Bring Llm Orchestration
to Pydantic AI
Learn how to connect LibreChat to Pydantic AI and start using 4 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the LibreChat MCP Server?
Connect your LibreChat instance to any AI agent and gain programmatic control over your self-hosted AI ecosystem. This server allows you to bridge your custom agents and models with any MCP-compatible client.
What you can do
- Agent Orchestration — List all available agents and models configured in your LibreChat environment.
- Unified Completions — Create chat completions using the Agents API, providing an OpenAI-compatible interface for your custom setups.
- Open Responses — Utilize the Open Responses API specification to generate structured AI outputs.
- Session Management — Authenticate directly via email and password to retrieve access tokens when a static API key is not preferred.
How it works
- Subscribe to this server
- Provide your LibreChat Base URL and API Key (or use the login tool)
- Start interacting with your private LLM agents through Claude, Cursor, or other MCP tools.
Who is this for?
- AI Engineers — integrate self-hosted LibreChat agents into automated workflows and IDEs.
- DevOps Teams — monitor and query available model configurations across different environments.
- Power Users — centralize access to multiple private LLMs through a single, secure interface.
Built-in capabilities (4)
Model corresponds to an Agent ID. Create a chat completion using the Agents API
List available LibreChat models/agents
Login to LibreChat to get access and refresh tokens
Create a response using the Open Responses API
Why Pydantic AI?
Pydantic AI validates every LibreChat tool response against typed schemas, catching data inconsistencies at build time. Connect 4 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
- —
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
- —
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your LibreChat integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your LibreChat connection logic from agent behavior for testable, maintainable code
LibreChat in Pydantic AI
LibreChat and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect LibreChat to Pydantic AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for LibreChat in Pydantic AI
The LibreChat MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 4 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
LibreChat for Pydantic AI
Every tool call from Pydantic AI to the LibreChat MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How can I see which agents are currently available in my LibreChat instance?
You can use the list_models tool. It will query your configured LibreChat instance and return a list of all accessible agents and models associated with your credentials.
Can I use this server to chat with a specific agent by its ID?
Yes! Use the chat_completions tool. Simply provide the model (which is the Agent ID) and an array of messages to generate a response from that specific agent.
What should I do if I don't have a static API key for my instance?
You can use the login tool. By providing your email and password, the server will authenticate with LibreChat and retrieve the necessary access tokens for subsequent requests.
How does Pydantic AI discover MCP tools?
Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.
Does Pydantic AI validate MCP tool responses?
Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.
Can I switch LLM providers without changing MCP code?
Absolutely. Pydantic AI abstracts the model layer. your LibreChat MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai
Explore More MCP Servers
View all →
Typefully
9 toolsWrite, schedule, and grow your audience on Twitter and LinkedIn with an editor that helps you craft threads that go viral.
UniProt
3 toolsSearch 250M+ protein sequences with functional annotations, gene names, subcellular locations, and amino acid data from the world's most comprehensive protein knowledge base.
HUD User (USPS Crosswalk)
10 toolsMap ZIP codes to Census geographies via HUD User USPS Crosswalk API.
DataScope
6 toolsCreate mobile forms for field inspections, audits, and data collection that work offline and sync when connectivity returns.