Intelligence & observability layer for AI agents
Datagran loads your agents with the intelligence they need through integrations, while acting as a safety and control layer that ensures every action is traceable, compliant, and secure.
Live Observability
AIC (AI Interaction Controller)
The AIC is the enforcement engine that lives inside Datagran. It handles risk scoring, request shaping, policy enforcement, approval flows, observability, and replay. Every LLM action flows through it.
Create a new campaign with $5,000 budget
This request exceeds the auto-approval limit ($1,000). I've flagged this for human review before execution.
1. Risk Scoring
Evaluates context, intent, and historical patterns.
2. Policy Enforcement
Checks against budget limits, allowed actions, and targets.
3. Observability
Logs full trace, including prompt, response, and API payload.
How It Works
Complete control in five steps
Create Partner Account
Sign up and set up your organization workspace.
Connect AI Platform
Integrate Claude, Lovable, Replit or any AI platform via MCP or API.
Visualize Flow
See AI interactions and data flow in real-time in the partner portal.
Enable Rules
Set up guardrails, budget limits, and approval policies for your agents.
Create Personas
Define synthetic personas to flag bad intent or analyze output quality.
Case Studies
See how enterprises are securing their AI
Marketing AI with Full Observability and Control
Challenge
Needed a way to safely give AI agents access to marketing systems without risking campaign tampering, data leaks, or untraceable decisions.
Solution
Implemented Datagran as middleware between AI agents and ad platforms (Meta, Google Ads). Provided a secure proxy, real-time observability, and automated performance reporting.
Results
- 100% visibility into all AI-initiated ad actions
- Improved ad performance through automated content learning
- Full audit trails for marketing ops and leadership
- Reduced risk of unauthorized changes
Securing AI Agents in Government Customer Support
Challenge
Deploying AI agents in sensitive support roles requiring access to CRMs and APIs, while meeting strict government compliance and audit standards.
Solution
Integrated Datagran as a control layer to enforce fine-grained action control, real-time monitoring, and risk evaluation for every API call.
Results
- Met internal/client security requirements for AI
- prevented unauthorized or destructive calls
- Enabled broader AI rollout in sensitive workflows
- Built trust through transparent tracking
Platform Features
Comprehensive protection for your AI infrastructure
AI Risk Evaluator
Real-time evaluation of every LLM request. Analyzes context, action type, system targeted, request volume, and partner-specific rules to determine if a request is safe.
Observability & Replay
A live console where Partners can see every request in and out. Drill down by user, intent, integration, risk, or model. Rewind time, replay actions, and instantly block abuse patterns.
Behavioral Anomaly Detection
Datagran continuously learns how each AI agent behaves—based on action types, intent patterns, frequency, targets, and context. Automatically flags or blocks deviations.
Synthetic Persona Evaluation
Create synthetic user personas to test how AI agents respond in controlled, repeatable scenarios. Simulate prompts, stress-test policies, and evaluate output accuracy.
The Evolution of MCP
Datagran is not a traditional MCP. We are an intelligent proxy that gives your LLMs total creative freedom while you maintain absolute control.
The LLM
Creates requests in real-time based on training.
POST /ads/createDatagran Proxy
- Validates Intent
- Enforces Policy
- Shapes Request
Real Systems
Executes only compliant, safe actions.
MCP Server for AI Agents
Connect Claude, Cursor, Replit, or any MCP-compatible AI to marketing APIs instantly
MCP Server URL
Add this to your MCP client configuration
https://datagran-mcp.fly.dev/mcpClaude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"datagran": {
"url": "https://datagran-mcp.fly.dev/mcp"
}
}
}Cursor IDE
Add to your .cursor/mcp.json:
{
"mcpServers": {
"datagran": {
"url": "https://datagran-mcp.fly.dev/mcp"
}
}
}Available Tools
check_connection_status
Check if a provider is connected
show_marketing_console
Open OAuth widget to connect
execute_script
Run API calls on connected accounts
Supports Facebook Ads • Instagram • Google Ads • Google Drive • LinkedIn Ads • TikTok Ads • Postgres / Supabase
Integrations
Connect to the platforms your users love
Available Now
Facebook Ads
Access ad accounts, campaigns, ad sets, and performance metrics.
Facebook Leads
Capture lead submissions via the dedicated leads_retrieval scope.
Read account insights via the instagram_manage_insights scope.
Google Ads
Auto-link to our manager, execute scripts, and centralize spend + performance.
LinkedIn Ads (Closed Beta)
Map Sponsored Accounts once and launch campaigns or creatives via our proxy. Scopes: r_ads_reporting · rw_organization_admin · r_ads · rw_ads.
Google Drive
Read files, metadata, and exports via our secure proxy.
TikTok Ads
Full marketing API access—advertisers, campaigns, reporting, leads, measurement, and ad comments.
Postgres / Supabase
Full SQL proxy with encrypted credentials, SSRF protection, audit logs, and query observability.
Bank-Level Security
Your users trust you with their data. We protect it like our own.
AES-256-GCM Encryption
All OAuth tokens are encrypted at rest using military-grade AES-256-GCM encryption. Each token has its own unique initialization vector and authentication tag for maximum security.
Zero Token Exposure
Tokens never touch your application or frontend. All API requests go through our secure data proxy—your partners only receive the data they need, never the raw credentials.
PKCE OAuth Flow
We implement OAuth 2.0 with PKCE (Proof Key for Code Exchange) to prevent authorization code interception attacks. Every auth session has unique challenge/verifier pairs.
API Key Hashing
Partner API keys are hashed with bcrypt (10 rounds) before storage. We never store plain-text keys—even we can't see your partners' credentials after creation.
Origin Whitelisting
Strict CORS enforcement and origin validation. The auth widget only opens from pre-approved domains, preventing unauthorized access attempts and phishing attacks.
Audit Logs
Complete audit trail of all authentication events, token refreshes, and API access. Track every action for compliance and security monitoring.
Data Deletion & Compliance
Full GDPR compliance with automated data deletion workflows. When users disconnect or delete their accounts, we automatically revoke tokens and purge all related data from our systems.
Ready to Secure Your Agents?
Stop worrying about AI risks. Get observability and control in minutes.