Skip to main content
Mercury’s official MCP server provides read-only access to your Mercury business banking data, including accounts, balances, transactions, cards, recipients, statements, and treasury. It cannot initiate transactions or modify account data because all mutations are blocked server-side.
Use Mercury MCP with DialNexa when the caller asks for access, recovery, permission changes, vault help, or anything that could expose sensitive systems.

​
Where Mercury MCP fits in a DialNexa workflow

Mercury MCP should receive DialNexa output when the conversation affects a vault item, access request, identity check, security review, policy exception, or suspicious-call escalation. The handoff should explain what the caller asked for, what DialNexa learned, which record or object is affected, and who owns the next step.

Route policy exceptions

Send unusual access requests to the correct security or IT owner with the policy, reason, and urgency attached.

Verify the caller before access changes

Capture who called, what access they requested, which workspace is affected, and whether identity confidence is high enough for review.

Escalate risky requests

Flag callers asking for secrets, emergency access, admin changes, recovery help, or unusual account actions.

Keep secrets out of notes

Store a safe summary and links to restricted evidence instead of writing passwords, tokens, keys, or recovery codes.

​
What DialNexa should capture for Mercury MCP

  • Caller identity, organization, role, account, phone, and verification confidence
  • Requested permission, policy exception, recovery action, affected system, and severity
  • Risk reason, suspicious phrases, urgency, approval requirement, and escalation owner
  • Safe summary, transcript link, recording link, DialNexa call ID, and review status
  • Redaction flag for secrets, tokens, passwords, keys, or recovery codes

​
High-value Mercury MCP workflows

For this workflow, DialNexa should send Mercury MCP a concise, action-ready handoff: matched caller, affected record, reason for the update, urgency, owner, next step, and links to call evidence.
For this workflow, DialNexa should send Mercury MCP a concise, action-ready handoff: matched caller, affected record, reason for the update, urgency, owner, next step, and links to call evidence.
For this scenario, DialNexa should treat Mercury MCP as an escalation destination. Send the impact, urgency, affected customer or object, owner, and transcript link so the right team can act before the issue gets colder.
For this scenario, DialNexa should treat Mercury MCP as an escalation destination. Send the impact, urgency, affected customer or object, owner, and transcript link so the right team can act before the issue gets colder.
For this workflow, DialNexa should send Mercury MCP a concise, action-ready handoff: matched caller, affected record, reason for the update, urgency, owner, next step, and links to call evidence.
DialNexa should keep this people workflow minimal and private: identity, role or case, requested next step, owner, timing, and sensitivity flag. Do not copy unnecessary personal details into Mercury MCP.
Use create external records from call outcomes only when DialNexa has a matched caller, a clear destination object, and enough call context to justify opening a new security record. If the caller is unclear, route to review instead of creating noise.
Use update follow-up workflows after the call when the caller changes a field, status, owner, date, priority, note, consent choice, or next step on an existing Mercury MCP record. Include the old value, new value, and reason from the call.

​
Workflows that pair Mercury MCP with other integrations

​
Implementation notes

  • Use the DialNexa call ID as the idempotency key before running Mercury MCP actions.
  • Write a short operational summary into Mercury MCP and link to the full transcript or recording for audit.
  • Map required fields before launch: destination object, owner, status, urgency, next step, and record URL.
  • Create review paths for low-confidence matches, sensitive requests, high-value customers, and actions that change money, access, legal terms, or customer commitments.

​
FAQs

Secrets, recovery phrases, private keys, full transcripts, and detailed internal security reasoning should stay in restricted systems.
No. Store a safe summary, risk reason, and restricted evidence links. Do not write passwords, recovery codes, tokens, API keys, or private credentials into broad-access records.
Create a review when the caller asks for account recovery, admin access, permission changes, shared secrets, unusual exceptions, or anything that changes security posture.
Send the verification method, confidence level, failed checks, and reviewer requirement as separate fields so the security team can see why DialNexa did or did not proceed.
Only for low-risk, pre-approved flows. Admin rights, emergency access, credential changes, and policy exceptions should require a human approval step.
Stop the account-changing workflow, create a restricted review item, and include the attempted request, failed checks, call ID, and escalation owner.
Caller identity, requested action, reviewer, decision, timestamp, policy reason, DialNexa call ID, and links to restricted transcript or recording evidence.
Tag the risk reason, avoid giving sensitive details, and notify the security or IT channel with the safe summary and evidence links.