Core governance principles
These principles define the minimum operating posture for enterprise MCP and agentic AI adoption.
Bounded purpose
Every agent has a named business purpose, approved user group, permitted systems and prohibited actions.
Read-only first
New agents begin with retrieval, summarisation or drafting before write actions are considered.
Action tiering
Tool calls are classified as read, write, destructive, privileged or high-impact before release.
Human control
High-impact and irreversible actions require human approval, rollback and accountable ownership.
MCP enterprise architecture and discovery
The enterprise pattern separates the user experience, AI orchestration, MCP protocol connection, governance gateway, approved MCP servers and downstream systems.
Employee or process
Starts a request from chat, Copilot, portal, workflow or business application.
AI client / agent host
Manages the AI experience and determines which approved agent capabilities are available.
Protocol session
Connects the AI host to a specific MCP server using the MCP protocol.
Enterprise MCP Gateway
Enforces identity, action tier, approvals, routing, rate limits, monitoring and audit logging.
Agent and server catalogue
Records approved agents, MCP servers, tools, data classes, owners and release status.
Approved MCP servers
Managed connectors exposing approved tools, resources and prompt templates.
Actions
Search, create ticket, update record, trigger workflow or call an approved API.
Context
Documents, records, knowledge entries or datasets retrieved within access boundaries.
Patterns
Reusable prompt templates that standardise approved interaction flows.
Collaboration and knowledge
Microsoft 365, SharePoint, Confluence, knowledge bases and policy stores.
Business platforms
CRM, ERP, HR, finance, customer service and operational workflow platforms.
Engineering and operations
Git repositories, DevOps tools, ITSM platforms, monitoring and cloud APIs.
MCP component overview
Host
The AI application or agent environment that presents the experience to users and decides which approved capabilities are available.
Client
The protocol component inside the host that opens and manages the MCP connection to one server at a time.
Server
The governed connector that exposes approved capabilities to the agent. It sits in front of the actual business system.
Tools, resources and prompts
Tools allow actions, resources provide context, and prompts provide reusable interaction templates. Each requires ownership, classification and release control.
Enterprise MCP discovery setup
Discover servers
Maintain an enterprise MCP catalogue covering internal, vendor and approved open-source servers.
Discover capabilities
Record each server's tools, resources, prompts, action tier, data class and approved caller list.
Discover authorization
For protected remote MCP servers, align clients with the correct authorization server and access policy.
Register through gateway
Route production MCP traffic through the gateway so identity, policy, HITL, rate limits and logs are enforced.
Review lifecycle
Retire or block servers without owner, logs, current review, approved purpose or passing release evidence.
Apply the framework
Select a scenario to view the governance question, default decision pattern, platform action and role involvement.
Control model
Controls are applied to the agent, the MCP server, the tool action and the resulting evidence record.
| Control domain | Enterprise requirement | Implementation pattern | Evidence artefact |
|---|---|---|---|
| Identity and access | Each agent and user context is attributable. | Managed identity, OAuth, RBAC, least privilege, no shared service accounts. | Access policy, identity record, approval history. |
| Tool action tiering | Actions are classified before release. | Read, write, destructive, privileged and high-impact tier model. | Tool tier dictionary, release gate record. |
| Prompt injection protection | Untrusted content is not treated as trusted instruction. | Input separation, adversarial tests, content filtering, restricted tool invocation. | Test pack, failed case log, remediation record. |
| Human control | High-impact actions are approved and reversible where possible. | Human-in-the-loop, rollback path, break-glass ownership. | Approval record, rollback procedure, incident owner. |
| Monitoring and audit | Agent actions are observable and reviewable. | Structured logs, correlation IDs, SIEM integration, anomaly alerts. | Audit log, dashboard, exception report. |
Action tier dictionary
| Tier | Examples | Default decision pattern |
|---|---|---|
| Read | Search knowledge base, fetch policy, list incidents, query approved view. | Allowed after identity, access and logging controls are confirmed. |
| Write | Create ticket, draft case note, update non-sensitive field. | Allowed after pilot if scope is narrow, logged and reversible. |
| Destructive | Delete record, close case, remove file, cancel workflow. | Human approval required; rollback and audit record mandatory. |
| Privileged | Change access, run admin action, alter configuration. | Privileged access controls and explicit approval required. |
| High-impact | Action affecting employment, finance, customer entitlement, safety or legal position. | Human decision ownership required; agent may support but not independently decide. |
Agent incident response model
Agentic systems require an operational response path because failures may involve tool actions, data exposure, incorrect records, workflow disruption or prompt injection in production.
