How much does Mendix cost?

Free plan for building and testing. Standard starts at $1,090 a month for one app or $2,725 a month for unlimited apps; Premium is custom. Named end users are billed per app per month on top, with anonymous users and developers free, and compute is not included for Standard or Premium. Mendix Cloud GenAI model and knowledge base capacity is sold as separate resource packs.

Does Mendix support MCP and tool calling?

Full under the Agentic Index verification standard. Mendix publishes public evidence of Model Context Protocol (MCP) support, tool calling, and API or SDK extensibility for connecting agents to external tools. Evidence basis: Documented interfaces for the vendor's own platform: the MCP Server module makes Mendix business logic available to any agent in the enterprise, agents can be created programmatically, Mendix publishes the Platform SDK and Model SDK plus RE. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Does Mendix have SOC 2, SSO and role based access control?

Full under the Agentic Index verification standard. Mendix publishes public evidence of enterprise security and identity controls, covering a compliance posture such as SOC 2 or ISO 27001, single sign on (SSO or SAML), and role based access control (RBAC). Evidence basis: Both halves documented. Compliance: ISO 22301, ISO/IEC 27001:2022, 27017, 27018 and 27701, ISO 9001, ISAE 3000 and 3402 Type II, SOC 1 and SOC 2 Type II, and C5 Type II, with PCI DSS Level 1 and NEN 7510 named on the governance page. Access. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Back to vendors

Mendix

Q: Who is Mendix for?

enterprise, mid-market, public sector, manufacturing, financial services, IT teams

Also known as: Mendix, Mendix Agents Kit, Mendix Agent Commons, Mendix Agent Editor, Mendix Cloud GenAI, Mendix, a Siemens business

Visit site

Agent buildersubsidiaryVerified 2026-10-02

Entry price$1,090/mo, Standard (one app) plus per user fees · free planFull pricing detail

Siemens' enterprise low code platform with Agents Kit: chat and task agents that call microflows and MCP tools, ground on knowledge bases, pause for human approval per tool, test in bulk, and deploy from Mendix Cloud to air gapped on premises.

Mendix is Siemens' enterprise low code platform, and its Agents Kit turns agents into a native part of the apps teams already build there. Agents are defined in two ways: at design time as version controlled documents in Studio Pro with the Agent Editor, or at runtime in an Agent Builder interface supplied by the Agent Commons module, where an admin can write prompts, pick a model, attach tools and knowledge bases, test, and switch the active version without redeploying the app.

Tools are microflows, the platform's own logic units, plus any tools from an MCP server, so an agent can act on whatever the app is wired to, from SAP and Snowflake to internal REST services. Knowledge bases connect for autonomous retrieval with configurable chunk counts and similarity thresholds. Chat agents serve conversational interfaces, while task agents run background jobs or act as subagents in an agent as tool pattern. Both can be called from microflows, and BPMN workflows include an AI agent task.

Oversight is built into the framework. Each tool can carry human in the loop settings that control whether a call needs the user's approval and whether it is shown, and the Conversational UI module handles those approvals in chat. Agents can be tested with multiple sets of test values run in bulk and compared, exported between environments, and traced through GenAI Commons.

The platform carries one of the deepest compliance stacks in the index: ISO 27001, 27017, 27018 and 27701, SOC 1, 2 and 3 Type II, ISAE 3000 and 3402, C5 Type II and PCI DSS. It deploys on Mendix Cloud, a dedicated single tenant cloud, Azure, Kubernetes, SAP BTP, on premises, or an air gapped Private Mendix Platform.

Vendor details

Canonical URL

https://www.mendix.com

Subcategory

Enterprise low code platform with an agent framework

Funding status

Owned by Siemens (Mendix, a Siemens business). Not separately funded.

Company status

subsidiary

Use cases & customers

Primary use cases

agents embedded in enterprise low code appstask agents running background jobs and subagentsAI agent tasks inside BPMN workflowsexposing enterprise business logic to other agents over MCPregulated deployments needing on premises or air gapped agents

Target customers

enterprisemid-marketpublic sectormanufacturingfinancial servicesIT teams

Deployment options

Mendix CloudMendix Cloud Dedicated (single tenant)Mendix on AzureMendix on KubernetesSAP BTPon premises (Windows, Linux, Docker)Private Mendix Platform, including air gapped installs

Integrations

Agents use Mendix microflows as tools, so anything a Mendix app can reach becomes an agent action: REST, OData and SOAP services, databases, SAP, Snowflake, AWS services, Teamcenter and other Marketplace connectors. The MCP Client module adds tools from external MCP servers, and the MCP Server module exposes Mendix logic to any agent in the enterprise. Model connectors cover Mendix Cloud GenAI, OpenAI, Amazon Bedrock, Google Gemini, Mistral and Snowflake Cortex, and knowledge bases run on Mendix Cloud GenAI, Bedrock, OpenAI or PgVector.

In practice

A support team ships a conversational agent from the Agent Builder Starter App that looks up orders through microflows and asks the agent user to approve before issuing a refund.

An operations app adds an AI agent task to a BPMN workflow so a task agent classifies incoming claims before a human reviewer picks them up.

