A2A GOSCE Agents
This server provides a portfolio of AI agents accessible via the A2A (Agent-to-Agent) protocol, covering LLM orchestration, authentication, observability, and infrastructure generation. A central GOSCE Portfolio Router discovers and routes requests to verified agents by capability.
Available agents:
Structured Output (
structured-output-agent): Convert a prompt and field schema into validated, typed JSON using Instructor over Gemini on Vertex AI.Traced LLM Proxy (
traced-llm-proxy): Proxy Gemini completions wrapped in OpenTelemetry trace spans, returning the answer along with a trace/span ID.Authenticated Multi-LLM Agent (
authenticated-multi-llm-agent): Google OAuth-gated LLM gateway that verifies a Google ID token before running a Gemini completion.Auth Token Service (
auth-token-service): Hash passwords with bcrypt and issue/verify JWT session tokens.LLM Orchestration Agent (
llm-orchestration-agent): Run prompts through a LangChain chain over Gemini on Vertex AI, with optional LangSmith tracing.LLM Observability & Orchestration (
llm-observability-orchestration): Same as above, with added observability support.Authenticated LLM Agent (
authenticated-llm-agent): JWT-gated gateway that authenticates via bcrypt/JWT before running a LangChain Gemini completion; unauthenticated calls are rejected.Authenticated MCP Agent (
authenticated-mcp-agent): Same as above but MCP-enabled.GOSCE Portfolio Router (
gosce-portfolio-router): Routes requests to the appropriate agent based on capability, providing quality-assured brokering across the entire portfolio.Infrastructure Stack Generation: Generate compose configurations for common backend services (Postgres, Redis, MySQL, MongoDB, Kafka, Prometheus, MinIO, RabbitMQ, Grafana, Nginx, etc.).
Generates Docker Compose stacks that include Adminer for database management alongside MySQL and Redis.
Provides authentication via Google OAuth for LLM agents, verifying Google ID tokens for secure access.
Generates Docker Compose stacks that include Grafana for monitoring and visualization alongside Postgres.
Generates Docker Compose stacks that include MinIO object storage, often combined with Redis, Postgres, or Kafka.
Generates Docker Compose stacks that include MongoDB along with Memcached and Redis.
Generates Docker Compose stacks that include MySQL, often combined with Redis and other services like Adminer or Nginx.
Generates Docker Compose stacks that include Nginx as a reverse proxy alongside MySQL and Redis.
Generates a backend stack for Observable, providing monitoring and observability tools.
Generates Docker Compose stacks that include Prometheus for monitoring, often combined with Postgres and Kafka.
Generates Docker Compose stacks that include RabbitMQ message broker alongside Redis.
Generates Docker Compose stacks that include Redis, combined with various other databases and services for caching and messaging.
GOSCE Agents
A portfolio of production remote MCP + A2A agents running on getvda.ai, discovered + quality-assured by the GOSCE Portfolio Router. Each agent is capability-scoped, speaks open A2A + MCP, and is metered with Nevermined x402 micropayments (discovery is free).
Generated by GOSCE (GitHub Open-Source Combination Engine) — an automated pipeline that mines the OSS dependency graph for monetizable package combinations and deploys each as a verified agent.
Agents
Agent | Capability | Docs |
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
LLM Observability & Orchestration Agent (LangChain Community) |
| |
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
Elasticsearch + MongoDB + Redis Stack Generator (Elasticsearch/Elasticsearch) |
| |
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
LLM Orchestration Agent (Opentelemetry Instrumentation Fastapi) |
| |
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
RabbitMQ + Elasticsearch + Postgres Stack Generator (Elasticsearch/Elasticsearch) |
| |
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
| ||
|
Related MCP server: Stackbilt
Entry point
Query the Portfolio Router for any capability — it returns the matching verified agent's endpoint, Agent Card, and a real example output from its own health probe.
Portfolio: https://getvda.ai/agents
Router: https://router.getvda.ai
Available Tools
9 toolsauthenticated-llm-agentAInspect
JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion. Unauthenticated calls are rejected.