Trigger from SIEM alert, gateway anomaly, user report, support ticket, cost spike, failed evaluation or unexpected tool-call pattern.
Disable the agent, block the MCP tool, revoke token, pause the gateway route, or switch the agent to read-only mode.
Capture correlation ID, prompt context, tool call, user identity, MCP server, response, timestamp and affected system record.
Classify data exposure, wrong action, customer impact, operational disruption, compliance impact and rollback feasibility.
Reverse records where possible, notify accountable owners, patch prompts/tools, update access policy and retest failed scenarios.
Return to production only after release gates pass again. Retire the agent or tool where residual risk is not acceptable.
| Incident type | Minimum response | Required evidence |
|---|---|---|
| Wrong record updated | Disable write tool, identify affected records, rollback or correct, notify business owner. | Tool call log, record diff, approval record, rollback evidence. |
| Prompt injection suspected | Freeze agent route, preserve prompt and retrieved content, run adversarial retest before release. | Prompt context, retrieved source, failed test case, remediation record. |
| Workflow crash or runaway call pattern | Trigger circuit breaker, pause gateway route, review rate limits and retry behaviour. | Call volume, error rate, timeline, system impact, corrected threshold. |
| Data exposure | Stop affected retrieval path, classify exposed data, involve privacy/security owner. | User identity, resource accessed, classification, recipients, containment action. |
Accountability model
Governance is distributed across accountable owners, platform teams and assurance functions. The platform layer provides consistent controls.
AI Experience & Platform Enabler Team
Owns the governed AI platform layer: agent catalogue, approved MCP/connectors, prompt patterns, release gates, operational telemetry, support model and evidence packs.
Business owner
Owns the process outcome, business risk, user group, acceptable action scope and adoption outcome.
Security, privacy and data partners
Validate access, data handling, prompt injection controls, monitoring, DLP and privacy requirements.
Architecture and operations
Maintain reference patterns, platform standards, incident path, support runbooks and lifecycle operations.
Evidence model
The evidence model converts governance into artefacts that can be reviewed by risk, audit, architecture and operations.
| Evidence area | Required artefacts | Owner |
|---|---|---|
| Agent inventory | Agent name, owner, purpose, user group, systems connected, action tiers. | AI Experience & Platform Enabler Team |
| Architecture | Reference diagram, data flow, MCP server list, integration dependency map. | Architecture lead |
| Controls | Access policy, approval gate, test result, monitoring rule and rollback path. | Platform, security and operations |
| Operations | Support model, incident workflow, known issues, service ownership, lifecycle status. | Service operations |
| FinOps | Usage dashboard, quota settings, budget alerts, licence assignment, API and connector consumption. | Platform and FinOps owners |
| Review record | Release decision, exceptions, residual risks and next review date. | Governance forum |
Cost and capacity control
Multi-vendor agentic AI introduces licence, token, API, connector and infrastructure cost. Cost governance should be part of the platform layer, not an afterthought.
Usage visibility
- Track agent sessions, model calls, tool calls, connector usage and failed calls.
- Attribute consumption to product, team, environment and business owner.
- Separate pilot, production and experimental usage.
Cost controls
- Set quotas and budget alerts for API, token and connector usage.
- Apply rate limits for expensive or high-volume tools.
- Require approval for agents that call paid external APIs or high-cost models.
Value review
- Review active use, repeat use, support demand, quality failures and avoided manual effort.
- Retire unused agents and duplicated connectors.
- Prefer shared MCP servers and reusable prompt/tool patterns over one-off builds.
Release gates and default decision path
The release decision is based on capability, action tier, data exposure, operational support and evidence. A gate that fails blocks release until remediated or formally accepted by the accountable risk owner.
Classify the use case
Purpose, users, data, systems, autonomy level, business impact and accountable owner.
Classify the action tier
Read, write, destructive, privileged or high-impact. The highest tier drives the release gate.
Apply release gates
Access, injection, schema, monitoring, approval, support, rollback and FinOps checks.
Operate with evidence
Catalogue status, logs, support pathway, incident handling, cost tracking and lifecycle review.
Minimum release gates
- Named business owner and platform owner recorded.
- Agent and MCP server registered in the catalogue.
- Data class and action tier recorded for every tool.
- Access policy validated against least privilege.
- Support category and incident owner available before go-live.
Pass/fail thresholds
- No high-severity prompt injection or tool misuse test remains open.
- All tool schemas validate expected, boundary and invalid inputs.
- All destructive, privileged and high-impact actions require human approval.
