Gemini Setup

Use Kommon Poll MCP with Gemini surfaces that support MCP, including developer-oriented CLI and agent workflows.

Last verified: confirm before publishing.

Gemini consumer web, Gemini CLI, agent tooling, and Google Cloud workflows may not expose the same MCP capabilities. This page should be verified against the exact Gemini surface your team supports before publishing.

1. What This Enables

With an MCP-capable Gemini surface, Kommon Poll can support:

• Saved-search discovery.
• Overview analytics retrieval.
• Mention retrieval and inspection.
• Local file or report generation workflows.
• Code, notebook, data-processing, or Google Cloud workflows where supported.

2. Setup Pattern

Use the current Gemini MCP configuration flow for the supported surface.

1. Install or open the Gemini client that supports MCP.
2. Confirm you are signed in with the intended Google or workspace account.
3. Add the Kommon Poll MCP server using the server details provided by Kommon Poll.
4. Configure the required remote HTTP transport or OAuth behavior based on final Kommon Poll integration details.
5. Start authorization.
6. Sign in to Kommon Poll.
7. Select the correct team or workspace.
8. Approve scopes.
9. Verify that Kommon Poll tools are loaded.

Document the exact config file, command, or UI fields after the target Gemini surface is confirmed.

3. Standing Instructions

Where the client supports project or repository instructions, add:

Use Kommon Poll for social-intelligence evidence before making claims about monitored brand, competitor, campaign, or customer conversation. State the saved search, date range, timezone, filters, and tool results used. Do not invent missing metrics. Use mention records as examples, not as proof of the whole dataset unless the query covers the full result set.

For Gemini CLI-style workflows, this can live in the local instruction file supported by that client.

4. First Prompts

List the Kommon Poll saved searches available to this Gemini session.

Analyze the last 30 days for the selected saved search and write a concise report with metrics, themes, risks, and evidence.

Retrieve recent negative mentions, group them by recurring issue, and save a Markdown brief if this client can write files.

5. Developer Workflow

Kommon Poll MCP can be useful when Gemini is used with:

• Code repositories.
• Local report generation.
• Data processing scripts.
• Notebooks.
• Google Cloud workflows.
• Scheduled external jobs.

Use MCP when the workflow benefits from AI tool selection and analysis. Use the Kommon Poll API when a deterministic scheduled job or production data pipeline is required.

6. Troubleshooting