# io.datadef/mcp (remote · datadef.io)

Generate, edit, and export data-architecture diagrams from your AI. Column lineage, PNG in chat.

- Trust score: 92/100 (high trust)
- Change this week: +1
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- remote · `datadef.io`: 92/100 (this document), [markdown](https://verifymcp.io/servers/io-datadef-mcp/datadef.md), [page](https://verifymcp.io/servers/io-datadef-mcp/datadef)

## Channel facts

- Endpoint: `https://datadef.io/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-20.

- **Endpoint Security**: 94/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 83/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 4714 tokens (~130/item across 36 items; 36 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **Tool Coverage**: 93/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 79% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 36 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the io.datadef/mcp server?

io.datadef/mcp is a hosted endpoint at https://datadef.io/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http io-datadef-mcp 'https://datadef.io/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "io-datadef-mcp": {
      "url": "https://datadef.io/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "io-datadef-mcp": {
      "type": "http",
      "url": "https://datadef.io/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.io-datadef-mcp]
url = "https://datadef.io/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "io-datadef-mcp": {
      "type": "remote",
      "url": "https://datadef.io/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add io-datadef-mcp --url 'https://datadef.io/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  io-datadef-mcp:
    url: "https://datadef.io/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "io-datadef-mcp": {
      "Transport": "http",
      "Url": "https://datadef.io/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add io-datadef-mcp -t streamable-http -u 'https://datadef.io/mcp'
```

### Other

```json
{
  "mcpServers": {
    "io-datadef-mcp": {
      "type": "http",
      "url": "https://datadef.io/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-15 (score 92, 0)

- [security] Stability: 0.97 → pass

### 2026-09-14 (score 92, +1)

No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-11 (score 91, +1)

No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-09 (score 90, +1)

No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-07 (score 89, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-05 (score 88, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-03 (score 87, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-01 (score 86, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (36)

### `get_design_guide` (~80 tokens)

Datadef 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 follows, so a diagram you build by hand comes out indistinguishable from a generated one.

### `canvas_describe_canvas` (~149 tokens)

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, named by diagram_id.

If you have not already, call get_design_guide first: it carries Datadef's size, edge, and zone standard, and diagrams built without it read poorly.

Input parameters:

- `diagram_id` (string, required): Canvas id, from list_diagrams, create_diagram, or create_blank_diagram.
- `includeColumns` (boolean): Include a short column list for each table node. Default false.

### `canvas_inspect_nodes` (~105 tokens)

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.

Input parameters:

- `diagram_id` (string, required): Canvas id, from list_diagrams, create_diagram, or create_blank_diagram.
- `nodes` (array, required): Node ids or exact labels. Up to 10 at a time.

### `canvas_measure_canvas` (~113 tokens)

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.

Operates on one Datadef diagram, named by diagram_id.

Input parameters:

- `diagram_id` (string, required): Canvas id, from list_diagrams, create_diagram, or create_blank_diagram.
- `nodes` (array): Limit to specific node ids or labels. Omit to measure everything.

### `canvas_suggest_simplifications` (~125 tokens)

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: keep the detail when the detail is the point.

Operates on one Datadef diagram, named by diagram_id.

Input parameters:

- `diagram_id` (string, required): Canvas id, from list_diagrams, create_diagram, or create_blank_diagram.
- `minGroupSize` (integer): Smallest group worth reporting. Default 3.

### `canvas_search_icons` (~139 tokens)

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 Datadef diagram, named by diagram_id.

Input parameters:

- `diagram_id` (string, required): Canvas id, from list_diagrams, create_diagram, or create_blank_diagram.
- `limit` (integer): Max results, default 8.
- `query` (string, required): Tool or service name, e.g. "snowflake", "kinesis", "power bi".

### `canvas_add_nodes` (~123 tokens)

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 already, call get_design_guide first: it carries Datadef's size, edge, and zone standard, and diagrams built without it read poorly.

Input parameters:

- `diagram_id` (string, required): Canvas id, from list_diagrams, create_diagram, or create_blank_diagram.
- `nodes` (array, required)

### `canvas_add_standalone_node` (~176 tokens)

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_nodes is better — it batches and lets layout position everything.

Operates on one Datadef diagram, named by diagram_id.

Input parameters:

- `description` (string)
- `diagram_id` (string, required): Canvas id, from list_diagrams, create_diagram, or create_blank_diagram.
- `icon` (string): Icon id from search_icons.
- `label` (string, required)
- `technology` (string)
- `type` (string, required)
- `x` (number): Absolute x. Omit to place clear of the existing diagram.
- `y` (number): Absolute y.

