nexus

Name: nexus
Author: Nexus-Router

437stars25forks

How to install nexus?

nexus-router/nexus

$git clone https://github.com/Nexus-Router/nexus

Installs into the current project.

Summary

MCP Server Aggregation: Connect multiple MCP servers (STDIO, SSE, HTTP) through a single endpoint - LLM Provider Routing: Unified interface for OpenAI, Anthropic, Google, and AWS Bedrock LLM providers with full tool calling support - Context-Aware Tool Search: Intel

Files · 1

View on GitHub

README.md

1	<div align="center">
2	<picture>
3	<source width="600" height="244" srcset="https://github.com/user-attachments/assets/9ca64651-b601-45e3-8ba1-f7bfb91625ab" media="(prefers-color-scheme: dark)">
4	<source width="600" height="244" srcset="https://github.com/user-attachments/assets/5ee33450-f9ee-4e47-b0ed-0d302110c4ce"" media="(prefers-color-scheme: light)">
5	<img src="https://github.com/user-attachments/assets/9ca64651-b601-45e3-8ba1-f7bfb91625ab" alt="Nexus logo">
6	</picture>
7	</div>
8
9	<p align="center">
10	Plug in all your MCP servers, APIs, and LLM providers. Route everything through a unified endpoint. <br />
11	Aggregate, govern, and control your AI stack.
12	</p>
13
14	## Features
15
16	- MCP Server Aggregation: Connect multiple MCP servers (STDIO, SSE, HTTP) through a single endpoint
17	- LLM Provider Routing: Unified interface for OpenAI, Anthropic, Google, and AWS Bedrock LLM providers with full tool calling support
18	- Context-Aware Tool Search: Intelligent fuzzy search across all connected tools using natural language queries
19	- Protocol Support: Supports STDIO (subprocess), SSE (Server-Sent Events), and streamable HTTP MCP servers
20	- Flexible Configuration: TOML-based configuration with environment variable substitution
21	- Security: Built-in CORS, CSRF protection, OAuth2, and TLS support
22	- Rate Limiting: Multi-level rate limiting with in-memory or Redis backends
23	- Docker Ready: Available as a container image with minimal configuration needed
24
25	## Installation
26
27	### Quick Install (Linux/Windows (WSL)/macOS)
28
29	```bash
30	curl -fsSL https://nexusrouter.com/install \| bash
31	```
32
33	### Docker
34
35	Pull the latest image:
36	```bash
37	docker pull ghcr.io/grafbase/nexus:latest
38	```
39
40	Or use the stable version:
41	```bash
42	docker pull ghcr.io/grafbase/nexus:stable
43	```
44
45	Or use a specific version:
46	```bash
47	docker pull ghcr.io/grafbase/nexus:X.Y.Z
48	```
49
50	### Build from Source
51
52	```bash
53	git clone https://github.com/grafbase/nexus
54	cd nexus
55	cargo build --release
56	```
57
58	## Running Nexus
59
60	### Using the Binary
61
62	```bash
63	nexus
64	```
65
66	### Using Docker
67
68	```bash
69	docker run -p 8000:8000 -v /path/to/config:/etc/nexus.toml ghcr.io/grafbase/nexus:latest
70	```
71
72	### Docker Compose Example
73
74	```yaml
75	services:
76	nexus:
77	image: ghcr.io/grafbase/nexus:latest
78	ports:
79	- "8000:8000"
80	volumes:
81	- ./nexus.toml:/etc/nexus.toml
82	environment:
83	- GITHUB_TOKEN=${GITHUB_TOKEN}
84	healthcheck:
85	test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
86	interval: 30s
87	timeout: 10s
88	retries: 3
89	```
90
91	## Configuration
92
93	Create a `nexus.toml` file to configure Nexus:
94
95	```toml
96	# LLM Provider configuration
97	[llm.providers.openai]
98	type = "openai"
99	api_key = "{{ env.OPENAI_API_KEY }}"
100	forward_token = true
101
102	# Model configuration (at least one model required per provider)
103	[llm.providers.openai.models.gpt-4]
104	[llm.providers.openai.models.gpt-3-5-turbo]
105
106	[llm.providers.anthropic]
107	type = "anthropic"
108	api_key = "{{ env.ANTHROPIC_API_KEY }}"
109
110	[llm.providers.anthropic.models.claude-3-5-sonnet-20241022]
111
112	# MCP Server configuration
113	[mcp.servers.github]
114	url = "https://api.githubcopilot.com/mcp/"
115	auth.token = "{{ env.GITHUB_TOKEN }}"
116
117	[mcp.servers.filesystem]
118	cmd = ["npx", "-y", "@modelcontextprotocol/server-filesystem", "/home/YOUR_USERNAME/Desktop"]
119
120	[mcp.servers.python_server]
121	cmd = ["python", "-m", "mcp_server"]
122	env = { PYTHONPATH = "/opt/mcp" }
123	cwd = "/workspace"
124	```
125
126	### Configuration Options
127
128	#### Server Configuration
129
130	- `server.listen_address`: The address and port Nexus will listen on (default: `127.0.0.1:8000`)
131	- `server.health.enabled`: Enable health endpoint (default: `true`)
132	- `server.health.path`: Health check endpoint path (default: `/health`)
133
134	#### LLM Configuration
135
136	- `llm.enabled`: Enable LLM functionality (default: `true`)
137	- `llm.protocols.openai.enabled`: Enable OpenAI protocol endpoint (default: `true`)
138	- `llm.protocols.openai.path`: OpenAI endpoint path (default: `/llm/openai`)
139	- `llm.protocols.anthropic.enabled`: Enable Anthropic protocol endpo

People who liked this also viewed

6 picks

Type

nexus

437stars25forks

View on GitHub

How to install nexus?

nexus-router/nexus

$git clone https://github.com/Nexus-Router/nexus

Installs into the current project.

