Multi Provider Schema Output Agent
MCP server that returns schema-validated LLM output across multiple model providers
- Platforms
- API
- Runs
- Remotely
- Version
- 1.0.0
- Listing updated
- today
Similar MCP servers
About Multi Provider Schema Output Agent
Multi Provider Schema Output Agent 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 points to a remote MCP endpoint and an A2A agent card for a service that combines the instructor and litellm libraries. Based on its site, the service is built to request structured output from language models and route calls across several providers through one interface.
According to its website, the agent is exposed both as an A2A agent and as an MCP endpoint at a streamable HTTP address, and it is also listed on Smithery. The site does not spell out the individual tools it exposes, supported models, or how requests are authenticated.
It suits developers who want typed, schema-constrained responses from different LLM vendors without writing separate client code for each one. The site includes a governance section and links to a related portfolio of agents from the same vendor.
Install
Run in a terminal
claude mcp add --transport http multi-provider-schema-output-agent https://instructor-litellm-6af681.getvda.ai/mcpAdd to Settings → Connectors → Add custom connector
https://instructor-litellm-6af681.getvda.ai/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"multi-provider-schema-output-agent": {
"url": "https://instructor-litellm-6af681.getvda.ai/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"multi-provider-schema-output-agent": {
"type": "http",
"url": "https://instructor-litellm-6af681.getvda.ai/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"multi-provider-schema-output-agent": {
"serverUrl": "https://instructor-litellm-6af681.getvda.ai/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"multi-provider-schema-output-agent": {
"type": "http",
"url": "https://instructor-litellm-6af681.getvda.ai/mcp"
}
}
}Using several servers? Build one config file with the MCP config generator.
What it does
- Structured output
- Targets responses that conform to a caller-supplied schema, built on the instructor library.
- Multi-provider routing
- Uses litellm to reach several LLM providers through a common calling layer.
- MCP endpoint
- Offers a streamable HTTP MCP endpoint that AI clients can connect to.
- A2A agent card
- Publishes an Agent2Agent card so other agents can discover and call it.
Good for
- Getting typed JSON responses from LLMs for downstream parsing
- Comparing structured outputs across different model providers
- Connecting an MCP-capable AI client to schema-constrained generation
Multi Provider Schema Output Agent FAQ
Is there an MCP endpoint I can connect to?
Yes, the registry entry and the website both list a streamable HTTP MCP endpoint.
Which libraries does it use?
The website says it composes instructor and litellm.
How do I add Multi Provider Schema Output Agent to Claude Code?
Run this command in your terminal: claude mcp add --transport http multi-provider-schema-output-agent https://instructor-litellm-6af681.getvda.ai/mcp
What are the best alternatives to Multi Provider Schema Output Agent?
The closest alternatives to Multi Provider Schema Output Agent are Structured Output Agent Openai, Structured Output Agent, Structured Output Agent C2ddcc, Traced Multi Llm Proxy and Llm Orchestration Agent MCP.
Where this comes from
- Description: written from the project's website and its MCP Registry entry.
- Install steps: from the official MCP Registry entry.