How to integrate Unify with Hermes Agent
To evaluate Unify with Hermes Agent, confirm the client with Unify, then configure its remote MCP endpoint in Hermes and complete OAuth. Hermes documents HTTP MCP servers and OAuth; Unify does not yet publish a Hermes-specific setup. A successful connection should identify your Unify workspace and return a completed research result before it becomes part of an operations workflow.[1][3][4]
- Connection
- Custom MCP
- AI assistants
- Tool
- Hermes Agent
- Model Context Protocol
- Data flow
- Hermes Agent ↔ Unify
- Tool calls and returned results
At a glance
- Confirm this custom client with Unify before connecting
- 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.
A technical operator may want an account-research task to sit alongside local files and scripts. The proposed benefit of Hermes is continuity: the next session can return to the research question and its source run instead of starting again. Write a short task contract first, including the company, desired artifact, and allowed actions. Save the run reference with the artifact so later edits can distinguish new research from reformatting old findings.
A good fit when
Technical RevOps users who want to evaluate Unify research inside a persistent agent workspace.
Reconsider the plan when
Unify must accept the Hermes authentication path. A working HTTP configuration is not proof of authorization. Remote terminal login also requires a reachable OAuth callback.
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 | A Hermes installation with HTTP MCP and OAuth support, plus confirmation that Unify accepts its client registration and callback |
| First task | Suggested prompt: “After authenticating to the intended Unify workspace, research example.com. Save a draft account brief with evidence, unresolved questions, and the source run ID. Do not change remote records.” |
| 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.
Keep an account brief next to an operations project
An operator needs current account context while drafting a local deliverable.
Make the research provenance part of the file, not just the conversation.
- Confirm the connector and intended account
- Request a single bounded research task
- Save the completed findings with their run reference
Resume research across sessions
A later session revisits a task that may still be pending.
Inspect the original run before requesting new work.
- Recover the saved run ID
- Read status and answer any clarification
- Update the brief from the terminal result
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, Hermes Agent 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 Hermes Agent.
How do I connect Unify to Hermes Agent?
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 I authenticate Hermes from a remote terminal?
Hermes documents browser OAuth with remote callback handling, including an interactive redirect fallback and SSH forwarding. Use that documented path with a Unify-approved client; do not assume device-code login is supported by Unify.[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.
- Unify must accept the Hermes authentication path. A working HTTP configuration is not proof of authorization. Remote terminal login also requires a reachable OAuth callback.[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 + Hermes Agent workflow.
The assistant requests work from Unify and retrieves its result using the connected user’s permissions.
| Decision | What to know |
|---|---|
| Connection route | Custom client support must be confirmed with the Unify account team[1] |
| Client requirement | A Hermes installation with HTTP MCP and OAuth support, plus confirmation that Unify accepts its client registration and callback[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 Hermes Agent connection.
Connection requirements and setup checklist
Before connecting
- A Hermes installation with HTTP MCP and OAuth support, plus confirmation that Unify accepts its client registration and callback
- 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
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]
Proposed Hermes configuration, subject to Unify OAuth compatibility
mcp_servers:
unify:
url: "https://mcp.unifygtm.com/mcp"
auth: oauthRun these in your own terminal, then follow the sign-in steps.
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.
Keep exploring
