This is a JWT-authenticated gateway to Google Vertex AI's Gemini model via LangChain. You send credentials (bcrypt-hashed), get a token, then fire completion requests through the authenticated endpoint. It's part of the GOSCE automated agent portfolio, where each server is capability-scoped and metered with Nevermined micropayments. Reach for this when you need to wrap Gemini calls behind auth without building the bcrypt and JWT plumbing yourself. The router at router.getvda.ai lets you query by capability and returns live health checks, so you can verify the agent is up before integrating.
Public tool metadata for what this MCP can expose to an agent.
invokeJWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion. Unauthenticated calls are rejected.1 paramsJWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion. Unauthenticated calls are rejected.
inputstringA 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.
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.
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent
fradser/mcp-server-mas-sequential-thinking