What it does
Delegate asynchronous coding jobs between Claude Code, Codex, Cursor Agent, and Pi.
- Connects 在你的电脑上运行
- Account or key No key needed
- Category 开发者工具
可搭配使用
教 AI 做这类工作的 Skill,可与本项一起使用
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
graphify
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
为什么排在这里
列表按使用分(满分 100)排序,由以下部分组成
| 热度 | 4/80 | GitHub 星标或每周下载量:较大的计 60,较小的计 20 |
|---|---|---|
| 新鲜度 | 12/12 | 30 天内有发布或代码更新得满分 |
| 仍在响应 | 0/8 | 上次检查时云端端点有响应 |
| 使用分 | 16/100 |
质量: 基础检查通过 2/3 项(仅展示,不用于排序) · 上升势头: 暂无数据 (只用于“上升中”标签)
安装
选择你使用的 AI 应用,然后复制设置。
通过 2/3 项检查 · 在你的电脑上运行
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude,但需要先准备
不需要密钥,不用安装程序 · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用
双击文件,然后在电脑版 Claude 应用中点击 Install
试一试
用 LLM Provider MCP 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 LLM Provider MCP,或回答中出现 LLM Provider MCP 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
ChatGPT 暂时无法连接 LLM Provider MCP
LLM Provider MCP 需要安装在你的电脑上,而 ChatGPT 只能连接在网上运行的服务器
你可以改用这些方式
A · 使用能连接 LLM Provider MCP 的应用
- 不需要密钥,不用安装程序 · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用
B · 开发者工具 类中能连接 ChatGPT 的其他服务器
从同类中使用较多的里挑选,仅限用地址即可连接、无需密钥的
- Sentry✓ ChatGPT
- Compiler Explorer✓ ChatGPT
- GitDiagram✓ ChatGPT
Claude Code 暂时无法连接 LLM Provider MCP
开发者只提供了电脑版 Claude 应用的安装文件
你可以改用这些方式
A · 使用能连接 LLM Provider MCP 的应用
- 不需要密钥,不用安装程序 · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用
Cursor 暂时无法连接 LLM Provider MCP
开发者只提供了电脑版 Claude 应用的安装文件
你可以改用这些方式
A · 使用能连接 LLM Provider MCP 的应用
- 不需要密钥,不用安装程序 · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用
VS Code 暂时无法连接 LLM Provider MCP
开发者只提供了电脑版 Claude 应用的安装文件
你可以改用这些方式
A · 使用能连接 LLM Provider MCP 的应用
- 不需要密钥,不用安装程序 · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用
一览
哪些应用可以使用它
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
在你的电脑上运行,适用于
ClaudeGooseLM StudioMsty StudioCherry StudioVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
它能做什么
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
基础检查i
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月19日
- ✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 manishiitg 验证,该账户拥有此仓库
- ✓ 通过
仍在维护
代码最后更新于今天
- ! 注意
有许可证
GitHub 无法识别许可证类型;请打开文件自行查看
- – 不适用
端点有响应
它在你的电脑上运行,没有互联网端点
- – 不适用
使用 OAuth 登录
在你的电脑上运行,改用本地设置
- … 尚未检查
工具描述中没有隐藏指令
它在你的电脑上运行;我们只能读取互联网端点的工具列表
作者:申请重新检查或报告信息错误
给作者:在 README 中加徽章
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/servers/manishiitg-llm-provider-mcp)讨论
提问、分享技巧或报告无法使用。按“有帮助”数量排序。
用户评价
还没有评价
与“开发者工具”中的其他服务器比较i
- 星标数多于此分类中其他 6182 个服务器的 69%
- 发布到注册中心的时间比此分类中其他 6182 个服务器的 20% 更新
- 基础检查结果等于或优于此分类中其他 6182 个服务器的 45%
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
常见问题
LLM Provider MCP 安全吗?
它在 3 项适用的基础检查中通过了 2 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
它需要哪些密钥或代码?
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在我的电脑上运行还是在云端?
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
它还在维护吗?
