narratives |
GET /v1/pulse/narratives |
$0.01 | Active AI-business narratives with lifecycle stage and momentum. |
get_pulse_narrative |
GET /v1/pulse/narratives/{id} |
$0.01 | Narrative detail — content items and source attribution. Requires id. |
get_pulse_digests |
GET /v1/pulse/digests |
$0.03 | Historical AI-business narrative digests. Optional since. |
get_pulse_content_recent |
GET /v1/pulse/content/recent |
$0.02 | Raw scraped content items from the last 4 hours. |
Prices are flat per call — no bundles, no entitlements.
How payments work (x402)
Signalis speaks the x402 exact scheme. The API's 402 advertises a
Base (USDC, EIP-3009) rail; this MCP settles on Base:
- The MCP requests a paid endpoint. With no payment, the API replies HTTP 402 with the accepted terms.
- If
PRIVATE_KEYis set, the MCP settles the call via the standard@x402/fetchV2 client and retries. If no key is set, the MCP returns the 402 price terms so you can see the cost without paying. - The API returns the data plus a
paymentblock.
Compute-first, settle-after: Signalis computes the full answer before charging, so you are never billed for an error.
No accounts, no API keys — just a wallet with USDC on Base Mainnet.
Environment variables
| Variable | Required | Description |
|---|---|---|
PRIVATE_KEY |
No | 0x-prefixed wallet key with USDC on Base Mainnet. Required to pay the 5 paid tools on a live API. Free tools work without it; without a key the paid tools surface the 402 price terms. |
SIGNALIS_API_URL |
No | Override the API base URL (default https://api.signalis.dev). |
Disclaimer
Signalis provides informational intelligence aggregated from public sources. It is not professional or financial advice and is provided as-is without warranty. See https://api.signalis.dev/terms.txt.
Docs for agents: https://api.signalis.dev/llms.txt · full: https://api.signalis.dev/llms-full.txt
License
MIT © jcislo
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。