Summary

Files · 1

View on GitHub

README.md

1	<div align="center">
2	<picture>
3	<source width="600" height="244" srcset="https://github.com/user-attachments/assets/9ca64651-b601-45e3-8ba1-f7bfb91625ab" media="(prefers-color-scheme: dark)">
4	<source width="600" height="244" srcset="https://github.com/user-attachments/assets/5ee33450-f9ee-4e47-b0ed-0d302110c4ce"" media="(prefers-color-scheme: light)">
5	<img src="https://github.com/user-attachments/assets/9ca64651-b601-45e3-8ba1-f7bfb91625ab" alt="Nexus logo">
6	</picture>
7	</div>
8
9	<p align="center">
10	Plug in all your MCP servers, APIs, and LLM providers. Route everything through a unified endpoint. <br />
11	Aggregate, govern, and control your AI stack.
12	</p>
13
14	## Features
15
16	- MCP Server Aggregation: Connect multiple MCP servers (STDIO, SSE, HTTP) through a single endpoint
17	- LLM Provider Routing: Unified interface for OpenAI, Anthropic, Google, and AWS Bedrock LLM providers with full tool calling support
18	- Context-Aware Tool Search: Intelligent fuzzy search across all connected tools using natural language queries
19	- Protocol Support: Supports STDIO (subprocess), SSE (Server-Sent Events), and streamable HTTP MCP servers
20	- Flexible Configuration: TOML-based configuration with environment variable substitution
21	- Security: Built-in CORS, CSRF protection, OAuth2, and TLS support
22	- Rate Limiting: Multi-level rate limiting with in-memory or Redis backends
23	- Docker Ready: Available as a container image with minimal configuration needed
24
25	## Installation
26
27	### Quick Install (Linux/Windows (WSL)/macOS)
28
29	```bash
30	curl -fsSL https://nexusrouter.com/install \| bash
31	```
32
33	### Docker
34
35	Pull the latest image:
36	```bash
37	docker pull ghcr.io/grafbase/nexus:latest
38	```
39
40	Or use the stable version:
41	```bash
42	docker pull ghcr.io/grafbase/nexus:stable
43	```
44
45	Or use a specific version:
46	```bash
47	docker pull ghcr.io/grafbase/nexus:X.Y.Z
48	```
49
50	### Build from Source
51
52	```bash
53	git clone https://github.com/grafbase/nexus
54	cd nexus
55	cargo build --release
56	```
57
58	## Running Nexus
59
60	### Using the Binary
61
62	```bash
63	nexus
64	```
65
66	### Using Docker
67
68	```bash
69	docker run -p 8000:8000 -v /path/to/config:/etc/nexus.toml ghcr.io/grafbase/nexus:latest
70	```
71
72	### Docker Compose Example
73
74	```yaml
75	services:
76	nexus:
77	image: ghcr.io/grafbase/nexus:latest
78	ports:
79	- "8000:8000"
80	volumes:
81	- ./nexus.toml:/etc/nexus.toml
82	environment:
83	- GITHUB_TOKEN=${GITHUB_TOKEN}
84	healthcheck:
85	test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
86	interval: 30s
87	timeout: 10s
88	retries: 3
89	```
90
91	## Configuration
92
93	Create a `nexus.toml` file to configure Nexus:
94
95	```toml
96	# LLM Provider configuration
97	[llm.providers.openai]
98	type = "openai"
99	api_key = "{{ env.OPENAI_API_KEY }}"
100	forward_token = true
101
102	# Model configuration (at least one model required per provider)
103	[llm.providers.openai.models.gpt-4]
104	[llm.providers.openai.models.gpt-3-5-turbo]
105
106	[llm.providers.anthropic]
107	type = "anthropic"
108	api_key = "{{ env.ANTHROPIC_API_KEY }}"
109
110	[llm.providers.anthropic.models.claude-3-5-sonnet-20241022]
111
112	# MCP Server configuration
113	[mcp.servers.github]
114	url = "https://api.githubcopilot.com/mcp/"
115	auth.token = "{{ env.GITHUB_TOKEN }}"
116
117	[mcp.servers.filesystem]
118	cmd = ["npx", "-y", "@modelcontextprotocol/server-filesystem", "/home/YOUR_USERNAME/Desktop"]
119
120	[mcp.servers.python_server]
121	cmd = ["python", "-m", "mcp_server"]
122	env = { PYTHONPATH = "/opt/mcp" }
123	cwd = "/workspace"
124	```
125
126	### Configuration Options
127
128	#### Server Configuration
129
130	- `server.listen_address`: The address and port Nexus will listen on (default: `127.0.0.1:8000`)
131	- `server.health.enabled`: Enable health endpoint (default: `true`)
132	- `server.health.path`: Health check endpoint path (default: `/health`)
133
134	#### LLM Configuration
135
136	- `llm.enabled`: Enable LLM functionality (default: `true`)
137	- `llm.protocols.openai.enabled`: Enable OpenAI protocol endpoint (default: `true`)
138	- `llm.protocols.openai.path`: OpenAI endpoint path (default: `/llm/openai`)
139	- `llm.protocols.anthropic.enabled`: Enable Anthropic protocol endpo

People who liked this also viewed

6 picks

Type