Nexus MCP
Enables querying Google Gemini models (Gemini 2.0 Flash, Pro) for text generation and reasoning, integrated into agents, plans, and councils.
Enables querying NVIDIA models (Nemotron-120B) for text generation and reasoning, integrated into agents, plans, and councils.
Enables querying local Ollama models for text generation and reasoning, integrated into agents, plans, and councils.
Enables querying OpenAI models (GPT-4o, GPT-5.4, o1) for text generation, reasoning, and task execution, integrated into agents, plans, and councils.
Enables querying Perplexity models (Sonar Pro, Sonar Reasoning) for text generation and research, integrated into agents, plans, and councils.
Enables querying Replicate's open-source models for text generation and reasoning, integrated into agents, plans, and councils.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Nexus MCP Run a multi-model council to decide the best pricing strategy"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Nexus MCP
The Universal AI Gateway for Claude — Delegate tasks to 27 AI providers. Orchestrate multi-agent plans. Run councils for decisions. All from a single MCP server.
What is Nexus MCP?
Nexus MCP is a Model Context Protocol (MCP) server that turns Claude into an orchestration engine for multi-AI systems. Instead of Claude doing everything, Nexus agents execute tasks while Claude plans, decides, monitors, and intervenes.
Paradigm: Opus Plans, Nexus Executes
Claude/Opus: Strategic thinking, planning, final decisions
Nexus agents: Autonomous execution, research, reasoning, tool use, code generation
27 AI providers: GPT-5.4, Gemini, Nemotron, Claude, Ollama, local models, and more
Key Features
27 Providers: 22 cloud (OpenAI, Google Gemini, Anthropic, Mistral, Cohere, Groq, Together, Perplexity, DeepSeek, xAI, HuggingFace, Replicate, Nvidia, etc.) + 5 local (Ollama, LM Studio, llama.cpp, LocalAI, vLLM)
15 MCP Tools: Quick asks, subagents, autonomous agents, plan execution, multi-agent councils
3 Orchestration Modes:
Agents: Autonomous execution with file/bash/web tools (ReAct loop)
Plans: Structured DAG workflows with dependencies and context injection
Councils: Multi-model deliberation (discussion/debate/research modes)
3 Auth Modes: API Key, Browser Session (Playwright), No Auth (local models)
Web Dashboard: Visual config at
http://localhost:9777— no JSON editingMulti-Round Deliberation: Agents see each other's outputs. Opus makes final decision
Zero AI SDKs: All providers via raw
fetch()— minimal dependenciesBrowser Auth: Log in via Chromium — no API keys needed
Related MCP server: Second Opinion MCP
Quick Start
1. Install
git clone https://github.com/your-username/nexus-mcp.git
cd nexus-mcp
npm install
npx playwright install chromium2. Build & Run
npm run build # Compile TypeScript
npm start # Run the serverOr for development:
npm run dev # Run with tsx (hot reload)3. Add to Claude Desktop
Edit your Claude Desktop config (%APPDATA%\Claude\claude_desktop_config.json on Windows):
{
"mcpServers": {
"nexus": {
"command": "node",
"args": ["C:/path/to/nexus-mcp/dist/index.js"]
}
}
}Restart Claude Desktop. You should see Nexus tools in the MCP tool list.
4. Add to Claude Code
claude mcp add nexus -- node /path/to/nexus-mcp/dist/index.js5. Configure
Open http://localhost:9777 in your browser to:
Enable providers
Add API keys
Switch models
Set up browser auth
Or configure from chat:
Use nexus_configure to set up OpenAI with API key sk-...
