💰 Calculate your AI costs📅 Book a 30-min Demo📞 Call/text (571) 293-0242

MCP Data Flow Architecture

How AI agents connect to institutional systems through Model Context Protocol

AI Clients & Agents

MCP-Compatible Clients

Any MCP-compatible AI agent or application connects to the broker through a single interface

Agents see a unified tool catalog — they do not need to know which backend system serves each tool
MCP Protocol — tool discovery + tool calls
ibl.ai Switchboard — MCP Broker

MCP Broker

Central orchestration layer — routes requests, enforces policy, caches responses, provides observability

Query Routing

Maps tool calls to the correct MCP server based on intent and payload

RBAC Enforcement

Checks requester role against tool policy before forwarding — deny-by-default

Response Caching

Configurable TTL per tool — cached data inherits the same access controls

Observability

Logs every request and response — metrics for latency, error rates, query patterns

Compliance: FERPA enforcement at every layer — rate limiting protects source systems from overload
mTLS — mutual TLS between broker and each MCP server
MCP Servers — Higher Education

MCP Servers

Each server is a thin wrapper around one system's API — exposes capabilities as tools with defined inputs, outputs, and permissions

LMS MCP Server

Canvas, Blackboard, Moodle, Open edX, Brightspace

SIS MCP Server

Banner, Colleague, PeopleSoft, Workday Student, Jenzabar

Advising MCP Server

EAB Navigate, Starfish, SSC Campus

Degree Audit MCP Server

DegreeWorks, Stellic, uAchieve

CRM MCP Server

Slate, Salesforce, Ellucian CRM

Financial Aid MCP Server

Banner FA, PowerFAIDS, Workday FA

Identity / SSO MCP Server

Shibboleth, CAS, SAML, Azure AD

Click any server to see its tools and data flow — add new servers without changing existing agents
Scoped service accounts — each server has its own credentials
Backend Systems — Higher Education

Source Systems

Data is queried in place — MCP does not replicate or move data between systems

LMS

Canvas / Blackboard / Moodle

REST / LTI

SIS

Banner / PeopleSoft / Workday

REST / SOAP

Advising

EAB Navigate / Starfish

REST

Degree Audit

DegreeWorks / Stellic

REST / batch

CRM

Slate / Salesforce

REST

Financial Aid

Banner FA / PowerFAIDS

REST / batch

Identity / SSO

Shibboleth / Azure AD

SAML / SCIM
Security — Every Layer

MCP Security Model

Defense-in-depth — security enforced at every layer of the MCP data flow

RBAC at the Broker

Every request is checked against the requester's role before forwarding. Deny-by-default — tools must be explicitly enabled per role.

PII Minimization

Input validation before calling upstream APIs. Output filtering to strip data the requester does not need.

Scoped Service Accounts

Each MCP server authenticates with its own credentials, scoped to only the operations it needs.

Audit Logging

Every tool call is logged: requester identity, tool name, parameters, timestamp, outcome. Immutable logs routed to your SIEM.

Transport Security

mTLS between broker and servers. TLS for all external API calls. No plaintext transport anywhere in the chain.

Data Residency

MCP servers run inside your data center or cloud tenancy. Data is queried in place, not copied to external systems.

Data Flow

Complete MCP Data Flow Sequence

  1. 1AI agent or MCP-compatible client initiates a tool call (e.g., a cross-system query)
  2. 2Request arrives at the ibl.ai Switchboard MCP Broker via the MCP protocol
  3. 3Broker authenticates the requester via SSO and resolves their roles and permissions
  4. 4Broker checks RBAC policy — does this role have permission to call this tool? Deny-by-default (FERPA enforced)
  5. 5Broker routes the request to the appropriate MCP server based on the tool name and routing rules
  6. 6MCP server authenticates with its scoped service account to the backend system
  7. 7Backend system returns raw data — MCP server filters the response for PII minimization based on requester role
  8. 8MCP server writes an immutable audit log entry (requester, tool, parameters, timestamp, outcome)
  9. 9Filtered, structured result returns through the broker to the requesting agent
  10. 10Agent combines results from multiple MCP servers into a single, coherent answer for the user
Access Control

Role-Based Data Access

The broker enforces what each higher education role can see — FERPA compliance is operationalized here

Campus RoleLMSSISAdvisingDegree AuditCRMFinancial Aid
Academic AdvisorsCaseload gradesEnrollment, GPAFull (own caseload)Progress, what-if
Registrar StaffFull (all students)Full access
FacultyOwn sections onlyOwn students only
Financial Aid StaffSAP dataFull access
Enrollment MgmtProspects + admittedPackage status