DelphiAnthropic

MCP搜索检索

提供方 MaxiDonkey · 包名 delphianthropic

搜索检索 stdio · 本地进程 未标注 社区 / 第三方 Claude DesktopCursorClineClaude Code
查看接入方式

The Anthropic API wrapper for Delphi leverages cutting-edge models, including Anthropic's advanced Claude series, to deliver powerful features for chat interactions, vision processing, caching, effici

一句话选型结论

按资料字段整理

DelphiAnthropic 属于搜索检索类 MCP 服务器,stdio · 本地进程,鉴权方式未标注,可直接接入 Claude Desktop、Cursor、Cline 等,有可直接执行的安装命令。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类搜索检索 传输方式stdio · 本地进程 鉴权未标注 部署方式本地部署
GitHub 星标 48 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

搜索检索
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

anthropic anthropic-ai anthropic-api anthropic-claude caching

支持客户端

适用场景

anthropicanthropic-aianthropic-api

安装与配置

stdio · 本地进程 未标注
客户端在本机拉起子进程,数据不出本机
git clone https://github.com/MaxiDonkey/DelphiAnthropic && cd delphianthropic

这条命令只是入口,具体启动参数请按官方文档补齐,不要直接照搬到别的服务器。

  1. 1
    准备运行环境

    stdio 服务在本地起进程,需要先装好 Cross-platform,再按安装命令拉取依赖。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
联网搜索取证

让模型查最新资料并给出出处。

资料聚合

把一个主题的网页、文档集中抓回来整理。

情报与竞品检索

按关键词持续检索行业动态和竞品信息。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 已适配 Claude Desktop、Cursor、Cline,换客户端不用重新研究配置。

先想清楚的地方

  • stdio 方式要求本地装好运行时(如 Node.js),换机器要重新装一遍。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在搜索检索场景里让模型直接调用外部能力的人。
  • 已经在用 Claude Desktop、Cursor 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 完全不想在本地装环境的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
DelphiAnthropic当前 未标注 stdio · 本地进程 本地部署 有 2026-04-20
Brave Search 433812ff 2 未标注 未标注 无 2026-05-17
Sequentialthinking 1 SSE · 服务端推送 远程部署 有 2026-05-18
Baidu Netdisk 未标注 未标注 未标注 无 2026-05-17
ragflow 未标注 stdio · 本地进程 本地部署 有 2026-04-11
mindsdb (430e18) 未标注 未标注 未标注 有 2026-05-17

服务器档案

搜索检索
字段来自项目仓库与公开索引,中文说明由本站标注
提供方MaxiDonkey上游标注的维护方 MaxiDonkey
分类搜索检索本站按上游分类展示
连接方式stdio · 本地进程客户端在本机拉起子进程,数据不出本机
鉴权方式未标注远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时delphianthropic · Cross-platform本地安装时用到的包标识与运行时
部署类型本地部署上游给出的部署形态
最近核验2026-04-20上游最后核验时间

详细介绍

11.0 KB
来自项目仓库与上游目录的原文,未做删改

DelphiAnthropic – Claude API Wrapper for Delphi


New

  • changelog v1.3.2
  • Managed Agents walkthrough (part 1)
  • Functional demo using Pythia-WebView2
  • Managed Agents API
  • Webhooks — signature verification (HMAC, constant-time) and strongly typed event dispatch

Two simple illustrative examples of synchronous text generation

>[!TIP]
>To obtain an Anthropic API key, refer to https://platform.claude.com/account/keys

  • Non-streamed example:```pascal
    // uses Anthropic, Anthropic.Types, Anthropic.Helpers;
    // Client: IAnthropic;

var Client := TAnthropicFactory.CreateInstance('ANTHROPIC_API_KEY');

//JSON payload
var Payload: TChatParamProc :=
procedure (Params: TChatParams)
begin
Params
.Model('claude-opus-4-7')
.Messages( Generation.MessageParts
.User('From which version of Delphi were multi-line strings introduced?')
)
.MaxTokens(1024);
end;

