Marketplace / Blueprint 07
LIVE FOUNDATIONAgents / agency

MCP Agent Hub

Give AI modular tools and data connectors without rebuilding the model layer.

Review my build
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.

Interactive platform map

Architecture in context

The focused blueprint, its required foundation, and declared recommendations.

Core Selected Automatic Required path
Blueprint 07 / Agents

MCP Agent Hub

Give AI modular tools and data connectors without rebuilding the model layer.

2 vCPU2 GB RAM5 services
01 / Problem

What this replaces

Chat interfaces answer questions but cannot safely interact with databases, crawlers, reports, documents and operational systems.

02 / Outcome

What your team gains

A standardized capability layer where MCP-capable clients can discover tools, resources and prompts and invoke permitted actions.

03 / Capability

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
04 / Architecture

How it fits the platform

AI client -> MCP protocol -> specialized MCP servers -> external systems/data/tools -> structured results back to the model.

Included services

neo4j-mcp-server, session-recall-mcp, scrapy-mcp, google-docs-mcp, grafana-reports, MCP-compatible clients

Platform requirements
05 / Delivery

From prerequisites to operation

Prerequisites
  1. MCP-capable client
  2. Tool-specific credentials
  3. Authorization and risk policy
Deployment
  1. Deploy/register MCP servers
  2. Choose local stdio vs remote Streamable HTTP
  3. Apply auth and network controls
  4. Define tool scopes
  5. Test client discovery/invocation
Configuration
  1. Tool descriptions/schemas
  2. Permissions
  3. Transport/auth
  4. Resource namespaces
  5. Rate limits
  6. Approval requirements
Operations
  1. Connector/API drift
  2. SDK compatibility
  3. Credential rotation
  4. Tool audit logs
  5. Dependency pinning
06 / Combinations

What this unlocks with other layers

MCP Agent Hub + Secure Coding Agent

Controlled Agency

Agents can act across systems while risky writes and commands remain human-gated.

AI Operations Center + MCP Agent Hub + Persistent AI Memory + Knowledge Graph & Institutional Intelligence

AI SRE Foundation

Agents can reason over the same telemetry and history humans use for diagnosis.

07 / Technology

Technology behind this capability

Model Context Protocol (MCP)MULTIPLE RUNNING SERVERSsession-recall-mcpAICORTEX nativeneo4j-mcp-serverAICORTEX nativescrapy-mcpAICORTEX nativegrafana-reportsAICORTEX nativegoogle-docs-mcpAICORTEX native