### `canvas_update_nodes` (~86 tokens)

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.

Input parameters:

- `diagram_id` (string, required): Canvas id, from list_diagrams, create_diagram, or create_blank_diagram.
- `updates` (array, required)

### `canvas_replace_node` (~184 tokens)

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 lose all the edges.

Operates on one Datadef diagram, named by diagram_id.

Input parameters:

- `description` (string)
- `diagram_id` (string, required): Canvas id, from list_diagrams, create_diagram, or create_blank_diagram.
- `icon` (string): Icon id from search_icons.
- `keepColumns` (boolean): Carry the existing columns over to the replacement. Default true.
- `label` (string, required): New label.
- `node` (string, required): Node id or exact label to replace.
- `technology` (string)
- `type` (string): New type. Omit to keep the current type.

### `canvas_remove_nodes` (~94 tokens)

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.

Input parameters:

- `diagram_id` (string, required): Canvas id, from list_diagrams, create_diagram, or create_blank_diagram.
- `nodes` (array, required): Node ids or exact labels.

### `canvas_connect_nodes` (~97 tokens)

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.

Input parameters:

- `diagram_id` (string, required): Canvas id, from list_diagrams, create_diagram, or create_blank_diagram.
- `edges` (array, required)

### `canvas_update_edges` (~90 tokens)

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.

Input parameters:

- `diagram_id` (string, required): Canvas id, from list_diagrams, create_diagram, or create_blank_diagram.
- `updates` (array, required)

### `canvas_disconnect_nodes` (~62 tokens)

disconnect nodes

Remove the edge between two nodes.

Operates on one Datadef diagram, named by diagram_id.

Input parameters:

- `diagram_id` (string, required): Canvas id, from list_diagrams, create_diagram, or create_blank_diagram.
- `edges` (array, required)

### `canvas_set_columns` (~116 tokens)

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 Datadef diagram, named by diagram_id.

Input parameters:

- `columns` (array, required)
- `diagram_id` (string, required): Canvas id, from list_diagrams, create_diagram, or create_blank_diagram.
- `node` (string, required): Table node id or exact label.

### `canvas_group_nodes` (~308 tokens)

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, named by diagram_id.

If you have not already, call get_design_guide first: it carries Datadef's size, edge, and zone standard, and diagrams built without it read poorly.

Input parameters:

- `description` (string)
- `diagram_id` (string, required): Canvas id, from list_diagrams, create_diagram, or create_blank_diagram.
- `family` (string): Accent hue encoding the zone role: source=teal (inputs/producers), ingest=blue (movement/processing), bronze/silver/gold=medallion layers, consume=magenta (outputs/consumers), dbt=coral (transformati…
- `label` (string, required): Zone name, e.g. "Silver Layer".
- `nodes` (array): Node ids or labels to place inside.
- `parentGroup` (string): Existing group to nest this one inside, e.g. "Databricks Workspace". Zones nest freely — a platform boundary containing Bronze/Silver/Gold is how architects draw.
- `style` (string): layer = horizontal band (default), cluster = box, swimlane = vertical lane.

### `canvas_move_to_group` (~99 tokens)

move to group

Move existing nodes into an existing group, or out of any group.

Operates on one Datadef diagram, named by diagram_id.

Input parameters:

- `diagram_id` (string, required): Canvas id, from list_diagrams, create_diagram, or create_blank_diagram.
- `group` (string|null, required): Target group id or label. Pass null to remove the nodes from their group.
- `nodes` (array, required): Node ids or labels to move.

### `canvas_add_lineage` (~92 tokens)

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_id.

Input parameters:

- `diagram_id` (string, required): Canvas id, from list_diagrams, create_diagram, or create_blank_diagram.
- `links` (array, required)

### `canvas_add_text` (~110 tokens)

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 data flow and take no edges.

Operates on one Datadef diagram, named by diagram_id.

Input parameters:

- `diagram_id` (string, required): Canvas id, from list_diagrams, create_diagram, or create_blank_diagram.
- `texts` (array, required)

### `canvas_add_shape` (~112 tokens)

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 zone use canvas_group_nodes instead.

Operates on one Datadef diagram, named by diagram_id.

Input parameters:

- `diagram_id` (string, required): Canvas id, from list_diagrams, create_diagram, or create_blank_diagram.
- `shapes` (array, required)

### `canvas_add_flow_arrow` (~149 tokens)

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 two areas rather than connecting every pair. This is a visual annotation, not a connection, so it adds no edges and no fan-out. Position it in the gap between the two areas using canvas_measure_canvas.

