Feature · Agent panel

Bring your own model. Watch every tool call it makes.

MCPOrbit's Agent panel runs against any model provider you have credentials for — eight ship today, three of them local. Point it at a connected MCP server and it drives real tool calls, showing you each one inline as the model makes it.

Providers

Eight providers, one panel.

AnthropicOpenAIOpenRouterBedrockGroqOllamaLM StudioAny OpenAI-compatible

Anthropic

Native Claude support, including the latest Opus and Sonnet.

OpenAI

GPT-5, GPT-5 Mini, the o-series reasoning models.

OpenRouter

One key, every router-supported model. Useful for cheap exploration.

AWS Bedrock

Claude, Llama, Mistral models hosted on Bedrock with your AWS credentials.

Groq

Sub-50ms first-token latency on Llama and Mixtral. Fast iteration.

Ollama

Fully local. Pull a model once; run it with no network.

LM Studio

Local model server with a GUI. Pair with MCPOrbit when you want both UIs.

Any OpenAI-compatible

Custom endpoint, custom model. Behind your VPC, in your test cluster, wherever.

Tool calls

You choose what the model is allowed to touch.

A connected server can expose dozens of tools. Before you run anything, tick the ones this session is allowed to call and leave the rest off. The agent works through up to ten provider round-trips per answer, and every tool call it makes is rendered inline with the exact arguments it sent — so when a model picks the wrong tool, you see which one and why.

  • Per-tool switches — enable only the tools this run should reach
  • Every call shown inline, with the arguments the model actually sent
  • Up to ten round-trips per answer, each one visible

agent · linear-mcp · tool calls

>

tools/call list_issues

args: team: 'ENG', state: 'started', limit: 20

>

tools/call update_issue

args: id: 'ENG-412', assignee: 'me'

Local-first

Plug Ollama or LM Studio in. Run the agent fully offline.

Useful when the MCP servers you're testing handle data you'd rather not put through a hosted model. Same agent UI, different runtime — against an air-gapped MCP server if you want.

  • No network needed for inference
  • Bring an air-gapped MCP server in too
  • Same agent UI, different runtime

Agent · local

Ollama · llama-3.3-70b

> tools/call list_files { path: '/private/notes' }

no networkno cloudyour machine only

Agent panel FAQ

Where do I put my API keys?

Locally, in MCPOrbit's settings. Keys never leave your machine. There is no cloud account.

Do you store my prompts or responses?

No. Telemetry, when shipped, never includes payloads — only metadata. The full schema is on /privacy/telemetry once that pipeline goes live.

Does the agent call tools automatically?

Yes, within the limits you set. Only the tools you tick are callable, and each call is shown inline with its arguments before you act on the result.

Multi-server agent runs?

Single-server agent runs ship today. Multi-server orchestration in one session is on the roadmap.

MCPOrbit

Test an MCP server in 60 seconds.

Download MCPOrbit for free — no account, no telemetry. Hear about a server and test it before the curiosity wears off.

macOS 14+ · Apple Silicon & Intel · No account needed