mcp-ollama-account-rotation
MCP server that transparently routes Ollama Cloud API requests across multiple user-owned accounts, handling quota exhaustion, rate limits, and failures via automatic account rotation.
README
mcp-ollama-account-rotation
MCP server that transparently routes Ollama Cloud API requests across multiple user-owned accounts, handling quota exhaustion, rate limits, and failures via automatic account rotation.
Architecture
┌──────────────────────────────────────────┐
│ MCP Client │
│ (Claude Code / OpenCode / etc.) │
└─────────────────┬────────────────────────┘
│ MCP Protocol (stdio/SSE)
▼
┌──────────────────────────────────────────┐
│ FastMCP Server │
│ Tools: chat, generate, list_models │
│ Resources: models://, accounts:// │
├──────────────────────────────────────────┤
│ Request Router │
│ select account → forward → classify │
├──────────────────────────────────────────┤
│ Account Manager │ Retry Engine │
│ State Manager │ Health Checker │
│ HTTP Client │ Logger/Metrics │
└──────────────────────────────────────────┘
│
▼
Ollama Cloud API
https://api.ollama.com
Installation
# Prerequisites: Python 3.11+
pip install -e .
# Or with uv:
uv sync
Configuration
Edit data/config.yaml:
ollama_base_url: "https://api.ollama.com"
retry:
max_attempts: 3
backoff_base: 2.0
backoff_max: 60.0
jitter: 0.1
rotation:
strategy: "round_robin"
health:
interval_seconds: 60
timeout_seconds: 10
timeouts:
request_seconds: 60
connect_seconds: 10
logging:
level: "INFO"
format: "json"
output: "console"
Account Setup
Add accounts to data/accounts.json:
{
"accounts": [
{
"email": "user1@example.com",
"api_key": "ollama-api-key-1"
},
{
"email": "user2@example.com",
"api_key": "ollama-api-key-2"
}
]
}
Usage
CLI
# stdio transport (default)
ollama-router
# custom config
ollama-router -c /path/to/config.yaml
# SSE transport
ollama-router --transport sse --port 8000
MCP Client Integration
OpenCode (opencode.json):
{
"mcpServers": {
"ollama-router": {
"command": "ollama-router",
"args": ["-c", "data/config.yaml"]
}
}
}
Claude Code (claude.json):
{
"mcpServers": {
"ollama-router": {
"command": "ollama-router",
"args": ["-c", "data/config.yaml"]
}
}
}
Tools
| Tool | Description |
|---|---|
chat |
Send chat completion request |
generate |
Send text generation request |
list_models |
List available models |
get_account_status |
Show current active account |
get_metrics |
Show server metrics |
Development
# Install dev dependencies
pip install -e ".[dev]"
# Run tests
pytest
# Type checking
mypy app
# Linting
ruff check app
ruff format app
Log Events
| Event | Description |
|---|---|
startup |
Server starts |
shutdown |
Server stops |
account_selected |
Account chosen for request |
account_rotated |
Rotated to different account |
retry_attempt |
Retrying failed request |
account_recovered |
Health check succeeded |
all_accounts_unhealthy |
No healthy accounts |
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.