Skip to integration content

How to integrate Unify with Gemini

The proposed Unify and Gemini integration uses a custom connected app in Gemini’s web interface. Google documents adding an MCP server URL, but Unify does not list Gemini in its supported client setup. Confirm Unify authentication compatibility and Google’s account requirements before connecting. This article covers Gemini Apps, not Gemini CLI.[1][3][4]

By UnifyDocumentation reviewed
Connection
Custom MCP
AI assistants
Tool
Gemini
Model Context Protocol
Data flow
Gemini ↔ Unify
Tool calls and returned results

At a glance

  1. Confirm this custom client with Unify before connecting
  2. Use tool calls and returned results instead of an outbound Play payload
  3. Check the final Agent result before treating the task as complete

When this workflow makes sense

Start with the decision your team needs to make, then choose the connection that supports it.

A Gemini account brief can be useful when the assistant can distinguish authorized sales context from the rest of the conversation. The setup decision comes first: Google’s documented custom-app eligibility is narrower than general Gemini availability. An organization using work accounts should check that boundary before planning a rollout. Only after a valid connection should the team evaluate the quality of research and follow-up recommendations.

A good fit when

Eligible Gemini users evaluating a provider-confirmed custom connection for bounded Unify account research.

Reconsider the plan when

Google’s reviewed guide excludes work and school Google Accounts from this custom-app path. It also requires a US location, age 18+, English, and Keep Activity enabled. Unify OAuth compatibility remains untested.

Design the handoff

Use this framework to agree on the input, the next action, and who owns the result.

Suggested workflow design, based on the documented capabilities below.

StageDecision to make
Client and accountAn eligible Gemini account: Google currently documents US users aged 18 or older, a personal Google Account, English, and Keep Activity enabled
First taskSuggested prompt: “After validating the Unify custom app, use it to review example.com. Separate current account facts, inferred fit, and questions for a rep. Do not send messages or enroll prospects.”
ExecutionDefine whether the request is research-only or includes a specific authorized action. Keep the run ID for follow-up.
ResultReview the final output and unresolved questions before using the result in a sales decision.

Explore the scenarios

Choose the situation that fits your team and work through the proposed plan.

Open a scenario to explore its plan. Checklists track your selections in this page only.

Evaluate account research in an eligible Gemini account

A user wants a small research pilot before relying on a custom connected app.

The decision that matters

Treat account eligibility and authentication as prerequisites, then assess the returned research separately.

  1. Confirm eligibility and Unify compatibility
  2. Select the connected app and request one bounded account review
  3. Compare its final result with the requested ICP criteria
Your validation checklist
0 of 3 checks marked by you
Decide whether the path fits a team rollout

A pilot user wants colleagues to adopt the same account-research process.

The decision that matters

A personal-account pilot does not establish availability for a Google Workspace deployment.

  1. Identify the Google account type used by the intended team
  2. Compare it with Google’s current custom-app requirements
  3. Choose an officially documented Unify client if the account path is unavailable
Your validation checklist
0 of 3 checks marked by you

Illustrative workflow, not a preconfigured automation. Complete these checks in your own account.

Connect your tools to Unify

Set up your integration or walk through it with our team

Define success before launch

Inspect the data and the intended outcome separately. Connection status is only the first check.

Expected, not tested

After the connection is authorized, Gemini can identify the intended Unify user and retrieve the completed output of the controlled research task.

Inspect get_me, the requested task, the final run status, and read_agent_results together. A discovered tool or a run ID confirms a different stage from a completed result. For any explicitly requested write, inspect the actual destination record as well.

Documentation-based reference. This workflow has not been tested end to end. Use a record or event you control before enabling live activity.

Questions answered

Common decisions when connecting Unify and Gemini.

How do I connect Unify to Gemini?

First confirm the custom client and authentication setup with Unify. Then follow the client’s documented MCP configuration and verify identity and tool access before requesting work.[1][3]

Can a Google Workspace account follow this Gemini setup?

Not under the eligibility rules in the reviewed Google guide. It specifies a personal Google Account and says work or school accounts are not currently supported for custom connected apps.[1][2][3]

How is MCP different from a Play webhook?

An MCP client can invoke Unify tools and retrieve their documented results. The Play Webhook action sends an external request and does not pass its response into downstream Play steps. They are separate connection mechanisms.[2][5]

Does a run ID mean the task succeeded?

No. run_agent starts background work. Check the run with poll_agent, handle any clarification, and call read_agent_results after the run reaches READY or ERROR.[2]

Does Unify MCP have separate usage charges?