- Monitoring confirms correlation ID, user identity, agent identity and tool name for each action.
- Rollback or containment path is documented for every write-capable tool.
Action-tier release rule
- Read: release after access, logging and data-boundary checks pass.
- Write: release after pilot, reversibility and support checks pass.
- Destructive: release only with approval workflow, rollback and break-glass owner.
- Privileged: release only with privileged access controls and additional security review.
- High-impact: release only with accountable executive approval and monitoring review.
Non-release conditions
- Unregistered MCP server or unmanaged connector.
- Shared service account with no attributable identity.
- External or user-generated content used without injection testing.
- No incident response path for production failure.
- No method to monitor usage, cost, errors or exceptions.
Roadmap and team responsibility
Implementation begins with discovery, then platform setup, read-only pilots and scaled operations.
- Inventory agents, AI tools and MCP servers.
- Identify data classes, action tiers and business owners.
- Confirm platform owner and governance forum.
- Establish catalogue, approved connector path and release gates.
- Define action tier dictionary and evidence model.
- Integrate monitoring and support categories.
- Start with retrieval, summarisation and drafting scenarios.
- Test prompt injection, tool boundaries and access controls.
- Capture adoption, issues and evidence.
- Introduce controlled write actions with approval gates.
- Publish patterns, runbooks and platform dashboard.
- Review exceptions, incidents and lifecycle status.
Where the team comes in
The AI Experience & Platform Enabler Team owns the reusable platform layer and co-ordinates the release path. Security and data partners validate controls. Business owners approve the purpose and risk. Operations run support and incident workflows. Architecture maintains reference patterns.
Steady operating rhythm: platform backlog, fortnightly release review, monthly risk and controls forum, monthly usage and cost review, quarterly evidence and roadmap review.
Australian governance alignment
The framework maps to Australian responsible AI practices and agentic AI security guidance through accountable ownership, risk controls, testing, monitoring and human control.
| Australian guidance area | Framework alignment | Operational artefact |
|---|---|---|
| Decide who is accountable | Named agent owner, business owner and platform owner. | Agent catalogue record. |
| Understand impacts | Use case classification, data class and action tier. | Impact review summary. |
| Measure and manage risks | Control gates, access policy, prompt injection testing and monitoring. | Risk and controls record. |
| Share essential information | User disclosure, support route and operational documentation. | Service page and support article. |
| Test and monitor | Release tests, telemetry, audit logs and anomaly alerts. | Test result and dashboard. |
| Maintain human control | Approval gates for destructive, privileged and high-impact actions. | Approval and rollback record. |
Implementation reference patterns
These patterns define how enterprise teams should implement and govern MCP-connected agents.
Pattern 1: Catalogue before connection
No agent or MCP server should be available for enterprise use until it has a catalogue record, owner, purpose, data class and action tier.
Pattern 2: Read before write
Read-only use cases establish data access, quality, monitoring and support pathways before write actions are enabled.
Pattern 3: Gateway before system access
Agent traffic should pass through a governed gateway or control layer before reaching MCP servers and enterprise systems.
Pattern 4: Test adversarial content
Prompt injection and tool misuse tests are required for agents that read user-generated or external content.
Pattern 5: Evidence by design
Logs, approvals, test outcomes and exceptions are captured during normal operation, not reconstructed later.
Pattern 6: Vendor-neutral platform layer
The same catalogue, control gate and evidence model applies across Microsoft, ServiceNow, Salesforce, GitHub, Atlassian, Snowflake and internal systems.
Pattern 7: Incident path before production
Every production agent requires a defined containment, rollback, evidence preservation and re-release path.
Pattern 8: Cost control by design
API, token, licence and connector costs are monitored and attributed as part of normal platform operation.
Source links
Model Context Protocol specification
Authoritative protocol reference for MCP servers, clients, tools, resources, prompts and authorization.
Open official MCP specificationMCP introduction
Official overview describing MCP as an open standard for connecting AI applications to external systems.
Open MCP introductionMCP authorization
Official authorization guidance, including protected resource metadata used by clients to discover authorization servers.
Open MCP authorization specificationAustralian Guidance for AI Adoption
Australian Government guidance covering accountability, impact, risk, information sharing, testing, monitoring and human control.
Open Australian AI adoption guidanceACSC / Five Eyes agentic AI guidance
Guidance for careful adoption of agentic AI services, including security and operational risk considerations.
Open agentic AI guidanceMicrosoft 365 Agent Registry
Microsoft documentation for agent visibility and lifecycle management in the Microsoft 365 admin centre.
Open Microsoft Agent Registry