GitHub 仓库最后更新于今天,最新版本(0.7.3)于4个月前进入注册中心。
哪些应用可以使用它?
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 MCPB。
有什么可以替代它?
同一分类中有:GitDiagram, Appllama, Cloudflare MCP, Omnara, Repowise
功能相近的其他选择
同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
GitDiagram
Architecture diagrams, explanations and Mermaid source for public GitHub repositories.
Appllama
Study screens, flows and paywalls from top-earning iOS apps, then build from what wins.
Omnara
Deploy durable AI agents with Omnara, an open-source managed-agent platform.
Repowise
Codebase intelligence for AI coding agents: graph, git history, docs, decisions, code health.
| 本项 LLM Provider MCP | GitDiagram | Appllama | Cloudflare MCP | Omnara | Repowise | |
|---|---|---|---|---|---|---|
| 运行位置 | 需要安装在电脑上 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 云端或安装在电脑上都可以 |
| 需要密钥 | 否 | 否 | 否 | 否 | 否 | 否 |
| 可在 Claude 中按 + 添加 | 否 | 否 | 否 | 是 | 否 | 否 |
| 基础检查 | 2/3 | 4/4 | 4/4 | 4/4 | 4/4 | 5/5 |
| 许可证 | NOASSERTION | MIT | MIT | Apache-2.0 | Apache-2.0 | AGPL-3.0 |
| 价格 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 |
作者的 README
打开 README
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Multi-LLM Provider for Go
multi-llm-provider-go is a Go library for using hosted LLM APIs and local coding agents through a shared set of provider interfaces.
It supports two complementary ways to run a model:
- API providers call hosted models through their normal SDK or HTTP transport, including OpenAI, Anthropic, Bedrock, Vertex AI, Azure, and OpenRouter.
- Coding-agent providers run Claude Code, Codex CLI, Cursor Agent, or Pi in native SDK or protocol sessions, preserving their native tools, subscriptions, project context, and authenticated sessions.
The repository also includes llm-provider-mcp, an optional MCP server for delegating asynchronous work between coding agents. It is one way to expose the provider library—not the library's only use case.
Why This Exists
Applications should be able to choose the right model and transport for each task without rebuilding their orchestration layer.
Use a direct API when you want a conventional request/response integration, predictable infrastructure, or model-level features such as structured output, embeddings, and media generation. Use a coding-agent CLI when you want an agent that can inspect a repository, edit files, run commands, and reuse an existing local subscription. Both fit behind the same Go model abstraction.
flowchart LR
App[Go application] --> Provider[Shared provider interfaces] Provider --> API[API and cloud adapters] Provider --> CLI[Local coding-agent adapters] API --> Hosted[Hosted models] CLI --> Native[SDK / app-server / RPC] CLI --> Tmux[Optional tmux sessions] Native --> Agents[Claude Code / Codex / Cursor / Pi] Tmux --> Agents MCP[Optional MCP server] --> CLI
Supported Providers
The core InitializeLLM factory returns the same llmtypes.Model interface for text and coding-agent providers:
| Provider ID | Integration | Transport |
|---|---|---|
openai | OpenAI | OpenAI Go SDK |
anthropic | Anthropic | Anthropic Go SDK |
openrouter | OpenRouter | OpenAI-compatible API |
bedrock | AWS Bedrock | AWS SDK |
vertex | Google Vertex AI and Gemini | Google Gen AI SDK |
azure | Azure AI | Azure/OpenAI-compatible API |
z-ai | Z.AI | OpenAI-compatible API |
kimi | Kimi/Moonshot | OpenAI-compatible API |
minimax, minimax-coding-plan | MiniMax | Provider API |
claude-code | Claude Code | Agent SDK; optional tmux |
codex-cli | Codex CLI | app-server; optional tmux |
cursor-cli | Cursor Agent | Cursor SDK; optional ACP or tmux |
pi-cli | Pi | RPC |
Specialized factories expose capabilities that do not fit the text-model interface:
| Capability | Providers |
|---|---|
| Embeddings | OpenAI, OpenRouter, Vertex AI, Bedrock |
| Image generation | Vertex AI, MiniMax Coding Plan, Codex CLI |
| Video generation | Vertex AI (Veo and Gemini Omni) |
| Text to speech | Vertex AI, MiniMax, ElevenLabs, Deepgram |
| Audio transcription | Deepgram |
| Music generation | ElevenLabs, MiniMax |
Gemini models are available through Vertex AI for direct API access or through Pi as a coding agent. The old Gemini CLI adapter has been removed.
