How to integrate Unify with Instinct
Connect Unify with Instinct through MCP to bring account research and sales tools into your assistant. Add Unify’s remote MCP server, sign in with your Unify account, and request a company assessment. Instinct can use the returned research to prepare an account brief and help you decide what to do next.[1][3]
- Connection
- MCP
- AI assistants
- Tool
- Instinct
- Model Context Protocol
- Data flow
- Instinct ↔ Unify
- Tool calls and returned results
At a glance
- Connect Instinct to Unify through MCP
- Use tool calls and returned results instead of an outbound Play payload
- 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.
An account owner often needs to return to a decision after gathering more information. Use the Unify MCP connection to request the research, then keep its result and open questions with the account brief in Instinct. Save the run reference so you can check progress or retrieve the completed output later without repeating the request.
A good fit when
Instinct users who want Unify research and sales context alongside their account-review tasks
Reconsider the plan when
The MCP connection uses the permissions of the Unify account you connect. Choose the account and workspace that should supply the research
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.
| Stage | Decision to make |
|---|---|
| Client and account | Access to Instinct, permission to configure MCP connections, and a Unify account for authentication |
| First task | Suggested prompt: “Use Unify to research example.com against our ICP. Prepare an account brief with evidence, open questions, and the Unify run reference. Do not change records or start outreach.” |
| Execution | Define whether the request is research-only or includes a specific authorized action. Keep the run ID for follow-up. |
| Result | Review 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.
Build a brief for an account review
An account owner needs current research before deciding how to approach a company.
Keep the facts, open questions, and next decision together.
- Connect the intended Unify account through MCP
- Request a company assessment against your ICP
- Create the brief from the completed research result
Return to an account review with its research intact
A later session picks up an account brief whose research may still be running.
Check the saved run before requesting more research.
- Recover the run ID from the brief
- Check its status and answer any clarification
- Retrieve the completed result and update the account brief
Illustrative workflow, not a preconfigured automation. Complete these checks in your own account.
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, Instinct 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 Instinct.
How do I connect Unify to Instinct?
Add https://mcp.unifygtm.com/mcp to the MCP connections in your Instinct account. Use Unify as the connection name so you can identify it when requesting research.[1][3]
What can I ask Instinct to do through Unify MCP?
Ask Instinct to use Unify for company research, prospect lists, or other available sales tools. State the company or audience, the result you need, and whether the task includes record changes. For background Agent work, keep the run ID and retrieve the completed output.[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]
Limits & decisions
Check these boundaries before designing a live workflow around the connection.
- The MCP connection uses the permissions of the Unify account you connect. Choose the account and workspace that should supply the research[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 + Instinct workflow.
The assistant requests work from Unify and retrieves its result using the connected user’s permissions.
| Decision | What to know |
|---|---|
| Connection route | Instinct connects to Unify through MCP[1] |
| Client requirement | Access to Instinct, permission to configure MCP connections, and a Unify account for authentication[1][3] |
| Published server | https://mcp.unifygtm.com/mcp (authentication required)[4] |
| Identity | Calls are scoped to the authenticated Unify user and tenant[2] |
| Agent lifecycle | Start a run, poll status, answer clarification, and read the terminal result[2] |
| Usage | Unify 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 Instinct connection.
Connection requirements and setup checklist
Before connecting
- Access to Instinct, permission to configure MCP connections, and a Unify account for authentication
- 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
Add Unify as a remote MCP server
Add https://mcp.unifygtm.com/mcp to the MCP connections in your Instinct account. Use Unify as the connection name so you can identify it when requesting research.[4]
Request an account brief
Ask Instinct to use Unify to research one company domain against your ICP. Specify the output you need and retain the returned run ID to check the research and retrieve its result.[2]
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.
Missing Instinct MCP setup documentation
Unify’s MCP documentation is available and linked below. The missing documentation is Instinct’s client-specific MCP setup instructions, not Unify’s server or tool documentation. For those client-side steps, contact Instinct support.[2][3][4]
The client cannot find or authorize Unify
Check the saved Unify MCP URL, your connected account, and your organization’s connector permissions. Complete sign-in again if the session has expired, then use get_me to check the connected workspace.[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.
Keep exploring
