developer-toolsanalytics-data

Agent Data Bridge

by AriaScarlet132

Agent Data Bridge: secure data integration server bridging Spring Boot interfaces with a lightweight Python sandbox—expo

An MCP server that provides data bridging from Spring Boot interfaces and a lightweight Python sandbox for script execution. It enables agents to fetch data as Markdown or Parquet files and perform automated data analysis within a controlled environment.

github stars

0

Sandboxed Python executionMultiple data export formats

best for

  • / Java developers integrating Spring Boot data with AI agents
  • / Data analysts needing automated processing pipelines
  • / Teams bridging JVM applications with Python analytics

capabilities

  • / Fetch data from Spring Boot interfaces
  • / Export data as Markdown or Parquet files
  • / Execute Python scripts in sandboxed environment
  • / Perform automated data analysis
  • / Bridge data between different systems
  • / Process data in controlled runtime

what it does

Connects agents to Spring Boot data sources and provides a Python sandbox for data analysis. Fetches data in Markdown or Parquet formats for automated processing.

about

Agent Data Bridge is a community-built MCP server published by AriaScarlet132 that provides AI assistants with tools and capabilities via the Model Context Protocol. Agent Data Bridge: secure data integration server bridging Spring Boot interfaces with a lightweight Python sandbox—expo It is categorized under developer tools, analytics data.

how to install

You can install Agent Data Bridge in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.

license

MIT

Agent Data Bridge is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.

readme

Agent Data Bridge

一个面向 Agent 的“数据桥接 + 轻量沙盒执行”服务,提供两种对外形态:

  • FastAPI HTTP API:用于手工/系统直接调用。
  • MCP Server(SSE Transport):把能力以 Tool 的形式暴露给支持 MCP 的客户端。

目前实际实现包含:

  • 通过两步 OAuth2(token -> query)调用 Spring Boot 接口获取数据(见 src/app/services/springboot_client.py)。
  • 将返回结果中的首个 Markdown 表格解析为 DataFrame;小数据直接返回表格,大数据保存为 parquet 到沙盒目录并返回摘要(见 src/app/main.py)。
  • 提供一个简易 Python “沙盒执行”入口:在指定的沙盒目录中运行脚本,支持超时与输出长度截断(见 src/app/services/sandbox.py)。

运行要求

快速开始

  1. 安装依赖
  • uv sync
  1. 启动 HTTP API(FastAPI)
  • uv run -- uvicorn app.main:app --reload --app-dir src

默认监听 http://127.0.0.1:8000

如果希望“一条命令同时启动 REST + MCP”,可使用:

  • uv run -- python -m app.run_all

1.(可选)启动 MCP Server(SSE)

本项目的 MCP Server 默认监听 0.0.0.0:9000(可通过 MCP_HOST/MCP_PORT 修改),并使用 SSE 传输:

  • SSE 端点:GET /sse
  • 消息端点:POST /messages/

启动命令:

  • Windows(PowerShell,推荐):
$env:PYTHONPATH = "src"
uv run -- python -m app.mcp_server
  • 或者切换到 src 目录运行(一次性):
pushd src
uv run -- python -m app.mcp_server
popd
  • macOS/Linux:
PYTHONPATH=src uv run -- python -m app.mcp_server

配置(.env)

复制 .env.example.env 后按需修改。

当前代码实际会用到的配置(与 .env.example 保持一致):

  • REST_HOST / REST_PORT:REST(FastAPI) 监听地址(用于 Docker 启动与一键启动脚本)。
  • MCP_HOST / MCP_PORT:MCP(SSE) 监听地址。
  • APP_ID / APP_SECRET:Spring Boot OAuth2 client credentials(默认 agent/agent)。

说明:

  • SPRING_BOOT_BASE_URL / SPRING_BOOT_API_PATH 目前在代码中未被使用;/api/fetch 与 MCP 的 fetch_data 都会直接使用传入的 host 参数作为目标地址(见 src/app/services/springboot_client.py)。

HTTP API

健康检查

  • GET /health

返回:{"status":"ok"}

拉取数据并返回摘要

  • POST /api/fetch

请求体:

{
  "host": "http://192.168.10.21:3000",
  "userid": "Admin",
  "sql": "select ...",
  "dataset": "demo"
}

行为(与实现一致,见 src/app/main.py):

  • 解析返回结果中的 data.markdown(Markdown 表格)。
  • Rows <= 15:直接返回完整 Markdown 表格。
  • Rows > 15:保存为 parquet 到 SANDBOX_DIR,并返回字段预览 + 前 5 行。

