MCP Hub
Back to servers

agenticorg

Validated

Run 25+ enterprise AI agents and 269 tools with human-in-the-loop governance

Registry
Stars
3
Forks
1
Tools
10
Updated
Apr 1, 2026
Validated
Apr 2, 2026
Validation Details

Duration: 5.7s

Server: agenticorg v0.1.0

Quick Install

npx -y agenticorg-mcp-server

AgenticOrg

AI Virtual Employee Platform — 25 pre-built agents that reason AND act. Agents call real APIs (Jira, HubSpot, GitHub) — not just generate text. 42 connectors, 269 tools, human-in-the-loop governance, no-code builder.

Live License Python React Tests E2E

Live: https://agenticorg.ai | App: https://app.agenticorg.ai | Playground: https://agenticorg.ai/playground


What Is AgenticOrg?

AgenticOrg deploys AI virtual employees that automate enterprise back-office work. Each agent has a name, designation, specialization, and tailored instructions — like a real team member. They process invoices, run payroll, triage support tickets, launch campaigns, and reconcile bank statements — with human approval on every critical decision.

Key Numbers

MetricValue
Pre-built Agents25 across 5 domains
Custom Agents37+ created on demo tenant (unlimited via no-code wizard)
Enterprise Connectors42 connectors, 269 tools
Live Connectors (verified)GitHub (9 tools), Jira (11 tools), HubSpot (13 tools)
Prompt Templates27 production-tested
Automated Tests1,031 (unit + security + connector + synthetic + functional)
Production E2E125/125 pass (100%) against live deployment
LLMGemini 2.5 Flash (primary), Claude/GPT-4o fallback
DeploymentGKE Autopilot, ~$95/month

What It Does

BeforeAfter
5-day month-end close1 day with AP + Recon + Close agents
Manual invoice processing11 seconds per invoice (OCR → GSTIN → 3-way match → GL)
40% ticket mis-routing88% auto-classification accuracy
2-week employee onboarding4 hours (Darwinbox + Slack + email auto-provisioned)
Manual bank reconciliation99.7% auto-match rate, done by 6 AM daily
Zero payroll errorsPF, ESI, TDS computed automatically

Agents That Act, Not Just Talk

Unlike AI chatbots that only generate text, AgenticOrg agents execute real actions:

You: "Production API returning 500 errors. CloudSQL connection pool exhausted."

Ops Commander (Aria Singh):
  → Gemini reasons about severity (636 tokens, 2.6s)
  → Creates Jira ticket KAN-5 via real API (1.1s)
  → Sets priority to Highest, assigns engineering team
  → Returns analysis + ticket link to you

Verified on production: agents have created 14 real Jira tickets, read HubSpot CRM data (contacts, deals, companies), and queried GitHub repo statistics — all through the LLM → tool_calls → connector → API pipeline.


Architecture

Landing Page (animations, interactive demo, blog, SEO)
    ↓
App Dashboard (agents, workflows, approvals, audit, sales pipeline)
    ↓
FastAPI Backend
    ├── Agent Registry → LLM Router (Gemini 2.5 Flash)
    │       ↓ tool_calls                    ↑ synthesis
    │   Tool Gateway → 42 Connectors (269 tools)
    │       ├── Jira (11 tools) ← verified, creates real tickets
    │       ├── HubSpot (13 tools) ← verified, reads real CRM
    │       ├── GitHub (9 tools) ← verified, reads real repos
    │       └── SAP, Oracle, GSTN, Darwinbox, Slack, Stripe...
    ├── Workflow Engine → real agent execution → HITL Queue
    ├── NEXUS Orchestrator → Audit Logger
    └── Sales Agent → Gmail API → Email Sequences
    ↓
PostgreSQL (Cloud SQL) + Redis + GCS

Agent Domains

DomainAgentsKey Agents
Finance6AP Processor, AR Collections, Reconciliation, Tax Compliance, Month-End Close, FP&A
HR6Talent Acquisition, Onboarding, Payroll Engine, Performance Coach, L&D, Offboarding
Marketing5Content Factory, Campaign Pilot, SEO Strategist, CRM Intelligence, Brand Monitor
Operations5Support Triage, Contract Intelligence, Compliance Guard, IT Operations, Vendor Manager
Back Office3Risk Sentinel, Legal Ops, Facilities Agent
Sales1Automated sales agent (qualification, email sequences, pipeline)
Custom37+ on demoCreate via 5-step no-code wizard — unlimited

