Sponge MCP Server
Provides a Model Context Protocol interface to the Sponge wallet API for managing digital assets and transaction histories. It enables users to securely check balances, retrieve addresses, and perform transfers using DAuth-style credential exchange.
README
sponge-mcp
A scaffold for a Sponge MCP server built with dedalus-mcp and DAuth-style credential exchange.
This server follows a DAuth-style credential exchange pattern:
- Credentials are provided by clients at runtime.
- The server declares a
ConnectionwithSecretKeys. - Tool calls dispatch through Dedalus secure connection handles.
Scaffold Scope
- DAuth-compatible API key authentication (
SPONGE_API_KEY). - Configurable Sponge base URL via
SPONGE_BASE_URL. - Read-only wallet inspection tools for the core Sponge wallet API.
- Includes a smoke ping tool for quick MCP handshake validation.
- Keeps the implementation intentionally small so Sponge engineers can extend it.
Setup
- Create a Sponge API key.
- Copy env template:
cp .env.example .env
Required:
SPONGE_API_KEY(provided by the MCP client via DAuth credentials in production flows)
Optional:
SPONGE_BASE_URL(defaults tohttps://api.wallet.paysponge.com)DEDALUS_AS_URL(defaults tohttps://as.dedaluslabs.ai)HOST(defaults to127.0.0.1)PORT(defaults to8080)
Run
uv run python src/main.py
Hosted SDK usage
For the current published Dedalus Python SDK, hosted MCP credentials are matched
using a slug-derived connection name. For this deploy, use tsion-sponge-mcp
when constructing runtime SecretValues:
import os
from dedalus_labs import AsyncDedalus, DedalusRunner
from dedalus_mcp.auth import Connection, SecretKeys, SecretValues
sponge = Connection(
name="name-of-server", #if name of server is tsion/sponge-mcp use tsion-sponge-mcp
secrets=SecretKeys(api_key="SPONGE_API_KEY"),
base_url="https://api.wallet.paysponge.com",
auth_header_format="Bearer {api_key}",
)
sponge_secrets = SecretValues(sponge, api_key=os.getenv("SPONGE_API_KEY", ""))
client = AsyncDedalus(
api_key=os.getenv("DEDALUS_API_KEY"),
as_base_url="https://as.dedaluslabs.ai",
)
runner = DedalusRunner(client)
result = await runner.run(
input="Use Sponge to get my wallet balances.",
model="openai/gpt-4.1-mini",
mcp_servers=["tsion/sponge-mcp"],
credentials=[sponge_secrets],
)
Tool Surface
sponge_get_addressessponge_get_balancessponge_get_balancesponge_get_transaction_historysponge_get_transaction_statussmoke_ping
Notes
- Sponge wallet endpoints are served from
https://api.wallet.paysponge.com. - This scaffold is intentionally wallet-only for now; future admin tools can be layered on once Sponge exposes a stable public REST surface for them.
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。