Datadef is a remote MCP server that gives an AI agent 36 tools, among them canvas_add_flow_arrow, canvas_add_lineage, canvas_add_nodes. It answers at https://datadef.io/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 10 September 2026; the last check, on 19 October 2026, succeeded.
Generate, edit, and export data-architecture diagrams from your AI. Column lineage, PNG in chat.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
canvas_add_flow_arrow | Draw one large labelled arrow representing a whole flow — "ingest", "serve", "publish" — instead of many thin edges saying the same thing. Use this when several things move the same way for the same reason: draw the arrow once between the t Inputs: diagram_id, arrows |
canvas_add_lineage | Record column-level lineage: which source column produces which target column, and how. This is what makes the diagram queryable for impact analysis, so add it for every real transformation. Operates on one Datadef diagram, named by diagram Inputs: diagram_id, links |
canvas_add_nodes | Add one or more nodes to the canvas. Batch every node you want in a single call. Positions are assigned by canvas_layout_canvas afterwards — never set them yourself. Operates on one Datadef diagram, named by diagram_id. If you have not alre Inputs: diagram_id, nodes |
canvas_add_region | Draw a labelled translucent area behind existing nodes to show they belong together, without reparenting them. Use this when the grouping is a reading aid rather than real containment, when areas would need to overlap, or when a node belong Inputs: diagram_id, regions |
canvas_add_shape | Place a rectangle, circle, arrow, or line as a visual annotation — a backdrop highlighting a region, an arrow pointing something out, a divider. Shapes sit behind data nodes and are not part of the data flow. To group nodes into a labelled Inputs: diagram_id, shapes |
canvas_add_standalone_node | Add a single data node at an exact position, without connecting it to anything. Use when the user wants something placed somewhere specific, or when you will wire it up yourself afterwards. For building out a connected diagram, canvas_add_n Inputs: diagram_id, type, label, description, icon, technology |
canvas_add_text | Place a free-floating text box on the canvas — a caption, a callout, a section heading, a note explaining a decision. Position it with explicit coordinates from canvas_measure_canvas. Text boxes are annotations: they are not part of the dat Inputs: diagram_id, texts |
canvas_align_nodes | Align nodes to a shared edge or centre line, or space them evenly. Cleaner and far more reliable than computing coordinates by hand. Operates on one Datadef diagram, named by diagram_id. Inputs: diagram_id, nodes, mode |
canvas_collapse_nodes | Merge several nodes into one summary node, keeping every connection. Use when a set of near-identical objects adds length without adding meaning — eight staging models that all behave the same become "stg_* (8)". Do not use when the individ Inputs: diagram_id, nodes, label, description |
canvas_connect_nodes | Draw edges between nodes to show how data flows. Always label the edge with what actually happens ("ingest", "dbt transform", "hourly sync") — unlabelled edges make a diagram useless. Operates on one Datadef diagram, named by diagram_id. Inputs: diagram_id, edges |
canvas_describe_canvas | Get an overview of the current canvas: every node with its id, type, label and group, plus all connections and groups. Call this first, before any edit, so you work from real node ids instead of guesses. Operates on one Datadef diagram, nam Inputs: diagram_id, includeColumns |
canvas_disconnect_nodes | Remove the edge between two nodes. Operates on one Datadef diagram, named by diagram_id. Inputs: diagram_id, edges |
canvas_group_nodes | Create a labelled zone (e.g. "Bronze Layer", "Ingestion") and optionally move nodes into it. Zones are what turn a tangle of boxes into a readable architecture — use them for layers, domains, or environments. Operates on one Datadef diagram Inputs: diagram_id, label, description, parentGroup, style, family |
canvas_inspect_nodes | Get full detail for specific nodes: all columns with types and keys, metadata, schedule, formula, owners. Use before modifying a node so you preserve fields you are not changing. Operates on one Datadef diagram, named by diagram_id. Inputs: diagram_id, nodes |
canvas_layout_canvas | Arrange the canvas. Call this once at the end, after all structural edits are done — not between each edit. By default only the parts you touched are re-arranged and everything else keeps its position. Operates on one Datadef diagram, named Inputs: diagram_id, full |
canvas_measure_canvas | Get exact geometry: every node's position and size in canvas units, the overall canvas bounds, and any nodes that overlap each other. Call this before moving, resizing, or placing anything precisely — positions are meaningless without it. O Inputs: diagram_id, nodes |
canvas_move_nodes | Set node positions precisely. Use absolute x/y to place something exactly, or dx/dy to nudge it. Coordinates are absolute canvas units (same space canvas_measure_canvas reports). Moving a group moves its children with it — do not also move Inputs: diagram_id, moves |
canvas_move_to_group | Move existing nodes into an existing group, or out of any group. Operates on one Datadef diagram, named by diagram_id. Inputs: diagram_id, nodes, group |
canvas_remove_nodes | Delete nodes and every edge touching them. Deleting a group also deletes the nodes inside it — check with canvas_describe_canvas first if that is not what you want. Operates on one Datadef diagram, named by diagram_id. Inputs: diagram_id, nodes |
canvas_replace_node | Swap a node for a different one while keeping every connection, its position, and its group. Use this when a component changes — Redshift becomes Snowflake, a batch job becomes streaming — instead of deleting and rebuilding, which would los Inputs: diagram_id, node, type, label, description, icon |
