MCP server for Claude Code — multi-AI orchestration across local + cloud LLMs, intelligent backend routing, council-driven workflows, and
MCP server for Claude Code — multi-AI orchestration across local + cloud LLMs, intelligent backend routing, council-driven workflows, and token-saving file
Smart AI Bridge is an MCP server that sits between Claude Code and your AI backends. It provides 18 tools for token-saving file operations, multi-AI workflows, code quality checks, and intelligent routing -- all configured through a single JSON file.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| analyze_file | Backend reads and analyzes files, returns structured findings |
| modify_file | Backend applies natural-language edits, returns diff |
| batch_analyze | Analyze multiple files via glob patterns; grepFilter narrows by content first, singlePass answers in one call |
| batch_modify | Apply same instructions across multiple files |
| generate_file | Generate code from a natural-language spec |
| explore | Answer codebase questions using intelligent search |
| ask | Smart routing with auto or forced backend selection |
| council | Multi-AI consensus across configurable backends |
| dual_iterate | Generate, review, fix loop between two backends |
| parallel_agents | TDD workflow with decomposition and quality gates |
| spawn_subagent | Specialized AI agents (10 roles including TDD) |
| review | Security, performance, and quality review |
| refactor | Cross-file refactoring with reference updates |
| check_backend_health | Health diagnostics for specific backends |
| backup_restore | Timestamped backup management |
| write_files_atomic | Atomic multi-file writes with backup |
| get_analytics | Usage analytics and optimization recommendations |
{
"mcpServers": {
"smart-ai-bridge": {
"command": "node",
"args": [
"/absolute/path/to/smart-ai-bridge/src/server.js"
],
"env": {
"NVIDIA_API_KEY": "YOUR_NVIDIA_API_KEY"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
| Variable | Description | Required |
|---|---|---|
| NVIDIA_API_KEY | Declared in the maintainer’s client configuration. | Check documentation |
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.
AWS Labs' official server suite — current AWS docs, CDK guidance, cost analysis and service tools.
Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.
Workers, KV, R2 and D1 by conversation — Cloudflare's official remote servers for building and observability.
Dashboards, Prometheus and Loki queries, incidents and alerts — observability by conversation.
kubectl with a conversational interface — inspect pods, read logs, diagnose clusters and manage workloads.