Core Features

Virtual Employee System

Each agent is a virtual employee with persona, specialization, and routing:

  • Employee name (Priya, Arjun, Maya) — appears in audit logs and approvals
  • Designation (Senior AP Analyst - Mumbai) — role clarity
  • Specialization (Domestic invoices < 5L) — task routing
  • Multiple agents per role — 3 AP Processors for different regions with smart routing

Organization Chart

Visual tree hierarchy per department. Each agent has an org_level field (e.g., Head → Manager → Analyst) and a parent reference, forming a reporting chain used for smart escalation — when an agent's confidence is below threshold, the task auto-escalates to its parent in the org tree. CSV bulk import lets you onboard entire departments in one upload.

No-Code Agent Creator

5-step wizard: Persona → Role → Prompt → Behavior → Deploy as Shadow

Prompt Template Library

27 production-tested templates with {{variable}} substitution. Built-in templates are read-only — clone to customize. Full prompt audit trail with edit history. Prompt lock on active agents.

Human-in-the-Loop (HITL)

Configurable confidence floors, trigger conditions, escalation chains, and timeout rules. Every HITL decision logged in audit trail. Agents cannot bypass their own gates.

RBAC

  • CEO/Admin: Full access, all domains
  • CFO: Finance agents only
  • CHRO: HR agents only
  • CMO: Marketing agents only
  • COO: Operations agents only
  • Auditor: Read-only audit log

Sales Agent

Automated lead qualification, personalized email outreach, follow-up sequences (Day 1/3/7/14), Gmail inbox monitoring, and pipeline dashboard. Demo request form → instant personalized response.

42 Enterprise Connectors

Finance: Oracle Fusion, SAP, Tally, GSTN, Stripe, QuickBooks, Zoho Books, Banking AA, Income Tax India, Pine Labs HR: Darwinbox, Okta, Greenhouse, LinkedIn Talent, DocuSign, Keka, Zoom, EPFO Marketing: Salesforce, HubSpot, Google Ads, LinkedIn Ads, Meta Ads, Ahrefs, Mixpanel, Buffer, Brandwatch Ops: Jira, ServiceNow, Zendesk, PagerDuty, Confluence, Sanctions API, MCA Portal Comms: Slack, GitHub, SendGrid, GCS, Google Calendar, Twilio, WhatsApp, LangSmith


Quick Start

Prerequisites

  • Python 3.12+ | Node.js 20+ | Docker

Local Development

git clone https://github.com/mishrasanjeev/agentic-org.git
cd agentic-org
cp .env.example .env  # Add your Gemini API key

# Backend
pip install -e ".[dev]"
docker compose up -d postgres redis
python -m scripts.seed_data
uvicorn api.main:app --host 0.0.0.0 --port 8000 --reload

# Frontend
cd ui && npm install && npm run dev

Docker Compose

docker compose up -d
# API: http://localhost:8000 | UI: http://localhost:3000

GKE Production

gcloud container clusters get-credentials agenticorg-lean --region=asia-south1
helm upgrade --install agenticorg ./helm -n agenticorg -f helm/values-lean.yaml

Demo Credentials

RoleEmailPassword
CEOceo@agenticorg.localceo123!
CFOcfo@agenticorg.localcfo123!
CHROchro@agenticorg.localchro123!
CMOcmo@agenticorg.localcmo123!
COOcoo@agenticorg.localcoo123!
Auditorauditor@agenticorg.localaudit123!