canvas_resize_nodes | Set the width and height of nodes. Mostly for shapes, text boxes, and group zones — data nodes size themselves from their content, and resizing one can clip what it displays. Operates on one Datadef diagram, named by diagram_id. Inputs: diagram_id, resizes |
canvas_search_icons | Search Datadef's icon library (2000+ cloud and data-tool logos) for a valid icon id. Use it when you want a specific vendor logo and are unsure of its exact id — passing an invalid id silently falls back to a generic icon. Operates on one D Inputs: diagram_id, query, limit |
canvas_set_columns | Set the full column list of a table node, replacing whatever it had. Pass every column you want to keep — this is a replace, not a merge. Mark primary and foreign keys; they are what make a data diagram worth reading. Operates on one Datade Inputs: diagram_id, node, columns |
canvas_suggest_simplifications | Report where this canvas could be collapsed — groups of similar nodes that could become one summary node — without changing anything. Use it to decide whether the diagram is denser than it needs to be. Density is not automatically a problem Inputs: diagram_id, minGroupSize |
canvas_update_edges | Change existing connections without deleting them: fix a label, change the type, or restyle. Use this to correct a wrong edge label rather than disconnecting and reconnecting. Operates on one Datadef diagram, named by diagram_id. Inputs: diagram_id, updates |
canvas_update_nodes | Change properties of existing nodes. Only the fields you pass are touched; everything else is preserved. To replace a table's columns use canvas_set_columns instead. Operates on one Datadef diagram, named by diagram_id. Inputs: diagram_id, updates |
canvas_validate_canvas | Check the canvas for structural problems (disconnected nodes, circular data flow, broken references) and quality problems (unlabelled edges, tables without columns). Call this before you finish, and fix any errors it reports. Operates on on Inputs: diagram_id |
create_blank_diagram | Create an empty diagram and return its diagram_id, so you can build it yourself with the canvas_* tools. No AI generation runs and no credit is spent: you draw it. Use this when you want control over the result, or already know the architec Inputs: name, description |
create_diagram | Generate a professional data architecture diagram from a description and save it to the user's Datadef account. Use this for any data-shaped diagram: medallion and lakehouse architectures, ETL/ELT pipelines, streaming topologies, data mesh, Inputs: prompt, name, scope, detailed |
edit_diagram | Change an existing diagram with a natural-language instruction, add nodes, rewire connections, add columns, reorganise into layers, fill in owners and schedules. Be specific about what to change and where. "Add a Kafka topic between the API Inputs: diagram_id, instruction, include_image |
export_diagram | Render a diagram to a PNG or JPEG image. Returns the image inline AND a short-lived signed download URL. Use the inline image to show the diagram; use the URL when the user wants to save it, attach it, or share a link: it serves the file di Inputs: diagram_id, format, width, height |
get_design_guide | Datadef's standard for what makes a diagram readable, size, edge discipline, nested zones, annotations, and the tool order for building or editing. Read this BEFORE your first canvas_* call. It is the same standard Datadef's own generator f |
get_diagram | Read the full structure of a diagram: every node with its type and columns, every connection, and the groups. Use this before editing so you know what is actually there. Inputs: diagram_id, include_columns, include_image |
list_diagrams | List diagrams in the user's Datadef account, most recently updated first. Use this to find the id of a diagram before editing or exporting it. Inputs: limit |
repo_refresh | Re-sync a repo-linked diagram from the current state of its repository. If the tracked branch or tag has not moved since the last sync, nothing changes. If it has, the diagram is REGENERATED from the repository, which replaces manual canvas Inputs: project_id |
repo_status | For a diagram that was created from a connected git repository: which repo and branch or tag it tracks, when it last synced, the commit it reflects, and whether daily sync is on. Use repo_refresh to sync it now. Only the owner of the reposi Inputs: project_id |
Every block below points at https://datadef.io/mcp. Pick your client and copy.
claude mcp add --transport http datadef https://datadef.io/mcp
{
"mcpServers": {
"datadef": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://datadef.io/mcp"]
}
}
}{
"mcpServers": {
"datadef": {
"url": "https://datadef.io/mcp"
}
}
}{
"servers": {
"datadef": {
"type": "http",
"url": "https://datadef.io/mcp"
}
}
}{
"context_servers": {
"datadef": {
"url": "https://datadef.io/mcp"
}
}
}{
"mcpServers": {
"datadef": {
"serverUrl": "https://datadef.io/mcp"
}
}
}{
"mcpServers": {
"datadef": {
"url": "https://datadef.io/mcp"
}
}
}name: Datadef
version: 0.0.1
schema: v1
mcpServers:
- name: Datadef
type: streamable-http
url: https://datadef.io/mcp{
"mcpServers": {
"datadef": {
"httpUrl": "https://datadef.io/mcp"
}
}
}{
"mcpServers": {
"datadef": {
"type": "http",
"url": "https://datadef.io/mcp"
}
}
}{
"mcpServers": {
"datadef": {
"url": "https://datadef.io/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fdatadef.io%2Fmcp&type=streamable_http&id=datadef&name=Datadef
It answered our last check on 19 October 2026 in 132 ms. Over 6 checks since 10 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by datadef.io and served from datadef.io, the vendor's own domain: https://datadef.io/mcp.
36, as returned by the server's own tools/list on 12 September 2026: canvas_add_flow_arrow, canvas_add_lineage, canvas_add_nodes, canvas_add_region, canvas_add_shape, canvas_add_standalone_node, canvas_add_text, canvas_align_nodes, and 28 more.
It answered our last check on 19 October 2026 in 132 ms. Over 6 checks since 10 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://datadef.io/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.datadef. Endpoint host: datadef.io. ARD identifier: urn:air:io.datadef:mcp:mcp.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.