Traced Claude Format Guard
MCP server wrapping Claude calls with structured-output enforcement and tracing
- Platforms
- API, Web
- Runs
- Remotely
- Version
- 1.0.0
- Listing updated
- today
Similar MCP servers
About Traced Claude Format Guard
Traced Claude Format Guard is an MCP server for ai models and llm tooling. It runs as a hosted remote server, so there is nothing to install locally.
The README-free listing is built from the product's own landing page and its MCP registry entry. The page describes a service that combines the Anthropic client, lm-format-enforcer and OpenTelemetry tracing, exposed over an MCP endpoint and an A2A agent card. The page also says it is listed on Smithery and links to a portfolio of agents from the same publisher.
According to the registry entry, the server is reached over streamable HTTP at a hosted remote URL, with no local packages published. The page does not list individual tool names, pricing, or licence terms, so those details are left out here.
It is most relevant to developers who want Claude outputs constrained to a required format and want traces of those calls for observability.
Install
Run in a terminal
claude mcp add --transport http traced-claude-format-guard https://traced-llm-proxy-anthropic.getvda.ai/mcpAdd to Settings → Connectors → Add custom connector
https://traced-llm-proxy-anthropic.getvda.ai/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"traced-claude-format-guard": {
"url": "https://traced-llm-proxy-anthropic.getvda.ai/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"traced-claude-format-guard": {
"type": "http",
"url": "https://traced-llm-proxy-anthropic.getvda.ai/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"traced-claude-format-guard": {
"serverUrl": "https://traced-llm-proxy-anthropic.getvda.ai/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"traced-claude-format-guard": {
"type": "http",
"url": "https://traced-llm-proxy-anthropic.getvda.ai/mcp"
}
}
}Using several servers? Build one config file with the MCP config generator.
What it does
- Structured output enforcement
- Constrains Claude responses to a required format using lm-format-enforcer, according to the page.
- OpenTelemetry tracing
- Instruments calls with OpenTelemetry API and SDK components for observability.
- Streamable HTTP MCP endpoint
- Exposes an MCP endpoint over streamable HTTP at a hosted remote URL.
- A2A agent card
- Publishes an Agent Card for Agent2Agent protocol discovery.
Good for
- Getting Claude to return JSON or other fixed-format output for downstream code
- Tracing LLM calls made through an MCP client for debugging and monitoring
- Adding a format-constrained Claude step to an agent workflow over MCP
Traced Claude Format Guard FAQ
How do I connect to this MCP server?
The registry entry lists a streamable HTTP remote at the /mcp path of the product's hosted domain.
Is it open source?
The page and registry entry do not state a licence or source repository.
How do I add Traced Claude Format Guard to Claude Code?
Run this command in your terminal: claude mcp add --transport http traced-claude-format-guard https://traced-llm-proxy-anthropic.getvda.ai/mcp
What are the best alternatives to Traced Claude Format Guard?
The closest alternatives to Traced Claude Format Guard are Structured Output Agent C2ddcc, Traced Llm MCP Proxy, Structured Output MCP Traced Agent, Tracelane MCP and Traced Openai Langchain Agent.
Where this comes from
- Description: written from the project's website and its MCP Registry entry.
- Install steps: from the official MCP Registry entry.