広告掲載
MCP.so
ログイン

PubFi MCP Server

@helixbox

リポジトリホームページ

基本情報

カテゴリ

メモリとナレッジ

ライセンス

NOASSERTION

作者

helixbox

PubFi MCP Server について

Public docs, examples, and agent-readable integration guides for PubFi's agent-native crypto data layer.

PubFi MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "pubfi": {
      "type": "streamable-http",
      "url": "https://mcp.pubfi.ai",
      "headers": {
        "Authorization": "Bearer <PUBFI_API_KEY>"
      }
    }
  }
}

PubFi MCP Server のツール

3

Enumerate the complete installed Registry v2 catalog as deterministic compact pages. The server does not rank, infer intent, or choose a capability.

Return the full typed request, response, metering, and readiness contract for one exact capability id from the installed Registry generation.

Execute one exact GET or POST path through the same Registry v2 matcher, credential authority, and typed executor as the HTTP gateway. Append :free to a published free route and use the authenticated account lane for rate- and total-limited execution without Credit charging. Otherwise use the authenticated account lane with metering, or call the explicit accountless x402 MCP endpoint with payment metadata.

概要

What is PubFi MCP?

PubFi MCP is an agent-native crypto data layer that provides a hosted MCP endpoint for agents and MCP clients. It exposes generic route and capability tooling, along with an open Discovery index that serves as a demand engine and source-selection surface for crypto data APIs.

How to use PubFi MCP?

Set up your MCP client by following the MCP client setup guide. For a quick smoke test, run the dependency-free stdio bridge in examples/agents/pubfi-route-tools-mcp/. Live examples require a PubFi API key loaded from environment variables.

Key features of PubFi MCP

  • Agent-native crypto data layer with hosted MCP endpoint
  • Open Discovery index for crypto data API source selection
  • Generic route and capability tooling for agents and MCP clients
  • Public MCP manifest and server card at well-known endpoints
  • LLM-friendly surfaces including llms.txt and agent-readable docs

Use cases of PubFi MCP

  • AI agents querying real-time crypto data through a unified MCP interface
  • Comparing and selecting crypto data sources via the Discovery index
  • Building agent workflows that combine crypto data routes with capability detection
  • Testing MCP client integration using the provided stdio bridge example

よくある質問

1

What is the PubFi MCP server?

It is a hosted MCP endpoint that implements generic route/capability tooling for accessing crypto data through the PubFi layer. It is described in the MCP manifest at `https://mcp.pubfi.ai/.well-known/mcp.json`.

2

How do I set up the PubFi MCP client?

Follow the [MCP client setup page](getting-started/mcp-client.md) and use the example in `examples/agents/pubfi-route-tools-mcp/` for a dependency-free stdio bridge. Live examples need a PubFi API key.

3

Does PubFi guarantee that every Discovery source is callable?

No. The README lists “every Discovery source is callable through PubFi” as an unsafe claim. Not all sources may be accessible via the hosted service.

4

What transports does PubFi MCP support?

The README shows an MCP manifest (HTTPS-based) and a stdio bridge for local testing. The manifest is served at `https://mcp.pubfi.ai/.well-known/mcp.json`.

5

Are there any authentication requirements?

Live examples require a PubFi API key. The docs instruct not to commit credentials. The MCP server card and manifest provide public discovery without authentication.

コメント

「メモリとナレッジ」の他のコンテンツ

Sooveryn

PANDAPROG

Sooveryn gives Claude Code a team of AI personas that remembers your project. Soov, the partner and team lead, keeps your decisions and how you work in a lasting memory, and finds them again by words and by meaning, from

Groundwork

Rarefied-Earth

Groundwork: company memory for your AI tools. Docs public. Source closed. Public proof needs no account.

1

Tempreon

Tempreon

Person-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions — captured in one assistant, available in all of them.

Orcha

westonhancock

Orcha is a unified context layer for AI tools and agents. It stores and indexes and exposes organizational, team, or individual knowledge. Files, structured databases, and connected sources live in one workspace, and age

Memlord

MyrikLD

Memlord is a remote MCP server available at https://app.memlord.com.

広告掲載