Inputs: input (required).
authenticated-mcp-agentAInspect
JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion. Unauthenticated calls are rejected.
Inputs: input (required).
authenticated-multi-llm-agentBInspect
Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.
Inputs: input (required).
auth-token-serviceBInspect
Hash passwords with bcrypt and issue/verify JWT session tokens.
Inputs: input (required).
gosce-portfolio-routerAInspect
Single entry point for the GOSCE portfolio: routes orchestrators to verified agents by capability, with real example output from the router's own /selftest probes (a quality-assured broker, not a directory).
Inputs: input (required).
llm-observability-orchestrationBInspect
Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.
Inputs: input (required).
llm-orchestration-agentCInspect
Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.
Inputs: input (required).
structured-output-agentAInspect
Turn a prompt + a field schema into validated, typed JSON (Instructor over Gemini 2.5 Flash on Vertex AI).
Inputs: input (required).
traced-llm-proxyAInspect
Proxy Gemini (Vertex AI) completions wrapped in OpenTelemetry trace spans; returns the answer plus the trace/span id.
Inputs: input (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 9 tools
Two pairs of tools have identical descriptions (authenticated-llm-agent/authenticated-mcp-agent and llm-observability-orchestration/llm-orchestration-agent), making them nearly indistinguishable. Only the router, auth service, structured output, and traced proxy have clear distinct purposes.
Names use hyphens but no consistent prefix or verb-noun pattern. 'authenticated-llm-agent' vs 'authenticated-mcp-agent' are confusingly similar, and the duplicate pairs exacerbate the inconsistency.
At 9 tools, the count is reasonable for a server focused on LLM agents with authentication and tracing. However, the redundancy makes the effective set smaller, but the raw count is not problematic.
The tool set covers user authentication, LLM calls, and tracing, but has significant gaps: no simple non-authenticated LLM call, no user management, and multiple tools overlap without adding distinct capabilities. The purpose of the server is unclear.
Maintenance
Related MCP Connectors
Independent directory of agentic AI tools — search, compare & recommend via MCP. Read-only.
Structured Output MCP Agent (Instructor)
Patterns for designing and reviewing AI skills, agents, and multi-agent workflows. Find guidance on context economy, delegation, verification, and tool design; inspect claims, worked examples, maturity labels, and source references. Five read-only tools let agents discover relevant patterns, compare concise cards, read specific sections, and explore relationships. Hosted Streamable HTTP at https://agentic-atlas.dev/mcp/ — no installation, account, or API key required. Browse the atlas at https://agentic-atlas.dev/.
One MCP endpoint for Claude, GPT & Gemini: 100+ tools + no-code connectors + agent workers.
Related MCP Servers
- AlicenseNot gradedqualityNot gradedmaintenanceA high-performance Go-based MCP server that provides a microservice architecture for orchestrating diverse tools through gRPC and HTTP/REST APIs. Enables seamless integration of language-agnostic tools including ML capabilities, web search, calculations, and human interaction for intelligent agent workflows.2-
- AlicenseNot gradedqualityAmaintenanceWe built a hosted MCP server that gives AI agents two capabilities through a single connection: 1. img-forge — Image generation across 5 quality tiers (SDXL Lightning to Gemini 3.1 Flash). One tool call, 5-30 seconds, done. 2. Stackbilder — Full-stack architecture scaffolding. Describe a product, get a 6-mode pipeline (Product → UX → Risk → Architect → TDD → Sprint)MIT
- AlicenseAqualityFmaintenanceScore your agent's governance (0-100), lint MCP tool definitions, and estimate costs across all major models. Free diagnostic tools with no API key needed. Expert skill files on governance, economics, and system architecture available with free tier.81MIT
- AlicenseAqualityCmaintenanceAgent Toolbelt is an MCP server exposing 11 focused API tools for LLM agents — schema generation, text extraction, token counting, CSV conversion, Markdown conversion, URL metadata, regex builder, cron expressions, address normalization, color palettes, and brand kits. Each tool is a focused microservice with structured input/output, WCAG-scored color data, USPS address parsing, and multi-model to2521 npm1MIT