Operates on one Datadef diagram, named by diagram_id.

Input parameters:

- `arrows` (array, required)
- `diagram_id` (string, required): Canvas id, from list_diagrams, create_diagram, or create_blank_diagram.

### `canvas_add_region` (~145 tokens)

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 belongs to two ideas at once — canvas_group_nodes cannot express any of those because it moves nodes into the zone. Call canvas_measure_canvas first and size the region to enclose the nodes with roughly 24px of margin.

Operates on one Datadef diagram, named by diagram_id.

Input parameters:

- `diagram_id` (string, required): Canvas id, from list_diagrams, create_diagram, or create_blank_diagram.
- `regions` (array, required)

### `canvas_move_nodes` (~117 tokens)

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 those children in the same call. Call canvas_measure_canvas first.

Operates on one Datadef diagram, named by diagram_id.

Input parameters:

- `diagram_id` (string, required): Canvas id, from list_diagrams, create_diagram, or create_blank_diagram.
- `moves` (array, required)

### `canvas_resize_nodes` (~92 tokens)

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.

Input parameters:

- `diagram_id` (string, required): Canvas id, from list_diagrams, create_diagram, or create_blank_diagram.
- `resizes` (array, required)

### `canvas_align_nodes` (~115 tokens)

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.

Input parameters:

- `diagram_id` (string, required): Canvas id, from list_diagrams, create_diagram, or create_blank_diagram.
- `mode` (string, required): left/right/top/bottom align edges; center-* align centre lines; distribute-* space evenly between the outermost two.
- `nodes` (array, required): Node ids or labels.

### `canvas_collapse_nodes` (~173 tokens)

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 individual objects are what the reader came for.

Operates on one Datadef diagram, named by diagram_id.

Input parameters:

- `description` (string): What the merged node stands for. Defaults to listing what was collapsed.
- `diagram_id` (string, required): Canvas id, from list_diagrams, create_diagram, or create_blank_diagram.
- `label` (string): Label for the merged node. Omit to generate one such as "stg_* (8)".
- `nodes` (array, required): Node ids or labels to merge. They should be genuinely similar.

### `canvas_layout_canvas` (~124 tokens)

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 by diagram_id.

Input parameters:

- `diagram_id` (string, required): Canvas id, from list_diagrams, create_diagram, or create_blank_diagram.
- `full` (boolean): Re-arrange the entire canvas from scratch, discarding existing positions. Only use when the user asks for a full reorganisation. Default false.

### `canvas_validate_canvas` (~92 tokens)

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 one Datadef diagram, named by diagram_id.

Input parameters:

- `diagram_id` (string, required): Canvas id, from list_diagrams, create_diagram, or create_blank_diagram.

### `create_diagram` (~498 tokens)

Create a data architecture 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, warehouse and dimensional models, lineage maps, and data platform designs.

Write a specific prompt. Name the actual technologies (Snowflake, dbt, Airflow, Kafka, Fivetran), the layers or zones you want, and the tables that matter, the diagram is only as detailed as the description. Zone names you give are treated as a specification, not a suggestion.

SCOPE: if the user's request is open-ended ("diagram our platform", "show me something"), ask them how much detail they want before calling this, or say which scope you chose. Default to scope "overview". A dense 40-node diagram is impressive and usually not what someone wanted from a one-line request; they can always ask you to expand it.

TIMING: this waits up to ~35 seconds; fast generations come back finished, with a preview image and a markdown line to show the user. Slower ones (1-3 minutes total) return a diagram_id while generation continues: call get_diagram with that id after ~60 seconds (poll every 30s) to get the finished diagram. If you cannot call tools again on your own, never leave the user empty-handed: give them the Open link, say it will be ready in about a minute, and offer to show the diagram inline when they next ask. Never call create_diagram a second time while one is still generating; you would create a duplicate and spend another credit.

Do not use image generation for these. This produces a real, editable diagram.

Input parameters:

- `detailed` (boolean): Use a higher-tier model. Slower and roughly 10x the cost, only when the user explicitly asks for maximum quality. Independent of `scope`.
- `name` (string): Title for the diagram. Defaults to an AI-chosen title.
- `prompt` (string, required): What to diagram. Include technologies, data sources, transformations, layers, and destinations.
- `scope` (string): overview (default): ~12-20 nodes, the shape of the system, right for almost every open-ended request. detailed: every object itemised, denser and harder to read. Ask the user rather than assuming the…

### `create_blank_diagram` (~144 tokens)

Create an empty diagram to build yourself

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 architecture from the conversation. Use create_diagram instead when you want Datadef's model to design the whole thing from a prompt.

