# The Bridge Stack — one stack, every LLM linked

> The Bridge Stack — one stack, every LLM linked is an MCP server for ai models and llm tooling. OpenAI-compatible BYOK LLM gateway with per-task routing and shadow testing. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Free trial
- **Starting price:** $5 a month
- **Platforms:** API
- **Website:** https://textforagents.com/products/llm-bridge-stack/
- **MCP Registry name:** com.textforagents/llm-bridge-stack
- **Categories:** AI models and LLM tooling
- **Listing updated:** 2026-11-15

## About

The Bridge Stack sits between your application and your own model-provider keys. You send standard chat-completion requests to one endpoint, and it chooses which model serves each type of task based on measured fitness. A candidate model only takes over a task type after a READY promotion verdict, and until then the incumbent keeps serving.

Sign-up is API-driven rather than a web form: you register with a name and payer wallet, claim a one-time free trial month by signing a challenge with that wallet, or subscribe by paying over x402. You then store your provider keys with a PUT to /providers. The vendor states it holds no provider keys for customer traffic and fronts no inference spend.

The tiers add capability. The base tier covers routing and adapters, Pro adds per-task scoreboards and paper-mode shadow evaluation on your own traffic, and Fleet adds promotion gates, spend rails, rationale audit trails and reconciliation. It is published by TextForAgents LLC.

## Features

- **Per-task model routing:** Routes each task type to a model by measured fitness.
- **Shadow evaluation:** Tests candidate models on your own traffic in paper mode (Pro tier).
- **Promotion gates:** A candidate serves a task only after a READY verdict (Fleet tier).
- **OpenAI-compatible endpoint:** Call POST /v1/chat/completions with a bearer token.
- **Bring your own keys:** Provider keys stay yours; the company fronts no spend.
- **Wallet-based billing:** Trial claim and subscription use a payer wallet and x402 payments.

## Good for

- Route different task types to different models without changing client code
- Test a cheaper model on real traffic before switching
- Add audit trails and spend rails to multi-model usage
- Keep one OpenAI-style endpoint across several providers

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http llm-bridge-stack https://textforagents.com/products/llm-bridge-stack/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://textforagents.com/products/llm-bridge-stack/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "llm-bridge-stack": {
      "url": "https://textforagents.com/products/llm-bridge-stack/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "llm-bridge-stack": {
      "type": "http",
      "url": "https://textforagents.com/products/llm-bridge-stack/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "llm-bridge-stack": {
      "serverUrl": "https://textforagents.com/products/llm-bridge-stack/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "llm-bridge-stack": {
      "type": "http",
      "url": "https://textforagents.com/products/llm-bridge-stack/mcp"
    }
  }
}
```

## FAQ

### What does it cost?

A one-time free first month, then $5 per month for routing and adapters, $19 for Pro and $39 for Fleet.

### Does it supply model access?

No. It is bring-your-own-keys only, and a company-fronted spend lane is not offered.

### How does a trial work?

You register, then sign a challenge with your wallet to claim the one-time trial; it is limited to one per operator.

### When does a new model start serving?

Only after a READY promotion verdict for that task type; the incumbent serves by default.

### Is The Bridge Stack — one stack, every LLM linked free?

The Bridge Stack — one stack, every LLM linked is a paid product with a free trial. Paid plans start at $5 a month.

### How do I add The Bridge Stack — one stack, every LLM linked to Claude Code?

Run this command in your terminal: claude mcp add --transport http llm-bridge-stack https://textforagents.com/products/llm-bridge-stack/mcp

### What are the best alternatives to The Bridge Stack — one stack, every LLM linked?

The closest alternatives to The Bridge Stack — one stack, every LLM linked are Claude Code Ultimate Guide, signafAIde, Toolkien, Lugh and HypePaper.

## Alternatives

- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [signafAIde](https://ai-powered.com/mcp/signafaide): signafAIde is a freemium MCP server for security.
- [Toolkien](https://ai-powered.com/mcp/toolkien): Toolkien is an open-source MCP server for ai models and llm tooling.
- [Lugh](https://ai-powered.com/mcp/lugh): Lugh is an open-source MCP server for ai models and llm tooling.
- [HypePaper](https://ai-powered.com/mcp/hypepaper): HypePaper is a freemium MCP server for ai models and llm tooling.
- [Agent Data Tools: Compact (find, describe, run)](https://ai-powered.com/mcp/agent-data-tools-compact-find-describe-run): Agent Data Tools: Compact (find, describe, run) is a freemium MCP server for developer tools.
- [Angel Agent Guard: pre-purchase check + prompt-injection scan](https://ai-powered.com/mcp/angel-agent-guard-pre-purchase-check-prompt-injection-scan): Angel Agent Guard: pre-purchase check + prompt-injection scan is a freemium MCP server for ai models and llm tooling.
- [Mizan Calibration](https://ai-powered.com/mcp/mizan-calibration): Mizan Calibration is a free MCP server for ai models and llm tooling.

---
Source: https://ai-powered.com/mcp/the-bridge-stack-one-stack-every-llm-linked
