The Bridge Stack — one stack, every LLM linked
Server Details
OpenAI-compatible BYOK LLM gateway: per-task routing, shadow evaluation, promotion gates.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 3 tools
The three tools target distinct concerns: account/billing status, a promotion-gate verdict, and a per-model scoreboard snapshot. The scoreboard and promotion verdict both deal with model/task_type performance and could be momentarily confused, but the descriptions make the boundary reasonably clear.
All tools use a consistent bridge_ prefix followed by a snake_case noun phrase (account_status, promotion_verdict, scoreboard). Although they are noun-based rather than verb_noun, the convention is uniform and predictable across the entire set.
Three tools is within a reasonable range for a narrow, read-only MCP surface, and each tool maps to a distinct observability need. The count is slightly thin for a platform described as 'one stack, every LLM linked,' but not inappropriate on its own.
The surface is entirely read-only: an agent can check status, read a verdict, and view scores, but cannot perform the central promotion action, which the description explicitly says happens over POST /promote outside the toolset. Other likely needs — listing providers/models, configuring spend caps, or triggering evaluations — are also absent, creating a dead end for the primary workflow.
Available Tools
3 toolsbridge_account_statusAInspect
Your Bridge Stack account: tier, expiry, provider spend, spend cap. Requires your Bearer token.
Inputs: no named parameters.
bridge_promotion_verdictBInspect
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.
Inputs: provider (required), task_type (required).
bridge_scoreboardAInspect
Per-(model, task_type) scoreboard snapshot for your account (Pro tier and above). Requires your Bearer token.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
BYOK AI router & FinOps control plane: audit token waste, check tool safety, and rank models.
OpenAI-compatible LLM gateway: pay per request with an API key, signed receipt for each call.
AI model routing on your own vendor keys: pick the best model per prompt, or route and run it.
Enterprise AI Control Plane: governance, guardrails, spend tracking, compliance & smart routing.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceOpenAI-compatible proxy with PII scrubbing, audit logging, and model routing. Drop-in replacement — set OPENAI_BASE_URL to point to this server. Supports GPT-4o, Claude, Gemini, and Llama via single endpoint.MIT
- FlicenseNot gradedqualityDmaintenanceUnified local MCP AI Gateway that routes across Groq, OpenRouter, Mistral, and local Ollama providers, with OpenAI-compatible APIs, MCP tools, fallback/racing router, monitoring, and web dashboard.-
- AlicenseAqualityBmaintenanceCentralized encrypted gateway that routes requests to 11+ LLM providers (API keys and CLI subscriptions) through a single OpenAI-compatible endpoint, with MCP tools for vault operations, code search, and shared state.302MIT
- AlicenseNot gradedqualityDmaintenanceUniversal MCP router and gateway that bridges LLM agents to OpenAPI, GraphQL, and AWS Lambda services with ISO/IEC 42001 AI governance, RBAC, PII redaction, semantic tool routing, and a web dashboard.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.