Hosted MCP server · #127 most used on Smithery
LangSmith Traced OpenAI Agent
a2a/llm-orchestration-agent
LangSmith Traced OpenAI Agent: composes langchain-core + langchain-openai + langsmith + openai — orchestration, observability, llm-client via A2A + MCP.
- Uses
- 4.2k
- Tools
- 2
- Runs
- Hosted
- Listed
- 5mo ago
Get started
Add it to your agent
npx -y @smithery/cli@latest install a2a/llm-orchestration-agent --client claudeSwap --client claude for cursor, vscode, windsurf or another client. The CLI asks for any required settings.
claude mcp add --transport http langsmith-traced-openai-agent https://server.smithery.ai/a2a/llm-orchestration-agent/mcpA hosted server: nothing to install. Run /mcp in Claude Code to sign in if it asks.
[mcp_servers.langsmith-traced-openai-agent]
url = "https://server.smithery.ai/a2a/llm-orchestration-agent/mcp"Add to ~/.codex/config.toml.
{
"mcpServers": {
"langsmith-traced-openai-agent": {
"url": "https://server.smithery.ai/a2a/llm-orchestration-agent/mcp"
}
}
}Add to ~/.cursor/mcp.json.
{
"servers": {
"langsmith-traced-openai-agent": {
"type": "http",
"url": "https://server.smithery.ai/a2a/llm-orchestration-agent/mcp"
}
}
}Add to .vscode/mcp.json.
gemini mcp add --transport http langsmith-traced-openai-agent https://server.smithery.ai/a2a/llm-orchestration-agent/mcpSaved to .gemini/settings.json.
What it can do
2 tools
invoke1 paramRun a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.
| Parameter | Type | Description |
|---|---|---|
input | string | JSON request for this capability (the same body you'd send as an A2A message). |
selftestFREE, no payment required. Runs this agent's real capability on a fixed canned input and returns the genuine result, an honest assertion …
FREE, no payment required. Runs this agent's real capability on a fixed canned input and returns the genuine result, an honest assertion grade, and the full trust manifest (signed Agent Card, JWKS, governance/licence chain, safety posture) with a proof link for every claim. Intended for registries, graders and auditors: this is behavioural evidence, not a self-description.