Common Capabilities
Provider support varies, but the shared interfaces cover:
- Text generation and streaming
- Tool calling and structured output
- Token usage, model metadata, logging, and event emission
- Embeddings
- Image input and generation
- Video generation and conversational video editing
- Audio generation and transcription
- Music generation
- Stateful coding-agent sessions, continuation, and terminal progress
Quick Start: Go Library
Install the module:
go get github.com/manishiitg/multi-llm-provider-go@latest
The current module requires Go 1.25.12 or newer.
Initialize a provider and use the returned llmtypes.Model:
package main
import ( "context" "fmt" "log"
llmproviders "github.com/manishiitg/multi-llm-provider-go" "github.com/manishiitg/multi-llm-provider-go/llmtypes" )
func main() { model, err := llmproviders.InitializeLLM(llmproviders.Config{ Provider: llmproviders.ProviderOpenAI, ModelID: "gpt-4.1-mini", }) if err != nil { log.Fatal(err) }
response, err := model.GenerateContent( context.Background(), []llmtypes.MessageContent{ llmtypes.TextParts(llmtypes.ChatMessageTypeHuman, "Explain tmux in one sentence."), }, ) if err != nil { log.Fatal(err) }
if len(response.Choices) == 0 { log.Fatal("provider returned no choices") } fmt.Println(response.Choices[0].Content) }
Set the credential expected by the selected provider—for example, OPENAI_API_KEY for OpenAI. Credentials can also be supplied explicitly with Config.APIKeys. See the examples for streaming, tool calls, custom logging, Bedrock, and Vertex AI.
Configuration
llmproviders.Config controls provider initialization:
| Field | Purpose |
|---|---|
Provider | Selects the API, cloud platform, or coding CLI |
ModelID | Selects a model; provider defaults apply when supported |
Temperature | Sets sampling temperature for providers that expose it |
APIKeys | Supplies credentials explicitly instead of using the environment |
MaxRetries | Configures retries on the selected model |
Logger / EventEmitter | Connects host logging, tracing, and model events |
Context | Controls initialization lifetime and cancellation |
Common credential sources include:
| Provider | Environment or native authentication |
|---|---|
| OpenAI | OPENAI_API_KEY |
| Anthropic | ANTHROPIC_API_KEY |
| OpenRouter | OPENROUTER_API_KEY |
| AWS Bedrock | Standard AWS credential chain and AWS_REGION |
| Vertex AI | VERTEX_API_KEY, GOOGLE_API_KEY, or Google application credentials |
| Azure AI | AZURE_AI_ENDPOINT and AZURE_AI_API_KEY |
| Z.AI / Kimi | ZAI_API_KEY, KIMI_API_KEY |
| MiniMax | MINIMAX_API_KEY or MINIMAX_CODING_PLAN_API_KEY |
| ElevenLabs / Deepgram | ELEVENLABS_API_KEY, DEEPGRAM_API_KEY |
| Coding-agent CLIs | Existing native CLI login or provider configuration |
See .env.example for common provider credentials. Model, endpoint, fallback, and test-specific variables are documented next to the provider adapters and tests that consume them.
Changing transports starts with changing the provider:
config.Provider = llmproviders.ProviderAnthropic // direct API
config.Provider = llmproviders.ProviderBedrock // cloud API config.Provider = llmproviders.ProviderCodexCLI // local coding agent config.Provider = llmproviders.ProviderCursorCLI // local coding agent
Bounded coding-agent calls can use the process working directory and a temporary session automatically. Long-lived host applications should explicitly pass CodingAgentWorkingDirOption, CodingAgentInteractiveSessionOption, and CodingAgentPersistentInteractiveOption. Provider-specific options additionally control the model, approval policy, resume ID, tools, and streaming behavior.