Use nexus_switch_model to switch to openai / gpt-4o
Use nexus_ask to ask: What is the meaning of life?MCP Tools (15 Total)
Core Tools
Tool | Description |
| Ask any provider/model a question — quick opinions |
| Change active provider and model |
| List all 27 providers and 217+ models |
| Health check all providers |
| Add/update API keys and settings from chat |
| Re-authenticate OAuth providers |
Subagents — Parallel Text Tasks
Tool | Description |
| Create batch of parallel text-only tasks |
| Run subagents and collect results |
| Chain models: A drafts → B reviews → C synthesizes |
| Check batch/task status |
Agents — Autonomous Execution
Tool | Description |
| Run single agent with file/bash/web tools (ReAct loop) |
| Run multiple agents in parallel with tools |
Orchestration — Complex Work
Tool | Description |
| DAG plan executor — steps with dependencies, parallel execution |
| Check plan status by ID |
| Multi-model council — discussion/debate/research modes, multi-round |
Supported Providers (27 Total)
Cloud Providers (22)
Provider | Auth Modes | Key Models |
OpenAI | API Key, OAuth | gpt-4o, gpt-5.4, o1, o3-mini |
Google Gemini | API Key, OAuth | gemini-2.0-flash, gemini-2.0-pro |
Anthropic | API Key | claude-opus-4-6, claude-sonnet-4-6 |
Nvidia | API Key (free) | Nemotron-120B, NV-Embed |
Mistral | API Key | mistral-large, codestral |
Cohere | API Key | command-r-plus, command-r |
Groq | API Key | Llama-3.3-70B, Mixtral-8x7B |
Together AI | API Key | Llama-3.3-70B, Qwen2.5-72B |
Perplexity | API Key | sonar-pro, sonar-reasoning |
DeepSeek | API Key | deepseek-chat, deepseek-reasoner |
xAI (Grok) | API Key | grok-2, grok-2-mini |
HuggingFace | API Key | Llama-3.3-70B, Mixtral-8x7B |
Replicate | API Key | 100+ open-source models |
OpenRouter | API Key | Multi-provider routing |
Fireworks | API Key | Fast inference |
DeepInfra | API Key | 100+ models, cheap |
Cerebras | API Key | Fast inference |
SambaNova | API Key | CoE architecture |
Abacus.AI | API Key | Custom models |
AI21 Labs | API Key | Jurassic models |
OpenCode Zen | API Key | Custom gateway |
Custom | API Key, OAuth | Any OpenAI-compatible endpoint |
Local Providers (5)
Provider | Default Port | Notes |
Ollama | 11434 | Auto-discovers installed models |
LM Studio | 1234 | OpenAI-compatible API |
llama.cpp | 8080 | OpenAI-compatible API |
LocalAI | 8080 | OpenAI-compatible API |
vLLM | 8000 | OpenAI-compatible API |
Browser Authentication
For providers that support it, you can use your existing browser login instead of an API key:
Use
nexus_reauthtool or click the 🔑 button in the dashboardA Chromium browser window opens at the provider's login page
Log in normally
Close the browser — your session is saved
Future requests use the saved session (headless)
Sessions are stored at ~/.nexus/sessions/.
Architecture
Claude Desktop/Code
│
├──stdio──> Nexus MCP Server
│ ├─ MCP Handler (15 tools)
│ ├─ Orchestrator
│ │ ├─ Agent Executor (ReAct loop, tools)
│ │ ├─ Plan Executor (DAG scheduler, dependency injection)
│ │ ├─ Council Manager (multi-round deliberation)
│ │ └─ Subagent Manager (parallel text tasks)
│ ├─ Provider Router (27 providers, auto-failover)
│ ├─ Auth Manager (API Key, OAuth PKCE, Sessions)
│ └─ Web Dashboard (:9777)
│
├──http──> Dashboard UI (http://localhost:9777)
│
└──APIs──> 27 AI Providers
├─ 22 Cloud APIs
└─ 5 Local ServersSingle Node.js process. Stdio for MCP (Claude communication), HTTP for dashboard UI, outbound to provider APIs. Config at ~/.nexus/config.json.
The Paradigm: Opus Plans, Nexus Executes
Claude/Opus is the strategic brain. It never executes directly. Instead:
Claude plans — Structure complex work as DAGs, orchestrate decisions via councils
Nexus agents execute — Autonomous execution with tools (file read/write, bash, web search)
Claude reviews & decides — Monitor all outputs, intervene when needed, make final calls
When to Use Each Tool
Scenario | Tool | Why |
Quick question |
| Get instant opinion from any model |
Parallel research |
| 5 agents researching in parallel |
Code/file work |
| Agent with tools (read, write, bash) |
Multi-step project |
| DAG with dependencies, parallel execution |
Architecture choice |
| Models challenge each other, Opus decides |
Security audit |
| Agents investigate with tools |
Plan Example
A three-step code generation project:
{
title: "Add JWT Auth",
steps: [
{
id: "analyze",
mode: "agent",
description: "Read codebase and find auth patterns"
},
{
id: "code",
depends_on: ["analyze"],
inject_context_from: ["analyze"],
mode: "agent",
description: "Generate JWT implementation"
},
{
id: "test",
depends_on: ["code"],
inject_context_from: ["code"],
mode: "agent",
description: "Write and run tests"
}
]
}Step code automatically sees step analyze's output. Steps run in parallel where possible.