A manufacturer exposes Teamcenter backed microflows through the MCP Server module so agents elsewhere in the company can query product data.

Sources & related URLs

Related / legacy domains

https://docs.mendix.com/agents/ https://www.mendix.com/trust https://www.mendix.com/evaluation-guide/security/

Research sources

https://docs.mendix.com/agents/ https://docs.mendix.com/agents/agents-kit-2/ https://docs.mendix.com/agents/agents-kit-2/reference-guide/agent-commons/ https://github.com/mendix/docs/pull/11285/files https://www.mendix.com/evaluation-guide/security/ https://www.mendix.com/trust https://mendix.com/pricing

Agentic Index coverage score

12.5 / 14 capabilities · 89%

Integrations & Tool Calling	Full
Agents act through tools the admin attaches: microflows, which the model calls by function calling with inputs it determines, and tools from any MCP server configured in the MCP Client module, either all of a server's tools or a selected subset with editable fields. Microflows reach REST, OData and SOAP services, databases and Marketplace connectors such as SAP and Snowflake. Mendix Agent Commons reference (Agents Kit 2), 2 Oct 2026. Sourcedocs.mendix.com/agents/agents-kit-2/reference-guide/agent-commonsread 2026-10-02
Workflow Orchestration	Full
Agents compose with each other and with process logic: task agents serve as subagents in an agent as tool setup, chat agents can be called conversationally by another agent, both are called from microflows and workflows by drag and drop activities, BPMN workflows include an AI agent task, and the GenAI Showcase App demonstrates multi agent patterns. Mendix Agent Commons reference and Agents Kit 2 overview, 2 Oct 2026. Sourcedocs.mendix.com/agents/agents-kit-2/reference-guide/agent-commonsread 2026-10-02
Knowledge Grounding & RAG	Full
Maintained knowledge bases attach to agents for autonomous retrieval, with platform supported connectors for Mendix Cloud GenAI, Amazon Bedrock, OpenAI and a PgVector knowledge base; retrieval parameters (number of chunks, similarity threshold) are configurable, and multiple named knowledge bases can be attached for the model to choose between. Mendix Agent Commons reference, Adding Knowledge Bases, 2 Oct 2026. Sourcedocs.mendix.com/agents/agents-kit-2/reference-guide/agent-commonsread 2026-10-02
Human Oversight & Guardrails	Full
Vendor shipped approval before the action commits: tools carry configurable human in the loop controls for execution approval and visibility, and when a tool call is set for user visibility the agent returns the requested call instead of executing it; the Conversational UI module supports these approvals out of the box. Guardrails are named among the agentic patterns Agent Commons supports. Mendix Agent Commons reference and GenAI glossary, 2 Oct 2026. Sourcedocs.mendix.com/agents/agents-kit-2/reference-guide/agent-commonsread 2026-10-02
Security, Identity & Governance	Full
Both halves documented. Compliance: ISO 22301, ISO/IEC 27001:2022, 27017, 27018 and 27701, ISO 9001, ISAE 3000 and 3402 Type II, SOC 1 and SOC 2 Type II, and C5 Type II, with PCI DSS Level 1 and NEN 7510 named on the governance page. Access: agent definition is gated by the AgentCommons.AgentAdmin module role inside Mendix app security, with SSO, access restriction profiles and Control Center administration on the platform. Mendix evaluation guide security and governance pages, trust page and Agent Commons reference, 2 Oct 2026. Sourcemendix.com/evaluation-guide/securityread 2026-10-02
Observability & Auditability	Full
Runtime tracing of agent behavior: the GenAI Commons module supports traceability to debug and monitor agents, agent versions are stored as snapshots with an in use version selected per environment, and the platform adds logs, metrics and OpenTelemetry export. Medium because the traceability page itself was not read; the claim comes from Mendix's GenAI glossary in its docs repository. Mendix GenAI glossary and Agent Commons reference, 2 Oct 2026. Sourcegithub.com/mendix/docs/pull/11285/filesread 2026-10-02
Memory & State Persistence	Partial
Conversation state within a chat: chat agents receive an alternating user and assistant history through the Call Agent w/ History activity and chat contexts, while task agents run without historical context. Prompt variables pull session context at runtime. No memory layer with a stated scope and lifetime across conversations is documented. Mendix Agent Commons reference, 2 Oct 2026. Sourcedocs.mendix.com/agents/agents-kit-2/reference-guide/agent-commonsread 2026-10-02
Deployment & Data Residency	Full
Named customer environment options: Mendix Cloud, Mendix Cloud Dedicated (single tenant), Mendix on Azure, Mendix on Kubernetes, Mendix on StackIT and Mendix on Server, plus SAP BTP and the Private Mendix Platform with a documented air gapped installation; agents deploy as part of the app model. Mendix pricing page deployment table and docs navigation, 2 Oct 2026. Sourcemendix.com/pricingread 2026-10-02
Prebuilt Agents, Templates & Packs	Full
Customer adoptable starting points on the Mendix Marketplace: the Agent Builder Starter App ships a working conversational support agent with tools, knowledge base and human in the loop already wired, the Blank GenAI App comes preloaded with model connectors and Agent Commons, and the GenAI Showcase App holds example multi agent, MCP, RAG and function calling patterns. Medium because the catalog is a handful of starters rather than a broad agent gallery. Mendix agents overview and Agents Kit pages, 2 Oct 2026. Sourcedocs.mendix.com/agentsread 2026-10-02
Triggers & Channel Coverage	Full
Agents run wherever app logic calls them: task agents are designed for background processes, the Call Agent activities sit in microflows (which the platform starts from scheduled events, published REST operations, business events and page actions) and in BPMN workflows, and chat agents serve Conversational UI chat interfaces. Medium because the wake paths are platform features around the agent rather than documented on the agent pages themselves. Mendix Agent Commons reference and Studio Pro docs navigation, 2 Oct 2026. Sourcedocs.mendix.com/agents/agents-kit-2/reference-guide/agent-commonsread 2026-10-02
Model Flexibility & Routing	Full
Customer model choice per agent version: each version is associated with a deployed model from any GenAI Commons connector (Mendix Cloud GenAI, OpenAI, Amazon Bedrock, Google Gemini, Mistral, Snowflake Cortex), with temperature, top P and max tokens configurable, and teams can build their own connector. Mendix Agent Commons reference and Agents Kit 2 navigation, 2 Oct 2026. Sourcedocs.mendix.com/agents/agents-kit-2/reference-guide/agent-commonsread 2026-10-02
APIs, SDKs & MCP Extensibility	Full
Documented interfaces for the vendor's own platform: the MCP Server module makes Mendix business logic available to any agent in the enterprise, agents can be created programmatically, Mendix publishes the Platform SDK and Model SDK plus REST APIs for apps, deployments, builds, pipelines and audit logs, and deploy APIs are also offered to AI agents over MCP. Mendix Agents Kit 2 overview, GenAI glossary and API documentation index, 2 Oct 2026. Sourcedocs.mendix.com/agents/agents-kit-2read 2026-10-02
Testing, Debugging & Optimization	Full
Stored test runs with comparison: Agent Commons includes logic to define and run tests individually or in bulk with result comparisons, multiple sets of test values can be saved and run together against an agent version in an isolated environment, and versions are compared before one is made active. Medium because no scoring or automated judge is documented. Mendix Agent Commons reference, Testing and Refining the Agent, 2 Oct 2026. Sourcedocs.mendix.com/agents/agents-kit-2/reference-guide/agent-commonsread 2026-10-02
Browser & Computer Use	Unable to verify
No browser, desktop or remote computer control by agents is documented in Agents Kit. Near miss: Mendix's ATS test automation drives browsers through Selenium, but it is a testing product, not an agent capability. Mendix agents overview and docs navigation, 2 Oct 2026. Sourcedocs.mendix.com/agentsread 2026-10-02

