TotalHealAgentGateMCP Gateway for AI agents
Zero trust for AI agents: every tool an agent calls through your MCP servers is checked against its allow list, approved by a person where it matters, and recorded.
Trial: 30 days, up to 5 agents. You sign in to the TotalHeal console with a Sttiz account and activate AgentGate MCP Gateway. No card.
AI agents now act — they read customer records, send e-mails, issue refunds and change systems through MCP servers. Each agent usually holds a server token that can do everything, nobody can say which agent called what, and a single prompt injection can turn a helpful agent into one that closes accounts or mails out customer data.
AgentGate sits between your AI agents and your MCP servers. Each agent gets its own identity and token and sees only the tools it is allowed; the servers’ own credentials stay with AgentGate. Every tool call is checked against the agent’s allow list — and, on the Professional tier, for sensitive data and for tools that need a person’s approval — then forwarded and recorded.
AgentGate MCP Gateway, feature by feature.
Registry of MCP servers
Register each server’s endpoint once; AgentGate reads its tools and how each declares itself (read only, or changes and deletes data). Turn any tool off for everyone, and pause a whole server.
Credentials agents never hold
The server’s token is kept encrypted by AgentGate and added to each forwarded request. Agents authenticate to AgentGate with their own token; revoking it cuts the agent off without touching the server.
An identity per agent
Every agent has a name, an accountable owner, a token shown once (only its fingerprint is kept) and an allow list of servers and tools. When an agent lists tools it sees only the ones it may call.
Arguments checked for sensitive data
Before a call is forwarded its arguments are inspected with the DataShield detectors — Aadhaar, PAN, bank accounts and IFSC, card numbers, cloud keys and passwords — and stopped at the threshold you set per server, with a message the agent can act on.
A person approves what matters
Tools that change or delete data can require approval. The call waits; a person approves or rejects it in the console with a note, and that exact call — same tool, same arguments — goes through once within 15 minutes. An AI agent can never approve.
Rate limits and a kill switch
Each agent has its own limit of tool calls a minute. Disable one agent, or stop every agent at once, and requests are refused immediately.
Unusual behaviour
After a learning week, an agent that calls a tool it has never used, or makes three times more calls in an hour than its busiest hour so far, raises an alert in the same incident queue as everything else.
A record of every call
Agent, server, tool, decision and reason, argument names and sizes (never their values), sensitive data found (masked), result and latency — for audits and for investigating what an agent did.
How AgentGate MCP Gateway works.
AgentGate puts every AI agent behind its own identity and every MCP tool call behind a check: is this agent allowed this tool, do the arguments carry sensitive data, does a person need to approve it? Server credentials stay with AgentGate, and every call is recorded.
- RegisterAdd your MCP servers; AgentGate reads their tools and keeps their credentials.
- IdentifyGive each agent its own token, an owner and the tools it may use.
- CheckEach call is checked against the allow list and, on Professional, for sensitive data and approval.
- ApproveA person approves or rejects high-impact calls; the approved call goes through once.
- RecordEvery call is recorded; unusual behaviour raises an alert and the kill switch stops agents at once.
Platforms and deployment
Platforms
| Platform | How it is covered |
|---|---|
| MCP servers | Model Context Protocol over Streamable HTTP (JSON and event-stream answers); tools/list and tools/call inspected, other messages passed through |
| Agents | Any MCP client that sends a bearer token (custom agents, agent frameworks, IDE assistants) |
| Console | TotalHeal web console |
Deployment
| Profile | Status |
|---|---|
| SaaS (India region) | AvailableThe gateway runs in the TotalHeal cloud and calls your MCP servers over HTTPS. |
| On-premises control plane | AvailableDelivered with our team from the on-premises kit. |
| Air-gapped | AvailableOffline kit, offline licence file and offline update bundles. |
Essential, Professional or Elite.
Priced per ai agent per year. Counted: aI agents registered in AgentGate.
| Feature | EssentialUS$180per AI agent per year | ProfessionalUS$360per AI agent per year | EliteUS$600per AI agent per year |
|---|---|---|---|
| Registry of MCP servers with their tools read automatically; server credentials kept encrypted and added by AgentGate — agents never hold them | |||
| An AI agent identity per agent: its own token, an owner, an allow list of servers and tools; the tool list each agent sees is filtered to it | |||
| Every tool call recorded: agent, server, tool, decision, argument names and sizes, result, latency | |||
| Arguments checked with the DataShield detectors and blocked at the threshold you set per server | |||
| High-impact tools held for a person’s approval (an AI never approves); rate limits per agent | |||
| Alerts on unusual agent behaviour (a tool never used before, a burst of calls); kill switch for one agent or all |
List prices per AI agent per year; minimum 3 AI agents. Each tier includes everything in the tier before it. Volume, multi-product and partner pricing on request.
AgentGate is sold on its own, outside the editions.
Government profile. Government is a profile, not a separate tier or price list: the Elite tier with Government defaults switched on — data residency in India, four-eyes approval of policy changes, a distinct approver for every approval-level action, retention of at least 180 days, and the CERT-In and DPDP reporting clocks.
What you need
- MCP servers reachable over HTTPS that speak Streamable HTTP
- Agents whose MCP client can send a bearer token
Procurement documents for AgentGate MCP Gateway
The datasheet is public. The full dossier is sent on request, so we can match it to your tender.
- Datasheet. What the product does, platforms, deployment profiles, tiers and honest limits.
- Compliance matrix. Each requirement marked comply, partial or no, with an evidence reference — CERT-In directions, DPDP, ISO 27001 controls touched, accessibility of the console, data residency.
- Bill of materials. SKUs per sizing, the unit and quantity formula, customer-side components and services.
- Architecture and hardening. How the product is deployed and the hardening guidance for each component.
- SLA. Support tiers, response targets the team can meet, update cadence and end-of-life policy.
- OEM authorisation letter. A MAF template for resellers and system integrators, with product names exactly as on the SKU.
Get a quote for AgentGate MCP Gateway.
Tell us how many ai agents you need and how you want to deploy. We reply with a quote and the procurement documents you ask for.
Or email business@totalhealsecurity.com.