//Synchronous example
var Chat := Client.Chat.Create(Payload);

try
for var Block in Chat.Content do
if Block.&Type = TContentBlockType.text then
Memo1.Lines.Text := Memo1.Text + Block.Text;
finally
Chat.Free;
end;

```

  • Streamed example (SSE):```pascal
    // uses Anthropic, Anthropic.Types, Anthropic.Helpers;
    // Client: IAnthropic;

//JSON payload
var Payload: TChatParamProc :=
procedure (Params: TChatParams)
begin
with Generation do
Params
.Model('claude-opus-4-7')
.Messages( MessageParts
.User('Explain the discrete topology')
)
.Thinking( CreateThinkingConfig('adaptive') )
.Stream;
end;

// Streaming callback
var StreamEvent: TChatEvent :=
procedure (var Event: TChatStream; IsDone: Boolean; var Cancel: Boolean)
begin
if not IsDone then
if Event.Block.&Type = TContentBlockType.text then
Memo1.Text := Memo1.Text + Event.Block.Text;
Application.ProcessMessages;
end;

//Synchronous example
Client.Chat.CreateStream(Payload, StreamEvent);
```

Summary
- Introduction
- Philosophy and Scope
- Documentation – Overview
- Going Further
- Functional Demo
- Functional Coverage
- Project Status
- License

Introduction

>Built with Delphi 12 Community Edition (v12.1 Patch 1)

>The wrapper itself is MIT-licensed.

>You can compile and test it free of charge with Delphi CE.

DelphiAnthropic is a native Delphi wrapper for the Anthropic Claude API, providing structured access to the Messages API, including:
- synchronous and asynchronous execution
- SSE streaming
- tools and function calling
- structured outputs (JSON schema)
- multimodal inputs (image, PDF)
- advanced reasoning modes (adaptive / extended thinking)
- the Managed Agents surface (Agents, Environments, Sessions, Vaults, Memory Stores)
- Webhook verification and consumption

>[!IMPORTANT]
> This is an unofficial library.

> Anthropic does not provide an official Delphi SDK for Claude.

> This project is a Delphi implementation over the public API

Philosophy and Scope

Anthropic now exposes two complementary surfaces:
- the Messages API, single and unified, where the client orchestrates each turn;
- the Managed Agents API, where Anthropic operates a long-lived runtime (Agent + Environment + Session) and the client drives it through events and resources.

Agent Skills extend Claude through implicit, model-selected execution. Tools are explicitly invoked and fully client-orchestrated. Managed Agents sit one level above: they bind an agent definition, an environment and a session container together, with their own event stream and resource model.

This wrapper therefore focuses on:
- faithful mapping of both the Messages API and the Managed Agents surface
- explicit modeling of execution modes (client-orchestrated vs server-orchestrated)
- clear separation between always-on API features and features gated by explicit Anthropic beta headers
- Delphi-first ergonomics, not JSON-first usage

Core execution modes

  • Standard generation
  • blocking or promise-based
  • full response returned at once
  • suitable for background processing or batch workflows

  • SSE streaming

  • synchronous or asynchronous
  • session-level or event-level callbacks
  • fine-grained interception of Claude SSE events

  • Tool-driven workflows

  • function calling
  • server-side tools (beta)
  • client-side orchestration
  • strict schema validation for agent safety

  • Server-orchestrated agents (Managed Agents)

  • long-lived Agent / Environment / Session lifecycle
  • resource attachments (GitHub repository, Files API entries, Memory Stores)
  • typed event surface (session events, thread events) with raw SSE access
  • credential management through Vaults
  • asynchronous, webhook-driven completion notifications

These distinctions are applied consistently at the API level and in the documentation.

Documentation – Overview

The documentation is organized as focused Markdown guides, each covering one major capability.

Main entry points

  • Content generation
  • non-streamed generation
  • SSE streaming
  • promises and orchestration (non-streamed and SSE)
  • Document & image understanding
  • image inputs
  • PDF analysis
  • Files API integration
  • Tools
  • function calling
  • tool orchestration
  • text editor
  • bash tools
  • web search
  • [beta] tools
  • Reasoning & control
  • adaptive thinking
  • extended thinking
  • effort control
  • fast mode
  • Agent Skills
  • Custom Skills – API & Versioning
  • Managed Agents
  • Agents
  • Environments
  • Sessions (Events / Resources / Threads / Thread Events)
  • Vaults & Credentials
  • Memory Stores

Each section includes Delphi-first examples, not raw JSON.

>[!WARNING]
> In Anthropic terminology, beta means "feature gated by explicit beta headers", not a prerelease SDK version.

