Runchat Docs

The Canvas API uses a single endpoint to dispatch operations via the tool field. This page documents each tool and its parameters.

Using an MCP client like Claude, ChatGPT, or Cursor? The easiest way to give an agent these tools is the Runchat MCP server — it exposes every tool below (plus model discovery and skills) and handles auth for you. The REST endpoint documented here is for plain HTTP / scripted access.

POST https://runchat.com/api/v1/{runchat_id}/canvas
Authorization: Bearer {api_key}
Content-Type: application/json

{
  "tool": "<tool_name>",
  "args": { ... }
}

All responses follow the shape { "result": { ... } }.

A machine-readable skill specification for this API is available at GET https://runchat.com/api/skills/canvas. AI agents can fetch this endpoint to learn the full tool schema automatically. We also include links to this in the ai-instructions metatag for any link to a workflow so you can simply share a link to a workflow and ask it to follow any instructions.

Typical workflow

get_canvas — discover what’s on the canvas
read_nodes — inspect specific nodes and their handles
create_prompt_node / create_code_node / … / update_node / connect_nodes — build or modify the workflow
organize_nodes — auto-layout the result
run_nodes — execute the workflow

Canvas Tools

`get_canvas`

Get a high-level overview of all nodes and edges on the canvas. Returns node IDs, types, labels, positions, and edge connections. Paginated at 50 nodes per page.

Parameter	Type	Required	Description
`offset`	number	no	Pagination offset. Omit for the first page. Use the `next_offset` value from a previous response to fetch the next page.

`read_nodes`

Read the full state of one or more nodes by ID. Returns each parameter’s name, type, label, status, and current data values. Use this to find handle names for connect_nodes.

Parameter	Type	Required	Description
`node_ids`	string[]	yes	Array of node IDs to read.

Creating nodes

Each node type has its own creation tool with a flat, type-specific schema — easier to call correctly than one polymorphic tool. Every creation tool shares these optional fields:

Parameter	Type	Required	Description
`label`	string	no	Display label for the node.
`position`	object	no	Explicit placement. Preferred: relative to an existing node — `{ "right_of": nodeId }` (or `left_of` / `below` / `above`, optional `gap`); the server computes coordinates from real node sizes. Raw form: `{ x, y }` offsets in canvas units from the top-left of the user’s viewport (or origin `0,0`). Omit to auto-place.
`input_depths`	object	no	Depth settings for input parameters. `0` = each (default), `1` = all, `-1` = flatten.

create_node (a single polymorphic call taking a type field) remains available as a legacy alias and is the only way to create several nodes in one call — see Creating multiple nodes.

`create_prompt_node`

Create an LLM node (promptNode) for reasoning, writing, analysis, or agent tasks. Output is on the messages handle; structured output (output_format) is on artifacts.

Parameter	Type	Required	Description
`prompt`	string	yes	The task or question. One task only — feeding N values in later runs the node N times. Persona/system text goes in `instruction`.
`model_id`	string	no	`api_id` of the LLM (from `list_models` type `llm`). Omit for the default model.
`instruction`	string	no	System prompt / persona (a hidden input — cannot be connected to).
`output_format`	string	no	`"list"` (array of strings), `"html"` (complete HTML document), `"code"` (single code block), or a JSON schema string. Omit for text.
`tools`	string[]	no	`runchat_id`s of published tools (from `search_tools`) the model can call while it runs.

`create_input_node`

Create a user-input widget (inputNode). Its value is exposed on the content handle. One input node holds a whole list — set a list with values, not one node per item.

Parameter	Type	Required	Description
`format`	`"string"` \| `"slider"` \| `"toggle"` \| `"image"` \| `"file"` \| `"select"` \| `"button"` \| `"code"`	no	Widget type. Defaults to `"string"`.
`value`	string	no	Initial single value. For `image`, an image URL. Ignored for `select` — use `options`/`selected`.
`values`	string[]	no	Initial LIST of values held by this one node. Downstream nodes run once per item. Use instead of `value` for lists.
`options`	string[]	no	For `select` only: the dropdown options.
`selected`	string	no	For `select` only: the initially selected option (defaults to the first).

