TrueFoundry

TrueFoundry MCP Connector for Claude

A+

Universal LLM Gateway & ML deployment hub: invoke 1000+ proxy models and manage MCP service instances natively.

8 tools Official Updated Jun 28, 2026 Official Vinkius Partner

What you can do

Connect AI agents to TrueFoundry's dual-architecture matrix encompassing both an AI Gateway and a Deployment Orchestrator:

  • Route LLM prompts securely utilizing a unified endpoint connecting to OpenAI, Anthropic, Gemini, Llama, and more
  • Manage LLM Embeddings mapping strings flawlessly through secure unified channels
  • Discover Gateway Models identifying exact runtime limitations and contexts
  • Orchestrate MCP Containers deploying new AI server topology straight onto infrastructure limits
  • Monitor Active Deployments generating status, usage array metrics, and isolation limits natively
  • List MCP Schemas utilizing the managed TrueFoundry MCP discovery engine array
  • Execute Chat streams dynamically routing user contexts purely bound without touching distinct API keys

How it works

  1. Generate your TrueFoundry credentials fetching your Personal Access Token from settings
  2. Identify your dedicated cluster URL (your exclusive TrueFoundry endpoint domain)
  3. Request inference executions bounding strictly the proxy routes, completely isolating original vendor APIs from your codebase
  4. Govern deploy processes natively bypassing complex container matrix orchestrations

Who is this for?

Essential for Platform Operations teams, AI Engineers, and Software Architects desiring an integrated hub that strips out the N-by-M fragmentation of multiple LLM pipelines and multiple MCP tool servers into a single secure plane.

llm-gatewaymodel-orchestrationml-deploymentai-infrastructureapi-proxy

8 tools expose this connector's capabilities to your AI agent.

truefoundry_deploy_mcp_server

Spawn a new backend container logical process using TrueFoundry service mesh

truefoundry_generate_embeddings

Calculate semantic vectors securely using the unifed abstraction

truefoundry_get_deployment_status

Emit detailed metric states on the orchestration matrix bounds

truefoundry_get_mcp_server_info

Extract exact JSON metadata of one registered TrueFoundry tool schema

truefoundry_list_deployments

Monitor the existing array of running backend topologies mapped to the team

truefoundry_list_gateway_models

List all accessible foundation models from the TrueFoundry unified AI gateway

truefoundry_list_mcp_servers

Extract registry mapping of all available logical MCP Tools in TrueFoundry

truefoundry_run_gateway_chat

g., openai/gpt-4o) mapping the true chat parameter to the gateway. Perform inference explicitly pushing a model query string through TrueFoundry

See how to talk to your AI agent using TrueFoundry.

List all active AI models supported natively inside my TrueFoundry gateway access instance.

Executing `list_gateway_models` cleanly... Extracted dynamic boundaries resolving exactly 23 natively available providers including OpenAI and Cohere. Fetching strict context limits matrix sequentially.

Trigger a chat payload pushing to 'openai-gpt4o' via TrueFoundry querying semantic structures bounding limits.

Generating structured call via `run_gateway_chat`. The backend relayed proxy safely isolating original network keys. Response received indicates valid bounding states matching flawlessly.

Deploy the 'supabase-mcp' node-image natively mapping strict variables onto my cluster runtime boundaries.

Processing native cluster allocation bounding resources via `deploy_mcp_server`. Configuration schemas synced into TrueFoundry engine cleanly. Running logs verify successful execution state bounds mapped efficiently.

Yes! You can orchestrate inferences parsing `run_gateway_chat` providing dedicated string formats mapping natively any enabled model.

Related Connectors