Call get_design_guide first: it is the standard Datadef's own generator follows, and building without it produces diagrams this tool exists to avoid.

Input parameters:

- `description` (string): Optional short description.
- `name` (string): Diagram name. Defaults to "Untitled diagram".

### `list_diagrams` (~52 tokens)

List the user's 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.

Input parameters:

- `limit` (integer): Max results. Default 25.

### `get_diagram` (~115 tokens)

Read a 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.

Input parameters:

- `diagram_id` (string, required): Canvas id, from list_diagrams, create_diagram, or create_blank_diagram.
- `include_columns` (boolean): Include table column lists. Default true.
- `include_image` (boolean): Attach a PNG preview and a markdown image link to show the user. Default true; pass false for structure-only reads.

### `edit_diagram` (~128 tokens)

Edit an existing 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 and the bronze table, labelled 'events'" works; "make it better" does not. Returns a PNG of the updated diagram.

Input parameters:

- `diagram_id` (string, required): Canvas id to modify.
- `include_image` (boolean): Return a PNG of the updated diagram. Default true.
- `instruction` (string, required): What to change, in plain language.

### `export_diagram` (~125 tokens)

Export a diagram as an image

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 directly and needs no API key.

Input parameters:

- `diagram_id` (string, required): Canvas id to export.
- `format` (string): Default png.
- `height` (integer): Viewport height in pixels. Default 1000.
- `width` (integer): Viewport width in pixels. Default 1600.

### `repo_status` (~90 tokens)

Repository sync 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 repository connection can use this.

Input parameters:

- `project_id` (string, required): Project id of the repo-linked diagram. A diagram_id from list_diagrams works too.

### `repo_refresh` (~95 tokens)

Sync a diagram from its repository

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 edits. Only the owner of the repository connection can use this.

Input parameters:

- `project_id` (string, required): Project id of the repo-linked diagram. A diagram_id from list_diagrams works too.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/io-datadef-mcp/datadef#diagnostics

## Score history

- 2026-09-20: 92
- 2026-09-19: 92
- 2026-09-18: 92
- 2026-09-17: 92
- 2026-09-16: 92
- 2026-09-15: 92
- 2026-09-14: 92
- 2026-09-13: 91
- 2026-09-12: 91
- 2026-09-11: 91
- 2026-09-10: 90
- 2026-09-09: 90
- 2026-09-08: 89
- 2026-09-07: 89
- 2026-09-06: 88
- 2026-09-05: 88
- 2026-09-04: 87
- 2026-09-03: 87
- 2026-09-02: 86
- 2026-09-01: 86
- 2026-08-31: 85
- 2026-08-30: 85
- 2026-08-29: 84
- 2026-08-28: 84
- 2026-08-27: 84
- 2026-08-26: 83
- 2026-08-25: 81
- 2026-08-24: 81
- 2026-08-23: 80
- 2026-08-22: 80

## Common questions

### What is the io.datadef/mcp server?

io.datadef/mcp is listed in the public MCP registry as io.datadef/mcp. Generate, edit, and export data-architecture diagrams from your AI. Column lineage, PNG in chat. This page covers its hosted endpoint (https://datadef.io/mcp).

### Is the io.datadef/mcp server safe to use?

io.datadef/mcp scores 92 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.datadef/mcp server expose?

io.datadef/mcp exposes 36 tools: get_design_guide, canvas_describe_canvas, canvas_inspect_nodes, canvas_measure_canvas, canvas_suggest_simplifications, and 31 more. Their descriptions and schemas cost roughly 4,714 tokens of context every time the server is loaded.

### Does the io.datadef/mcp server require authentication?

Yes. io.datadef/mcp asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the io.datadef/mcp server still maintained?

io.datadef/mcp is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://datadef.io/mcp
- Authorisation metadata: https://datadef.io/.well-known/oauth-protected-resource/mcp
- Website: https://datadef.io/
- Changelog RSS feed: https://verifymcp.io/servers/io-datadef-mcp/datadef.xml
- Changelog JSON feed: https://verifymcp.io/servers/io-datadef-mcp/datadef.json
- HTML version of this page: https://verifymcp.io/servers/io-datadef-mcp/datadef