API Reference

Base URL: https://app.agenticorg.ai/api/v1

MethodPathAuthDescription
GET/health/livenessNoHealth check
POST/auth/signupNoCreate account
POST/auth/loginNoGet JWT token
POST/auth/googleNoGoogle OAuth
POST/auth/forgot-passwordNoRequest password reset email
POST/auth/reset-passwordNoReset password with token
POST/demo-requestNoDemo form → lead + sales agent
GET/agentsJWTList agents (RBAC filtered)
POST/agentsJWTCreate agent
POST/agents/{id}/runJWTExecute agent
PATCH/agents/{id}JWTUpdate (prompt lock on active)
GET/agents/org-treeJWTOrg chart tree (department hierarchy)
POST/agents/import-csvJWTBulk import agents via CSV
POST/agents/{id}/cloneJWTClone with persona
POST/agents/{id}/promoteJWTShadow → Active
GET/agents/{id}/prompt-historyJWTPrompt audit trail
GET/prompt-templatesJWTList templates
POST/prompt-templatesJWTCreate template
GET/sales/pipelineJWTSales pipeline
POST/sales/pipeline/process-leadJWTTrigger sales agent
POST/sales/process-inboxJWTProcess Gmail replies
GET/sales/metricsJWTWeekly digest data
GET/workflowsJWTList workflows
GET/approvalsJWTHITL approval queue
GET/auditJWTAudit log
GET/connectorsJWTList connectors
GET/connectors/{id}/healthJWTConnector health check
GET/connectors/{id}JWTConnector details
PUT/connectors/{id}JWTUpdate connector config
GET/a2a/agent-cardNoA2A agent discovery card
POST/a2a/tasksJWT/GrantexExecute A2A task
GET/mcp/toolsNoList MCP tools
POST/mcp/callJWT/GrantexCall MCP tool
POST/sop/uploadJWTUpload and parse SOP document
POST/sop/parse-textJWTParse SOP text
POST/sop/deployJWTDeploy parsed SOP as agent
POST/agents/{id}/delegateJWTGrantex delegation setup

Python SDK

pip install agenticorg
from agenticorg import AgenticOrg
client = AgenticOrg(api_key="your-key")
result = client.agents.run("ap_processor", inputs={"invoice_id": "INV-001"})

See sdk/README.md for full documentation.


Testing

# All automated tests (1,053 tests)
pytest tests/ --ignore=tests/e2e --ignore=tests/integration

# Unit tests (761 tests)
pytest tests/unit/

# Security tests (84 tests)
pytest tests/security/

# Connector harness — all 42 connectors (174 tests)
pytest tests/connector_harness/

# Synthetic data — invoice/resume/contract flows (15 tests)
pytest tests/synthetic_data/

# Full production E2E — 125 checks against live deployment
python tests/e2e_full_production_test.py

# Production connector test — real Jira/HubSpot/GitHub API calls
python tests/test_production_connectors.py
SuiteTestsWhat It Covers
Unit739Agents, registry, schemas, routing, prompts, RBAC, workflows
Security84Auth bypass, token exploits, alg:none, HITL bypass, PII
Connector harness17442 connectors × all 269 tools
Synthetic data15Invoice OCR → match, resume screening, contract analysis
Ops/Marketing functional13End-to-end workflow scenarios
Production E2E125Fresh org signup → 62 agents → workflows → HITL → audit → RBAC
Production connectors17Real API calls to Jira, HubSpot, GitHub
Total1,167125/125 production E2E at 100%