响应:

{ "message": "..." }

示例(curl):

curl -X POST http://127.0.0.1:8000/api/fetch \
  -H "Content-Type: application/json" \
  -d '{"host":"http://192.168.10.21:3000","userid":"Admin","sql":"select 1","dataset":"demo"}'

运行沙盒脚本

  • POST /api/sandbox/run

方式 A:JSON

{ "filename": "anything.py", "code": "print(123)" }

方式 B:multipart/form-data

  • 上传字段名 file(.py 文件)
  • 或者传 code / filename

返回(与实现一致,见 src/app/services/sandbox.py):

{
  "filename": "script_xxx.py",
  "exit_code": 0,
  "stdout": "...",
  "stderr": "..."
}

MCP Tools

MCP Server 目前提供以下 tools(见 src/app/mcp_server.py):

  • fetch_data(host, userid, sql, dataset) -> str
  • sandbox_run(code, filename=None) -> dict
  • sandbox_list_files() -> str

常见用法:先 fetch_data 生成 parquet 文件名,再用 sandbox_run 执行 Python 读取:

import pandas as pd
df = pd.read_parquet("<file_name>")
print(df.head())

目录说明

  • sandbox_storage/:默认沙盒数据目录(可通过 SANDBOX_DIR 覆盖)。
  • sandbox_storage/_scripts/:沙盒执行时写入的临时脚本目录(自动创建)。

安全与限制

  • 沙盒执行不是强隔离:只是把工作目录固定到 SANDBOX_DIR,并加了超时与输出截断;请勿在不可信输入场景直接暴露到公网。
  • Spring Boot 的 client_id/client_secret 已改为从 .env 读取(APP_ID/APP_SECRET,默认 agent/agent)。

Docker

同时启动 REST + MCP(推荐使用 compose,并把沙盒目录挂载到宿主机):

docker compose up --build

端口:

  • REST: http://127.0.0.1:${REST_PORT:-8000}
  • MCP(SSE): http://127.0.0.1:${MCP_PORT:-9000}/sse

数据卷:

  • ./sandbox_storage -> /app/sandbox_storage

常见问题

Windows 下 ModuleNotFoundError: No module named 'app'

使用 PowerShell 运行 MCP Server 时,请先设置:

$env:PYTHONPATH = "src"
uv run -- python -m app.mcp_server

FAQ

What is the Agent Data Bridge MCP server?
Agent Data Bridge is a Model Context Protocol (MCP) server profile on explainx.ai. MCP lets AI hosts (e.g. Claude Desktop, Cursor) call tools and resources through a standard interface; this page summarizes categories, install hints, and community ratings.
How do MCP servers relate to agent skills?
Skills are reusable instruction packages (often SKILL.md); MCP servers expose live capabilities. Teams frequently combine both—skills for workflows, MCP for APIs and data. See explainx.ai/skills and explainx.ai/mcp-servers for parallel directories.
How are reviews shown for Agent Data Bridge?
This profile displays 10 aggregated ratings (sample rows for discoverability plus signed-in user reviews). Average score is about 4.5 out of 5—verify behavior in your own environment before production use.
MCP server reviews

Ratings

4.510 reviews
  • Shikha Mishra· Oct 10, 2024

    Agent Data Bridge is among the better-indexed MCP projects we tried; the explainx.ai summary tracks the official description.

  • Piyush G· Sep 9, 2024

    We evaluated Agent Data Bridge against two servers with overlapping tools; this profile had the clearer scope statement.

  • Chaitanya Patil· Aug 8, 2024

    Useful MCP listing: Agent Data Bridge is the kind of server we cite when onboarding engineers to host + tool permissions.

  • Sakshi Patil· Jul 7, 2024

    Agent Data Bridge reduced integration guesswork — categories and install configs on the listing matched the upstream repo.

  • Ganesh Mohane· Jun 6, 2024

    I recommend Agent Data Bridge for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.

  • Oshnikdeep· May 5, 2024

    Strong directory entry: Agent Data Bridge surfaces stars and publisher context so we could sanity-check maintenance before adopting.

  • Dhruvi Jain· Apr 4, 2024

    Agent Data Bridge has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.

  • Rahul Santra· Mar 3, 2024

    According to our notes, Agent Data Bridge benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.

  • Pratham Ware· Feb 2, 2024

    We wired Agent Data Bridge into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.

  • Yash Thakker· Jan 1, 2024

    Agent Data Bridge is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.