Unify says MCP uses the same Agent and usage or credits as Unify Chat, with no separate charge for connecting through MCP. Your AI client’s own subscription and usage terms still apply.[1][3]

Limits & decisions

Check these boundaries before designing a live workflow around the connection.

  • Google’s reviewed guide excludes work and school Google Accounts from this custom-app path. It also requires a US location, age 18+, English, and Keep Activity enabled. Unify OAuth compatibility remains untested.[1][3]
  • Unify permissions and Agent usage limits still apply[1][2]
  • A completed research result does not itself authorize sending, enrollment, or CRM updates
  • No authenticated end-to-end execution has been performed

What the connection supports

Understand the connection, the data involved, and the behavior that matters for a Unify + Gemini workflow.

Connection flowCustom MCP
Proposed MCP connection

The assistant requests work from Unify and retrieves its result using the connected user’s permissions.

Documented behavior at a glance
DecisionWhat to know
Connection routeCustom client support must be confirmed with the Unify account team[1]
Client requirementAn eligible Gemini account: Google currently documents US users aged 18 or older, a personal Google Account, English, and Keep Activity enabled[1][3]
Published serverhttps://mcp.unifygtm.com/mcp (authentication required)[4]
IdentityCalls are scoped to the authenticated Unify user and tenant[2]
Agent lifecycleStart a run, poll status, answer clarification, and read the terminal result[2]
UsageUnify MCP Agent work uses existing Unify Chat usage and credits[1]

MCP exposes tool schemas to the client. For Agent work, provide a natural-language prompt and retain the returned runId for status and result calls. Direct API tools have their own required inputs. This connection is separate from a Play’s outbound Webhook action and does not make webhook responses available to later Play steps.

Technical setup reference

References and requirements for the Gemini connection.

Connection requirements and setup checklist

Before connecting

  • An eligible Gemini account: Google currently documents US users aged 18 or older, a personal Google Account, English, and Keep Activity enabled
  • A Unify user with access to the intended workspace and available Chat credits for Agent runs
  • One controlled research task with a clear output and explicit boundaries on record changes
  1. Check eligibility and Unify support

    Confirm the Google account requirements above and ask Unify for the supported Gemini authentication setup. Stop here if either requirement cannot be met.[1][3]

  2. Add a custom app on the web

    In gemini.google.com, open Settings → Connected Apps. Some accounts place this under Personal Intelligence. Under Custom apps, add the confirmed MCP URL and follow the connection flow.[3][4]

  3. Complete authentication and select the app

    Google provides Advanced features for servers without Dynamic Client Registration. Use only credentials supplied for this client. After connecting, select the custom app with @ for a controlled identity and research check.[3]

  4. Check the Agent result

    For Agent work, run_agent returns a runId before the task finishes. Poll that run. Answer every returned question if its status is CLARIFICATION_NEEDED. On READY, read_agent_results returns the completed output; on ERROR, inspect the reported failure.[2]

Troubleshooting

Start with the stage where the expected data or action stops appearing.

The client cannot find or authorize Unify

Check custom connector availability and the OAuth client requirements with Unify. Do not substitute another client’s OAuth identifiers, disable authentication, or assume a public server URL grants access.[1][3]

A run starts but no result appears

Keep the original runId and poll its status. PENDING is still running; CLARIFICATION_NEEDED requires answers; READY permits reading the result. Use list_agent_runs to find a previous run rather than starting duplicate work.[2]

The tool reports missing access or unavailable credits

Verify the connected user and workspace. Unify scopes tools to that user, and Agent runs require available Chat funding and are subject to rate limits. A table owned by another user is not accessible through load_datatable.[2]

Sources & review

Official documentation reviewed on September 16, 2026.

Technical claims link to primary documentation from Unify and the destination tool. Scenarios, field choices, and recovery plans are editorial implementation examples. Documentation review is separate from execution testing.

Documentation reviewed; end-to-end execution not tested. No named technical reviewer has signed off on these articles yet.

Content updated: . Report a correction to Unify with the tool name, source URL, and behavior you observed.

  1. [1] Unify: Getting started with MCP
  2. [2] Unify: MCP tools and Agent lifecycle
  3. [3] Google: Connect and manage custom apps for Gemini
  4. [4] Unify: Official MCP server configuration
  5. [5] Unify: Webhooks in Plays

Get started with Unify

Create your account or book a demo with our team