Coding-agent transports
The coding-agent adapters turn native coding CLIs into providers without reimplementing their agent loops. They use each CLI's existing login and model access, and run in a local project with that CLI's native file and shell tools.
Native SDK and protocol transports are the defaults. Keep tmux available explicitly when a terminal session is needed:
| Provider | Default | Environment override |
|---|---|---|
| Claude Code | SDK | CLAUDE_CODE_TRANSPORT=sdk or tmux |
| Codex | app-server | CODEX_CLI_TRANSPORT=app-server or tmux |
| Cursor | SDK | CURSOR_CLI_TRANSPORT=sdk, acp or tmux |
| Pi | RPC | No terminal transport |
Set these variables on the backend and restart it. A native launch failure does not switch to tmux automatically. SDK modes require Node.js and the matching @anthropic-ai/claude-agent-sdk or @cursor/sdk package. The adapters look in the managed CLI installation prefix before the global npm prefix; explicit CLAUDE_AGENT_SDK_PATH and CURSOR_SDK_PATH overrides are also supported.
| CLI | Provider ID | Authentication |
|---|---|---|
| Claude Code | claude-code | Existing Claude Code login or scoped OAuth token |
| Codex CLI | codex-cli | Existing Codex login |
| Cursor Agent | cursor-cli | Existing Cursor login |
| Pi CLI | pi-cli | Existing Pi/provider configuration |
Requirements for the optional tmux transport:
- macOS or Linux
- tmux 3.x or newer
- At least one installed and authenticated coding CLI
The library exposes session lifecycle, resume, input, interrupt, pane capture, and cleanup helpers so a host application can manage coding agents as part of its own workflow.
Module Layout
multi-llm-provider-go/
├── providers.go # Provider IDs, configuration, initialization ├── provider_*.go # Shared provider behavior and media factories ├── interfaces/ # Logging, events, and public support contracts ├── llmtypes/ # Messages, responses, tools, streams, options ├── pkg/adapters/ # API, cloud, media, and coding-CLI adapters ├── pkg/codingagentjob/ # Durable asynchronous job execution ├── pkg/codingagentmcp/ # Optional MCP tool surface ├── pkg/tmuxcapture/ # Terminal progress capture and cleanup ├── cmd/llm-chat/ # Local provider chat client ├── cmd/llm-test/ # Manual provider contract runner └── cmd/llm-provider-mcp/ # Optional delegation MCP server
llmtypes.Model is the central text request/response interface. Additional interfaces cover embeddings, image generation, video generation, audio generation and transcription, and music generation.
Optional: Asynchronous Delegation Over MCP
llm-provider-mcp packages the coding-agent providers as a local stdio MCP server. A Codex or Claude Code host can queue work in another coding CLI, continue working, and retrieve the result later. Jobs are persisted in SQLite and executed in detached tmux sessions.
Install it in the project where you want delegation:
curl -fsSL https://raw.githubusercontent.com/manishiitg/llm-provider-mcp/main/scripts/install-mcp.sh | sh
The setup detects installed CLIs, registers selected hosts and targets for the current project, verifies authentication, and installs the delegation skill. The server is also published in the official MCP Registry as io.github.manishiitg/llm-provider-mcp.
It exposes five tools:
| Tool | Purpose |
|---|---|
list_coding_agents | List enabled targets and capabilities |
list_coding_agent_models | Discover available model selectors |
delegate_coding_agent | Start an asynchronous coding job |
get_coding_agent_job | Read progress, terminal output, or the final result |
cancel_coding_agent_job | Stop a queued or running job |
See Installation and Delegation workflow for the complete MCP workflow.
Security And Trust
- Direct API credentials remain in the host process or the provider's normal credential chain.
- Coding-agent credentials remain owned by the native CLI.
- tmux-backed agents have the local user's filesystem and process permissions; tmux is a transport, not a sandbox.
- A coding agent can modify the working tree and run commands. Review and test delegated changes before accepting them.
- `LLM_PROVIDER_M