Configuration
All configuration is managed through the web dashboard or MCP tools. The config file is at ~/.nexus/config.json but you should never need to edit it manually.
Environment Variables
Variable | Description |
| Set to any value to enable debug logging |
Development
npm run dev # Run with tsx
npm run build # Compile TypeScript
npm run typecheck # Type check without emittingArchitecture Deep Dive
Core Subsystems
Agent Executor (
src/agent/executor.ts) — ReAct loop with OpenAI function-calling format. Agents can read/write files, run bash, search web.Plan Executor (
src/orchestrator/plan-executor.ts) — DAG scheduler using topological sort (Kahn's algorithm). Detects cycles, runs steps in parallel, injects context from dependencies.Council Manager (
src/orchestrator/council.ts) — Multi-round deliberation. Three modes:Discussion — Models collaborate
Debate — Models challenge each other
Research — Agents investigate with tools
Provider Router (
src/providers/router.ts) — Failover logic. If one provider is down, auto-switches to next available.Auth Manager (
src/auth/) — API keys, OAuth PKCE (Chromium browser), session storage.Web Dashboard (
src/web/server.ts) — Visual config UI at port 9777.
File Structure
src/
├── index.ts # Entry point
├── mcp-server.ts # MCP tool handlers
├── agent/
│ ├── executor.ts # ReAct agent loop
│ ├── sandbox.ts # Tool execution sandbox
│ └── tools.ts # File/bash/web/search tools
├── orchestrator/
│ ├── plan-executor.ts # DAG scheduler
│ ├── plan-types.ts # PlanStep, PlanRecord interfaces
│ ├── council.ts # Multi-agent councils
│ └── council-types.ts # Council interfaces
├── providers/ # 27 provider adapters
│ ├── router.ts # Main routing logic
│ ├── registry.ts # Provider registration
│ ├── cloud/ # OpenAI, Gemini, Anthropic, etc.
│ └── local/ # Ollama, LM Studio, etc.
├── auth/ # Authentication strategies
├── config/ # Config schema & defaults
├── tools/ # 15 MCP tool definitions
├── utils/ # Logging, errors, HTTP
└── web/ # Dashboard frontend + server
dist/ # Compiled JS (after npm run build)Contributing
Contributions are welcome! Please:
Fork the repository
Create a feature branch (
git checkout -b feature/my-feature)Make your changes
Run tests and type-check (
npm run typecheck)Submit a pull request
Adding a New Provider
Create a new file in
src/providers/cloud/orsrc/providers/local/Implement the
ProviderAdapterinterface (or extendOpenAICompatibleProvider)Register it in
src/providers/registry.tsAdd default config in
src/config/defaults.tsType-check and test with other providers
Adding a New MCP Tool
Create a new file in
src/tools/my-tool.tsExport a function matching the tool interface
Add to
ALL_TOOLSinsrc/mcp-server.tsAdd the switch case handler
License
MIT License. See LICENSE for details.
Available Tools
15 toolsnexus_agent_multiA
Run multiple autonomous AI agents IN PARALLEL, each with its own model and task. Each agent independently reads files, writes code, and executes commands. Perfect for divide-and-conquer tasks: one agent codes while another tests, or multiple agents each tackle a different part of a large codebase. All agents run simultaneously and results are returned together.
Inputs: agents (required).
nexus_agent_runA
Run an autonomous AI agent that can read files, write code, execute shell commands, search the web, and iterate until the task is complete. The agent uses the specified model (GPT-5.4, Nemotron, Gemini, etc.) and works independently through a ReAct loop. Returns the final answer plus a full trace of every action taken.
Inputs: task (required), model (required), provider (required), role, +7 more.
nexus_askB
Send a prompt to any AI provider (ChatGPT, Gemini, Claude, Ollama, etc.). Uses the active provider/model by default, or specify a different one.
Inputs: prompt (required), model, provider, maxTokens, +2 more.
nexus_configureB
Configure a provider directly from chat — set API keys, base URLs, enable/disable providers. For full management, use the web dashboard.
Inputs: provider (required), apiKey, baseUrl, enabled, +1 more.
nexus_councilA
Convene a multi-model council where AI agents deliberate in rounds and Opus makes the final decision. DISCUSSION: Models build on each other collaboratively. DEBATE: Models challenge each other adversarially. RESEARCH: Models investigate with tools (file read, web search) and cross-reference findings. All participants respond in parallel each round, seeing all prior contributions. Use this for architecture decisions, code reviews, security audits, complex analysis.