Going Further

Advanced or cross-cutting topics are documented separately to keep the core readable:
- structured outputs
- Batch processing
- Prompt caching (5 min / 1 hour)
- Token counting
- Citations
- Models API — now exposes structured capability metadata (thinking modes, effort tiers, context-management features)
- Files API (CRUD)
- Webhooks — signature verification + typed event dispatch
- Tips and Tricks

Each topic has its own Markdown document, directly linked from the guides.

Functional Demo

This repository includes a working VCL demo in the demos folder, built on top of Pythia-WebView2, used here as the host application for the wrapper.

This demo matters for users of the wrapper because it shows DelphiAnthropic running inside a real application flow, not only through isolated code snippets. It demonstrates how the IAnthropic client is connected to a UI-oriented conversation layer, with asynchronous SSE streaming, request/response JSON traceability, file upload and download through the Files API, reasoning display, web search, code execution, skills and MCP configuration.

One key part of the demo is the context reconstruction layer (Demo.Anthropic.Context.pas). Instead of replaying only a flat history of user prompts and assistant answers, it rebuilds richer message context from the stored JSON request and streamed JSON response: text blocks, reasoning blocks, tool calls and matching tool results, MCP exchanges, web-search results and reusable container state for skills/code execution. This gives the next request a more faithful view of what actually happened in previous turns, while deliberately avoiding stale or ephemeral file references.

The guides keep the didactic path: each API surface is explained independently, with focused Delphi examples. The demo is the complementary reference: it shows how those capabilities cooperate end-to-end in a functional Delphi application, and it provides a practical starting point for validating your API key, runtime setup and optional MCP configuration. See also the demo-specific setup notes in demos/README.md.

Functional Coverage

Domain / Feature Supported Anthropic API (Beta)
Text generation ●
Multimodal (image, PDF input) ●
SSE / streaming ●
Persistent conversations ●
Agent skills ● ●
Batch processing ●
Structured outputs (JSON / strict tools) ●
Function / tool calling ●
Programmatic tool calling ● ●
Tool search (dynamic discovery) ● ●
Fine-grained tool streaming ●
Code execution (Python sandbox) ● ●
Computer use ● ●
Memory (cross-conversation) ● ●
Web search ●
Web fetch (URL / PDF content) ● ●
Citations ●
Search results grounding ●
Large context window (1M tokens) ● ●
Adaptive thinking ●
Extended thinking ●
Effort control ●
Context compaction ● ●
Context editing ● ●
Prompt caching (5 min) ●
Prompt caching (1 hour) ●
Token counting ●
File management (Files API) ● ●
Data residency (inference geo) ●
Fast mode (research preview) ● ●
Managed Agents — Agents ● ●
Managed Agents — Environments ● ●
Managed Agents — Sessions (Events / Resources / Threads) ● ●
Managed Agents — Vaults & Credentials ● ●
Managed Agents — Memory Stores ● ●
Webhooks (HMAC verification + typed events) ● ●
Advisor tool ● ●

>- Supported: support provided by DelphiAnthropic
>- Anthropic API (Beta): Feature available only via the Anthropic API (beta).

Project Status

  • The Anthropic API is evolving rapidly
  • Several advanced capabilities are still beta
  • The wrapper follows a pragmatic approach:
  • expose what exists
  • clearly label what is beta
  • avoid duplicating the official documentation
  • prefer correctness over abstraction

License

This project is licensed under the MIT License.

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
DelphiAnthropic 怎么安装?

在客户端按下面的安装命令接入:git clone https://github.com/MaxiDonkey/DelphiAnthropic && cd delphianthropic。对应的包名是 delphianthropic。装完在客户端配置里引用同一个包或端点。

DelphiAnthropic 怎么在 Claude Desktop、Cursor、Cline 里配置?

它的传输方式是stdio · 本地进程,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

DelphiAnthropic 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

DelphiAnthropic 需要 API Key 吗?

资料没有标注鉴权方式,是否需要密钥取决于服务本身,接入前按官方文档确认。

DelphiAnthropic 支持哪些客户端?

资料标注支持 Claude Desktop、Cursor、Cline、Claude Code;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

DelphiAnthropic 能提供哪些能力?

资料显示能力标签包括 anthropic、anthropic-ai、anthropic-api、anthropic-claude、caching。具体工具清单以官方文档为准。

DelphiAnthropic 需要什么运行环境?

运行时为 Cross-platform;属于本地进程,需要在本机装好运行环境。

DelphiAnthropic 是本地还是远程?

它是本地进程(stdio),由客户端在本机拉起。传输方式为stdio · 本地进程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 2026-04-20。