Marketplace
LIVE FOUNDATIONAgents / agency
MCP Agent Hub
Give AI modular tools and data connectors without rebuilding the model layer.
Core MCP servers (graph, memory, research, reporting) are running in the census. The Google Docs connector is currently disabled (OAuth non-functional) and is not sold as an active capability.
Live workload cutawayArchitecture in context
MCP Agent Hub
Signal path active5 deployment units
What this replaces
Chat interfaces answer questions but cannot safely interact with databases, crawlers, reports, documents and operational systems.
What your team gains
A standardized capability layer where MCP-capable clients can discover tools, resources and prompts and invoke permitted actions.
What is inside the blueprint
MCP tools for model-controlled actions
Resources for contextual/read-only data
Prompts/templates
stdio and Streamable HTTP transports
Server notifications/streaming patterns
Authorization for HTTP transports
Sampling and elicitation support in modern SDKs
Task/logging/completion capabilities depending on server/client
Composable custom MCP servers for graph, recall, reports and crawling
How it fits the platform
AI client -> MCP protocol -> specialized MCP servers -> external systems/data/tools -> structured results back to the model.
Included services
graph-mcp-server, session-recall-mcp, crawler-mcp, docs-connector-mcp, report-service, MCP-compatible clients
Platform requirements
- AICORTEX Core PlatformMCP servers are Core-managed containers behind Core's ingress.
From prerequisites to operation
Prerequisites
- MCP-capable client
- Tool-specific credentials
- Authorization and risk policy
Deployment
- Deploy/register MCP servers
- Choose local stdio vs remote Streamable HTTP
- Apply auth and network controls
- Define tool scopes
- Test client discovery/invocation
Configuration
- Tool descriptions/schemas
- Permissions
- Transport/auth
- Resource namespaces
- Rate limits
- Approval requirements
Operations
- Connector/API drift
- SDK compatibility
- Credential rotation
- Tool audit logs
- Dependency pinning
What this unlocks with other layers
Controlled Agency
Agents can act across systems while risky writes and commands remain human-gated.
AI SRE Foundation
Agents can reason over the same telemetry and history humans use for diagnosis.
Technology behind this capability
Model Context Protocol (MCP)Session recall MCP serverAICORTEX nativeGraph MCP serverAICORTEX nativeCrawler MCP serverAICORTEX nativeReport serviceAICORTEX nativeDocument connector MCPAICORTEX native