Loading...
×Connect GitHub Copilot's agent mode to Tareno to turn a merged pull request into a short LinkedIn story with the problem and the outcome, approved by you in Tareno.
Yes, once Tareno is added as an MCP server in VS Code. Copilot's agent mode reads the pull request, tells its story with the original problem and the user-visible outcome, and saves the draft through Tareno. Tareno has not completed a client test for Copilot, so the setup follows published documentation. Scheduling needs your approval.
Last reviewed 2026-10-24 · Markdown version for AI agents
A pull request has a story: someone hit a problem, a team debated options, a change landed. The description usually tells it badly, because it was written for reviewers, not readers. A LinkedIn post tells the same story for people who never saw the repository. GitHub Copilot sits where the pull request lives, so its agent mode can read the thread and the diff and translate them. This page follows a product engineer who wants to share a fix that users noticed, including how to connect Tareno in VS Code, how organization policy can block MCP servers and how to keep a post accurate.
Picture an engineer at a project-management software company who merged a fix for a bug that made shared boards load slowly. In VS Code she opens Copilot's agent mode and asks it to read the pull request, its linked issue and the release note. Copilot writes a 190-word story: the problem users reported, the cause in one plain sentence, the change and what users now notice. It leaves out the internal service name and marks a sentence claiming "twice as fast" as unsupported by the description. She supplies the real measurement from the release note, Copilot confirms her profile with list_accounts and saves the post through create_drafts, and she requests Thursday 09:30 in her time zone, which waits as a pending action.
For Copilot Business and Enterprise, GitHub's documentation says the policy for MCP servers in Copilot must be enabled by your organization. If the option is missing, ask your administrator before you look for a workaround.
Add Tareno to the workspace mcp.json as a remote server with its type set to http and the hosted endpoint as the URL, or use the Add Server command. Published guides describe a browser sign-in on first use.
Switch Copilot to agent mode and ask for list_accounts. If your LinkedIn profile appears, the connection works; if not, connect the profile in Tareno first.
Give Copilot the pull request, the linked issue and the release note. Ask it to separate the problem users saw from the technical cause, and to drop internal service names.
Ask for a 190-word story and a list of every claim that the description does not support. Replace unsupported claims with real measurements or remove them.
Copilot saves the post through create_drafts. Give a date, a time and an IANA time zone, and approve the pending request in the Tareno dashboard.
Read pull request [number], the linked issue and the release note. In five sentences describe the problem users reported, the cause in plain language and what users notice now. Leave out internal service names and say which statements are not supported by the description.Write a 190-word LinkedIn story about this fix for [product managers and engineers]: the problem, the cause, the change and the outcome. Use only this measurement: [boards load in 1.8 seconds instead of 4]. Flag every claim that goes beyond it.Use Tareno to confirm my LinkedIn profile [name] and save the final story as a draft. Return the draft ID and the text, and do not request a time until I give you the day and the time zone.Ask Tareno to schedule draft [draft ID] for [Thursday 09:30] in the [Europe/Amsterdam] time zone. Return the pending action ID and remind me that the post is not scheduled until I approve it in the Tareno dashboard.As configured in Tareno on 2026-10-24. The live rules for your own account come from the get_platform_schema tool.
Source: Microsoft Learn: LinkedIn Posts API, read on 2026-10-24. Platform rules change; check the page before you rely on a number.
https://tareno.co/api/mcpUse the same Tareno account across supported clients. Open the relevant setup guide for authentication, first use, reconnect, and revocation.
list_accountsYes, as a remote MCP server added in VS Code, according to published documentation. Tareno has not completed a client test for Copilot. For Business and Enterprise seats the MCP policy has to be enabled by your organization first.
Yes, MCP tools are used by agent mode, not by plain chat. Switch to agent mode, check that the Tareno tools are listed and then ask for `list_accounts` as a first read-only test.
Put a remote server entry with type http and the hosted endpoint in your workspace mcp.json, or use the Add Server command, and sign in when the browser opens. Guides describe this flow; check the labels against your VS Code version.
If you tell it to. Ask for plain descriptions instead of service names, and read the draft in Tareno before you request a time. Tareno only receives what Copilot sends, so the check is a read of the text.
No. A scheduling request becomes a pending action in Tareno. LinkedIn receives the story only after you approve it in the dashboard, and Copilot can only report that the action is pending.
No. The hosted endpoint supports OAuth, so you sign in with your Tareno account when the browser opens. Never paste a key or a token into a prompt or a committed configuration file.