OpenAI-compatible BYOK LLM gateway: per-task routing, shadow evaluation, promotion gates.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Your Bridge Stack account: tier, expiry, provider spend, spend cap. Requires your Bearer token.
This tool takes no arguments.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
claude mcp add --transport http llm-bridge-stack https://textforagents.com/products/llm-bridge-stack/mcp
Your Bridge Stack account: tier, expiry, provider spend, spend cap. Requires your Bearer token.
No arguments.
{
"type": "object",
"properties": {}
}Promotion-gate verdict (INSUFFICIENT / UNDECIDED / READY) for a candidate provider on a task type. Read-only: promotion itself happens over POST /promote. Requires your Bearer token.
| Argument | Type | Description |
|---|---|---|
| provider* | string | |
| task_type* | string |
{
"type": "object",
"required": [
"provider",
"task_type"
],
"properties": {
"provider": {
"type": "string"
},
"task_type": {
"type": "string"
}
}
}Per-(model, task_type) scoreboard snapshot for your account (Pro tier and above). Requires your Bearer token.
No arguments.
{
"type": "object",
"properties": {}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 2, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.