Build your models in days minutes.

The Koddex MCP server doesn't just read your data, it exposes modeling. From Claude, Gemini or ChatGPT, ask for the BOM of a 6-axis robot arm and the agent builds the cascading assembly tree, hundreds of components and sub-components, with linked requirements and certifications, exactly like on the Custom templates page.

claude.ai · workspace · koddex-mcp mcp connected

In Koddex, create the full BOM of a 6-axis robot arm: generate the cascading assembly tree with every component and sub-component (motors, reducers, encoders, brakes, bearings…), and link the requirements and certifications at each level.

tool ·koddex.create_item("6-axis robot arm")

tool ·koddex.add_children · Base + Axis 1…6 + end effector

tool ·koddex.add_children · 312 components across 6 levels

tool ·koddex.add_attribute · mass, torque, part number…

tool ·koddex.link · 48 requirements → components

tool ·koddex.link · ISO 10218-1 · ISO/TS 15066 · ISO 13849

Done. The assembly tree is live: 312 components across 6 levels, 48 requirements and 12 certifications linked. A change on any component will roll its impact up the whole tree.

Bill of materials · assembly tree312 components

6-axis robot armRBT-ARM-6 ISO 10218-1 CE Machinery
└Base assemblyASM-BASE
└Slew bearingBRG-140
└Cable managementCBL-SYS
└Axis 1 · ShoulderAX-1REQ-014 payload ISO/TS 15066
└Servomotor 750 WMOT-750
└Harmonic reducerHDR-50REQ-031 backlash
└Absolute encoderENC-19b
└Holding brakeBRK-24 ISO 13849 PL d
└Axis 2 · Lower armAX-2REQ-018 reach
└Servomotor 400 WMOT-400
└Harmonic reducerHDR-32
└Axes 3–6 + end effector · 214 more components

Ask Claude to build a bill of materials…

The same custom models and trees you'd build by hand, created by prompt. See Custom templates

Ask any question. Get an audited, traceable answer.

Through the Koddex MCP server, an AI agent reads your engineering data with the same scoped permissions and full audit trail as a human engineer.

claude.ai · workspace · koddex-mcp mcp connected

What's the operating temperature range of actuator J3 in WAND-EXO, and when was it last validated?

Ask Claude anything about your Koddex data…

Tools that aren't headless or API-first

Closed tools, no API

Legacy PLM/ERP suites have no headless API. You can't script them, can't integrate them, can't connect AI agents. Every workflow ends in a copy-paste.

AI agents have no scoped access

An LLM either gets an admin password (terrifying) or no access at all (useless). There's no way to give an agent read-only, audited, attribute-level access to your engineering data.

External providers can't reach the data

Suppliers need a part spec, an auditor needs a verification trace, and you ship them a PDF or a leaky drive folder, with no way to revoke access or hide confidential fields.

The Koddex way: open, scoped, auditable

Headless, fully API-first

Every Koddex object is queryable through typed REST and GraphQL endpoints. Scripts, automations and dashboards plug in directly. No scraping, no exports.

MCP-native, scoped agent access

Koddex exposes its data model through Model Context Protocol. Agents authenticate, get typed scopes, and every read or write is logged with the same granularity as a human edit.

Granular external sharing

Invite a supplier or auditor with attribute-level scopes: share the dimensions, hide the cost; share the test results, hide the BOM. Revoke in one click. Every access logged.