The Agentic Index coverage score grades every vendor Full, Partial or Unable to verify against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded

Recent platform changes

2026-09-30·Agent capabilityVerified

In Studio Pro 11.15.0, Maia, the Mendix development agent, can start and stop the local runtime, check its status and read its logs, so it can test the changes it makes. The same release has Maia ask before running tools that reach external resources or make changes, with allow once, for the session or always.

Bears on: Human approval / guardrails

View source

View all 1 change for Mendix →Tracked since Sep 2026 · Verified from public vendor sources

Pricing

$1,090/mo, Standard (one app) plus per user fees · free plan

platform package fee per app or unlimited apps, plus named end users per app per month; compute and GenAI resource packs separate

Free tierTrial available

Included quota

Standard: up to 3 environments per app and business hours support. Premium: flexible environments and 24/7 support.

What is public

Package names, starting monthly prices for Standard (one app and unlimited apps), environment counts, support levels and deployment options are published on 2 Oct 2026. Per user rates and Premium are not.

Billing mechanics

Monthly package fee for one app or unlimited apps, plus a per user per app fee for named end users. Anonymous users and developers are not charged.

Cost watchouts

End user fees per app per month sit on top of the package price. Standard and Premium exclude the compute an app runs on. Mendix Cloud GenAI model and knowledge base capacity is sold as separate resource packs whose prices were not retrieved; other model providers bill directly.

Variable cost rationale

The package price is a floor: end user fees scale with adoption, compute is extra on paid packages, and GenAI capacity is bought separately.

Additional watchouts

Model the end user count first; at enterprise scale it usually outweighs the package fee.

Overage / add-ons

Additional named end users add a monthly per user fee that falls as volume grows; external users get lower rates.

Sales call required

Mixed (some tiers require a call)

Free / trial

Free plan for building and testing apps, including Agents Kit

Lowest paid plan

Standard at $1,090 a month for one app

Commercial notes

Free plan is self serve; Standard and Premium go through sales, with deployment on Mendix Cloud, Dedicated, Azure, Kubernetes, StackIT or customer servers.

Key ambiguities

Per user rates and GenAI resource pack prices are not shown on the pricing page.

Missing data

Per user rates, GenAI resource pack prices and Premium pricing.

Agentic Index verified 2026-10-02

Official pricing page

Data confidence: high