Project Structure

agenticorg/
├── api/v1/                 # FastAPI endpoints (agents, auth, sales, templates, connectors)
├── core/
│   ├── agents/             # 25 agent types + 27 prompt templates
│   │   ├── prompts/        # Production system prompts
│   │   ├── registry.py     # Agent registry (built-in + custom type fallback)
│   │   └── base.py         # BaseAgent: LLM reasoning → tool calling → HITL
│   ├── orchestrator/       # NEXUS: task routing, smart routing, state machine
│   ├── llm/                # LLM router (Gemini primary, Claude/GPT-4o fallback)
│   ├── models/             # SQLAlchemy ORM (agents, workflows, HITL, leads, templates)
│   ├── tool_gateway/       # Scope enforcement, rate limiting, PII masking, audit
│   ├── gmail_agent.py      # Gmail API integration (inbox monitor, send replies)
│   └── email.py            # SMTP email sending
├── connectors/             # 42 enterprise connectors
│   ├── finance/            # Oracle, SAP, GSTN, Stripe, Tally, Banking AA...
│   ├── hr/                 # Darwinbox, Okta, Greenhouse, EPFO, Zoom...
│   ├── marketing/          # Salesforce, HubSpot, Google Ads, Ahrefs...
│   ├── ops/                # Jira, Zendesk, ServiceNow, PagerDuty...
│   ├── comms/              # Slack, GitHub, SendGrid, GCS, Twilio...
│   └── framework/          # BaseConnector, auth adapters, circuit breaker
├── workflows/              # Workflow engine, triggers, conditions
├── ui/src/
│   ├── pages/              # Landing, Dashboard, Agents, Sales, Blog, Resources, Ads
│   ├── components/         # AgentCard, ActivityTicker, InteractiveDemo, SocialProof
│   └── pages/blog/         # 5 SEO blog articles
│   └── pages/resources/    # 26 SEO content pages across 7 topic clusters
├── tests/
│   ├── unit/               # 739 unit tests
│   ├── security/           # 84 security tests
│   ├── connector_harness/  # 174 connector tests (42 connectors × tools)
│   ├── synthetic_data/     # Invoice, resume, contract test data
│   └── e2e/                # Playwright browser tests
├── migrations/             # 8 PostgreSQL DDL files
├── helm/                   # Kubernetes Helm charts
├── docs/                   # PRD, architecture, QA test plan
└── scripts/                # Seed data, deployment helpers

SEO & AI Discoverability

AssetURLStatus
Landing pagehttps://agenticorg.ai39 URLs in sitemap
Blog (5 articles)/blogInvoice processing, RPA vs AI, reconciliation, HITL, no-code
Resources (26 pages)/resources7 topic clusters, FAQ schemas, internal linking
llms.txt/llms.txt4.6KB product summary for AI crawlers
llms-full.txt/llms-full.txt18.7KB complete documentation
JSON-LD7 schemasOrganization, Product, FAQ, Breadcrumb, SoftwareCompany, WebSite, SoftwareApplication
AI crawlersrobots.txtGPTBot, ClaudeBot, PerplexityBot, ChatGPT-User, OAI-SearchBot, cohere-ai, Applebot-Extended

Pricing

PlanPriceAgentsConnectorsTasks
Free$03520500/day
Pro$499/moUnlimited42Unlimited
EnterpriseCustomUnlimited42Unlimited + SLA

India-First Connectors

Built for Indian enterprise — not retrofitted:

  • GSTN — e-Invoice IRN, GSTR-1/2A/3B/9 filing, ITC reconciliation
  • EPFO — ECR filing, UAN verification, passbook download
  • Income Tax India — TDS 26Q/24Q, Form 16A, 26AS credit check
  • Darwinbox — HRMS (payroll, attendance, performance, onboarding)
  • Tally Prime — Accounting (vouchers, trial balance, GST reports)
  • Banking AA — RBI-compliant Account Aggregator framework

Security & Compliance

FeatureImplementation
Tenant isolationPostgreSQL RLS, Redis key namespacing, GCS prefix isolation
HITL governanceConfigurable thresholds, prompt lock on active agents, escalation chains
Audit trailEvery agent action logged, 7-year WORM retention, HMAC signed
PII maskingDefault-on masking of email, phone, Aadhaar, PAN, bank accounts
SOC-2 readyPassword policy (bcrypt 12), token blacklist, rate limiting, HSTS, CSP
Prompt auditEvery prompt edit logged with user, timestamp, before/after, reason

Documentation

DocumentDescription
PRDComplete product requirements (7 pages)
QA Test Plan65 manual test cases with steps
QA Test Cases70 automated test results
Architecture8-layer system design

Contributing

Fork → branch → test → PR. See CONTRIBUTING.md.

  • Python: ruff check . && mypy --ignore-missing-imports .
  • TypeScript: npx tsc --noEmit
  • Tests: pytest tests/unit/ tests/connector_harness/

License

Apache License 2.0 — free for commercial use. See LICENSE.


Built by Edumatica Pvt Ltd | Bengaluru, India

Reviews

No reviews yet

Sign in to write a review