Inputs: topic (required), participants (required), mode, rounds, +1 more.
nexus_list_modelsA
List all available AI providers and their models, with status indicators. Optionally filter by a specific provider.
Inputs: provider.
nexus_plan_executeA
Execute a structured multi-step plan where Claude is the orchestrator and Nexus agents do the work. Independent steps run IN PARALLEL. Dependent steps wait and receive context from prior steps. Use mode="agent" for steps that need file access/code execution. Use mode="prompt" for analysis/review steps. Opus plans, Nexus executes.
Inputs: steps (required), title, context, max_total_time_ms.
nexus_plan_statusB
Check the status of a previously executed plan. Returns per-step results and metadata.
Inputs: plan_id.
nexus_reauthA
Open a browser window for re-authentication with a provider. Log into your account, then close the browser. Your session will be saved for future use. Supported providers: openai, gemini, anthropic, perplexity, mistral, cohere, huggingface, deepseek, groq
Inputs: provider (required), url.
nexus_statusB
Health check all configured AI providers. Shows connection status, latency, and any errors.
Inputs: provider.
nexus_subagent_collabA
Multi-model collaboration pipeline. Models work sequentially: first model produces output, next reviews/refines, optional final model synthesizes. Returns final output plus all intermediate steps showing each model's contribution.
Inputs: task (required), models (required).
nexus_subagent_runA
Execute all tasks in a spawned batch in parallel. Waits for all to complete. Returns results from every model with metadata (text, latency, tokens, errors).
Inputs: batchId (required).
nexus_subagent_spawnA
Spawn one or more AI subagent tasks for parallel execution. Each task targets a specific provider/model with its own prompt. Returns a batch ID — use nexus_subagent_run to execute.
Inputs: tasks (required), timeoutMs.
nexus_subagent_statusB
Check status of subagent batches. Shows pending, running, or completed batches with results. Omit batchId to list all recent batches.
Inputs: batchId.
nexus_switch_modelA
Switch the active AI provider and model. After switching, all subsequent nexus_ask calls will use the new provider/model.
Inputs: model (required), provider (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 15 tools
The provider-management tools are clearly distinct, but the orchestration family overlaps: nexus_subagent_spawn/run, nexus_agent_run/multi, nexus_subagent_collab, and nexus_council all involve dispatching model tasks, and the boundaries between subagent, agent, and council workflows are not immediately obvious. The descriptions clarify the different interaction patterns enough to be usable, but an agent could still misselect among them.
All tools share the nexus_ prefix and snake_case, but the convention is inconsistent: list_models, switch_model, and reauth use verb-led names, while subagent_spawn, subagent_collab, agent_multi, and council use noun-led or noun-only names. The prefix helps recognition, but an agent cannot reliably predict a tool name from its function.
At 15 tools, this sits at the upper edge of the ideal range but is justifiable for a multi-provider orchestration server covering provider configuration, simple prompts, subagents, autonomous agents, plans, and councils. A few orchestration modes could potentially be consolidated, but the count is not bloated.
The surface covers provider health, authentication, configuration, model listing/switching, prompt execution, subagent batches, autonomous agents, plans, and councils, with status/result retrieval for the async workflows. The main gap is the lack of any cancel/abort tool for long-running agents, batches, or councils, which is a notable but non-fatal omission.
Maintenance
Related MCP Connectors
One MCP endpoint for Claude, GPT & Gemini: 100+ tools + no-code connectors + agent workers.
AI work orchestration for plans, tasks, teams, and coding-agent dispatch.
AI routing, memory, guardrails, and governance. Routes across Claude, GPT, Gemini.
The AI brain for builders: ChatGPT, Claude and your other AIs share one workspace and one method.
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables Claude to coordinate multiple specialized AI agents by creating tasks, tracking their complete thought process and execution in real-time, and monitoring progress across parallel workflows with full transparency.1822 npm2MIT
- AlicenseNot gradedqualityCmaintenanceEnables Claude to consult over 17 AI platforms and 800,000+ models to provide alternative perspectives, code reviews, and diverse feedback. It features a unique personality system and supports multi-AI group discussions and debates directly within the chat interface.46MIT
- AlicenseNot gradedqualityCmaintenanceCoordinates up to 64 parallel expert agents for complex multi-agent orchestration and intelligent task routing within Claude Code. It enables users to analyze requests, manage hierarchical execution plans, and monitor active orchestration sessions.MIT
- AlicenseAqualityBmaintenanceEnables Claude to chat with various AI models and obtain multi-model consensus for complex decisions.41,864 npm2MIT