Traced Llm Proxy
io.github.mikerawsonnzPublished by GitHub account mikerawsonnzv1.0.0Updated Oct 24, 2026
Proxy Gemini (Vertex AI) completions wrapped in OpenTelemetry trace spans; returns the answer plus t
Overview
A remote MCP agent that proxies Gemini (Vertex AI) completions wrapped in OpenTelemetry trace spans, returning the answer with trace data.
- What you can do
- Send prompts to Gemini (Vertex AI) through the proxy and get completions back wrapped in OpenTelemetry trace spans, so the answer arrives alongside its trace information. The README describes it as one capability-scoped agent in a larger portfolio of remote MCP and A2A agents, with a router that returns matching agent endpoints and example outputs. No individual tools are listed in the manifest, so the exact tool set is not documented here.
- When to use it
- When you want an assistant to call Gemini (Vertex AI) completions and receive OpenTelemetry trace spans with the result, for example to inspect or record tracing around LLM calls.
- Requirements
- A remote streamable HTTP endpoint; no local runtime, packages, environment variables or headers are declared. The README states agents are metered with Nevermined x402 micropayments, so payment handling is likely needed for use beyond free discovery.
Installation
In SourceWeft
- Open Traced Llm Proxy in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.mikerawsonnz%2Ftraced-llm-proxy/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"traced-llm-proxy": {
"type": "http",
"url": "https://anthropic-mcp-opentelemetry-api-264025.getvda.ai/mcp"
}
}
}README
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
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
Source: README.md at commit 2e82345
Tools
0Version history
1- v1.0.0LatestSep 16, 2026
Score
85% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
- Auth declaredRequired10 pts
- Tools listedRequired15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts