Skip to content

Your agent. Your workspace. · Page 6

Connect through MCP, sign in once, and bring source-backed research into the tools you already use. Browse page 6 of 7.

Integrations

One connection. A real first result.

Add the server, sign in and approve, then verify your workspace connection. No key to copy for an OAuth-capable agent.

Integrations

Choose the OpenAI Agents SDK Montage execution boundary

Before adapting connection code, decide whether the application or Responses API should execute remote tools.

Read guide
Integrations

Separate OpenAI service credentials from Montage authorization

An application can authenticate successfully to OpenAI while having no approved Montage account access.

Read guide
Integrations

Review OpenAI Agents SDK local MCP connection lifetime

A locally controlled SDK connection must stay valid while its discovered tools are used.

Read guide
Integrations

Review Montage tool approval before an OpenAI Agents SDK run

A remote tool being available to an SDK agent does not mean its effects were approved.

Read guide
Integrations

Review Pydantic AI MCPToolset generation before adapting Montage

Pydantic AI examples from different API generations should not be mixed into one application.

Read guide
Integrations

Isolate Pydantic AI Montage authorization by user session

A Pydantic AI toolset can wrap an authorized FastMCP client, but it must not become a vehicle for sharing one user’s workspace access with others.

Read guide
Integrations

Keep Pydantic AI Montage tools inside their async lifetime

A discovered tool can depend on a client that closes before the Agent ever uses it.

Read guide
Integrations

Gate Pydantic AI Agent tool use on a direct Montage read

Attaching a toolset is not the same as proving an authorized account can execute it.

Read guide
Integrations

Review LlamaIndex tool filtering for a Montage status diagnostic

A LlamaIndex application can discover many remote tools when it needs only one preliminary read.

Read guide
Integrations

Review a LlamaIndex custom ClientSession authorization boundary

LlamaIndex documents custom ClientSession integration, but it is an extension point rather than a shortcut around protocol initialization or account authorization.

Read guide
Integrations

Move LlamaIndex Montage tool use into the HTTP client lifetime

LlamaIndex discovery helpers can make remote tools look like ordinary reusable objects.

Read guide
Integrations

Produce a LlamaIndex status receipt without a retrieval or agent run

A notebook can display a discovered tool list and still have no successful Montage workspace call.

Read guide
Integrations

Select Semantic Kernel’s Python Streamable HTTP plugin for Montage

Semantic Kernel’s main MCP example may show SSE, which is not the hosted transport used here.

Read guide
Integrations

Review Semantic Kernel plugin authorization independently of model access

Semantic Kernel may have valid model-service configuration while its Montage plugin lacks authorized account access.

Read guide
Integrations

Keep Semantic Kernel Montage functions within the plugin lifetime

Discovered kernel functions can outlive the remote plugin that supplied them if application cleanup is misplaced.

Read guide
Integrations

Review Montage function exposure before a Semantic Kernel model run

Adding MCP functions to a kernel can broaden what a model may propose.

Read guide
Integrations

Select an installed MCP Inspector interface without downloading tools

Inspector examples can invoke package runners that fetch dependencies automatically.

Read guide
Integrations

Separate Inspector proxy access from Montage authorization

Inspector may have a protected local proxy as well as a remote Montage account challenge.

Read guide
Integrations

Trace Montage initialization discovery and execution in MCP Inspector

A failed MCP workflow may break during initialization, discovery or tool execution.

Read guide
Integrations

Prepare a secret-safe Montage status handoff from MCP Inspector

Inspector is useful for handing protocol evidence to another engineer, but raw transcripts may contain local proxy or account secrets.

Read guide
Integrations

Distinguish FastMCP client construction from an active Montage session

A FastMCP Client object can be constructed before the application ever establishes a usable remote session.

Read guide
Integrations

Review FastMCP OAuth storage before serving multiple Montage users

FastMCP can supply direct remote access without a model, but private OAuth state must remain tied to its owner.

Read guide
Integrations

Handle a FastMCP Montage call failure without leaking its client lifetime

A failed direct call should leave an explicit error and a properly released client, not a reusable-looking success object.

Read guide
Integrations

Inspect the FastMCP Montage tool contract before direct execution

A direct FastMCP diagnostic can stay narrower than an agent workflow while still checking the actual remote contract.

Read guide

Know what social media shows about you.
Start with a question.

Get started
montage