Log inSubmit server
Agenticorg logo

Agenticorg

Connects MCP clients to governed AgenticOrg agent and workflow execution with authenticated tool access.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Agenticorg

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "agenticorg": {
      "command": "npx",
      "args": [
        "-y",
        "agenticorg-mcp-server"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Automated check passed— started and listed 16 tools correctly (1d ago).

Overview

agenticorg MCP server exposes AgenticOrg's authenticated agent and workflow runtime through MCP discovery and execution paths. It is designed for governed operations, including tool invocation, tenant and role boundaries, human approvals, policy checks, and audit records. Reach for it when an MCP-compatible client needs controlled access to AgenticOrg workflows rather than direct, ungoverned provider calls.

Use cases

  • Run governed AgenticOrg workflows from an MCP client
  • Invoke tenant-scoped agent tools with authenticated access
  • Route business processes through human approval queues
  • Audit agent and workflow activity
  • Connect configured enterprise workflows to MCP-compatible applications

Key features

  • Authenticated MCP discovery and execution
  • Agent and workflow runtime access
  • Scoped tools and tenant boundaries
  • Human approval and escalation controls
  • Policy checks and audit records
  • REST, SDK, CLI, and MCP developer surfaces

Tools16

What Agenticorg lets your agent do. Expand a tool for its parameters.

Verified live~1.5k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 3d ago

Recent health check succeeded.

6/6 checks healthy over the last 46d

What it can do

From the 16 tools this server returned when we ran it.

Makes network requests · 1Read-only tools · 16
Network at startup3 connections
Files written at startupNone
Install scriptsNone
npm provenanceNot published
Package age204 days
Maintainers1

Observed 2026-10-22 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 13d ago via OSV.dev · agenticorg-mcp-server (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars13Stargazers on the source repository.
npm downloads222Package downloads in the last 30 days.
Last commit3d agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed16Callable tools this server registers over MCP.
Directory activity1 viewsConfig copies, upvotes, and views on AllMCPs.

How Agenticorg works

What the agenticorg MCP server does

The agenticorg MCP server provides an MCP-facing access path to the AgenticOrg platform, an enterprise system for creating, running, and governing agent workflows. AgenticOrg covers business workflows across areas such as finance, HR, marketing, operations, back-office work, communications, and bounded commerce. The repository identifies MCP as one of its developer access surfaces alongside REST APIs, Python and TypeScript SDKs, a CLI, and A2A interfaces.

The agenticorg MCP server is intended for authenticated discovery and execution. It connects MCP clients to platform capabilities rather than acting as a standalone model runtime. The underlying platform supports built-in and tenant-created agents, workflow definitions and runs, schedules, conditions, approvals, persisted execution state, model routing, retry handling, and confidence-aware execution.

Access is governed by the active tenant and role context. The platform includes scoped tools, policy checks, human-in-the-loop queues, escalation conditions, audit records, and kill-switch patterns. External actions remain dependent on the credentials, scopes, provider access, and tenant configuration required by the target connector or channel.

How it works

AgenticOrg uses a FastAPI and LangGraph runtime for agent and workflow execution. MCP discovery and authenticated execution sit alongside the platform's other public developer interfaces.

A request can involve an agent, a workflow, or a registered tool, but execution remains subject to AgenticOrg's governance controls. Connector registration alone does not prove that a provider is connected or usable. A connector may still require tenant authorization, valid credentials, approved scopes, a health check, and provider availability. Similar restrictions apply to voice, document processing, browser automation, commerce, and other configured channels.

Human review is part of the platform's operating model. Approval queues and configurable escalation conditions can keep a workflow from completing an external action without an authorized decision. Audit records capture governed runtime activity, while tenant and role boundaries restrict which users or agents can reach particular operations.

The agenticorg MCP server therefore fits integrations that need MCP access to AgenticOrg's governed runtime.

Limitations and notes

The repository describes a source implementation and platform capability set; it does not establish that every feature is enabled for every hosted tenant. Model providers, connectors, OCR, voice, browser RPA, Jev, commerce actions, and other external capabilities can be configuration- or provider-dependent.

Live product totals are published by a runtime product-facts endpoint and can change independently of documentation releases. Treat the agenticorg MCP server as an authenticated gateway into a governed platform, and confirm deployment-specific availability before relying on a particular connector or action.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Agenticorg

agenticorg is an MCP server that connects MCP clients to the AgenticOrg enterprise agent and workflow runtime. It exposes authenticated discovery and execution paths for agent workflows, tool invocation, and governed operations, with access controlled by tenant configuration, credentials, scopes, and policies.

It identifies an MCP server package and authenticated execution paths, so consult the repository's technical documentation for the current installation, transport, and authentication instructions.

AgenticOrg controls access through authentication, tenant and role boundaries, scoped tools, policy checks, required credentials, provider scopes, and tenant configuration. Human approval queues and escalation conditions can also be required before governed workflow actions proceed.

Related MCP servers

All in Coding Agents All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewAgenticorg AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/agenticorg?style=directory)](https://allmcps.com/mcp/agenticorg)
HTML Embed
<a href="https://allmcps.com/mcp/agenticorg"><img src="https://allmcps.com/api/badge/agenticorg?style=directory" alt="Agenticorg on AllMCPs" /></a>