`create_image_node`

Create a media generation node (imageNode) — images, video, 3D, or audio. Generated media is on the image handle. Always call get_model_params for the model first and use the returned parameter names as params keys.

Parameter	Type	Required	Description
`model_id`	string	yes	The `api_id` of the generation model.
`params`	object	no	Model parameter values keyed by the names from `get_model_params`, e.g. `{ "prompt": "a red chair", "aspect_ratio": "16:9" }`.

`create_code_node`

Create a code node (codeNode). Code executes on the server only when the node is run. Output is on the result handle by default.

Parameter	Type	Required	Description
`language`	`"javascript"` \| `"html"` \| `"rhino-python"` \| `"blender-python"` \| `"revit-csharp"`	no	`"javascript"` (default) sandboxed JS/TS. `"html"` renders in a live preview iframe. CAD languages run in the connected app via the bridge.
`code`	string	no	The source code.
`inputs`	object	no	Named input handles with defaults, e.g. `{ "myInput": "default" }`. Reference them in code by the same camelCase names.
`outputs`	string[]	no	Named output handles, e.g. `["summary", "imageUrl"]`. Declare only when the code returns an object with exactly these keys.

JavaScript nodes support multiple files: add a package.json and helper modules with create_files after creation (this upgrades the node to the bundler sandbox automatically). Other languages have a single entry file.

`create_note`

Create a markdown note (noteNode) for documentation, summaries, or links.

Parameter	Type	Required	Description
`content`	string	yes	The markdown content of the note.

`place_tool`

Place a published tool (found with search_tools) onto the canvas as a runChatNode.

Parameter	Type	Required	Description
`tool_id`	string	yes	The `runchat_id` of the published tool (from `search_tools`).
`expand`	boolean	no	When true, copy the tool’s full internal node graph onto the canvas as editable nodes instead of one collapsed tool node.
`inputs`	object	no	Input values keyed by the tool’s input parameter names (from `search_tools`).

`create_artifact_node`

Create an artifact node (artifactNode) that saves or fetches an artifact (blog post, website, or app).

Parameter	Type	Required	Description
`operation`	`"create"` \| `"get"`	no	`"create"` to save/update content (default), `"get"` to fetch an existing artifact by ID.
`name`	string	no	Artifact name (create mode).
`content`	string	no	Content to save — markdown (→ blog), HTML (→ website), or app HTML that uses `window.runchat` (→ app).
`artifact_id`	string	no	Only when fetching or updating an existing artifact.
`folder`	string	no	Optional folder path, e.g. `"myFolder/subFolder"`.

Creating multiple nodes

The legacy create_node tool takes a nodes array to create a whole pipeline in one call. Each item is a full node spec (type required), and an optional position lays it out. The response is { "count": N, "nodes": [ ... ] }.

{
  "tool": "create_node",
  "args": {
    "nodes": [
      {
        "type": "inputNode",
        "label": "Topic",
        "initial_data": { "input": ["robots"] },
        "position": { "x": 0, "y": 0 }
      },
      {
        "type": "promptNode",
        "label": "Write",
        "initial_data": { "prompt": ["Write a haiku about {{topic}}"] },
        "position": { "x": 420, "y": 0 }
      }
    ]
  }
}

Omit position on any node to let it auto-place — batched nodes chain left-to-right in creation order off the existing workflow. Relative positions (right_of etc.) can reference any node that already exists, including ones created by an earlier call; they cannot reference siblings in the same batch (their IDs are generated server-side). If you set positions yourself you don’t need to call organize_nodes.

`update_node`

Update an existing node’s label, model, or input values.

Parameter	Type	Required	Description
`node_id`	string	yes	The ID of the node to update.
`label`	string	no	New display label.
`model_id`	string	no	Change the model on this node.
`inputs`	object	no	Input values to set, keyed by parameter name. Values are arrays with one string element.
`input_depths`	object	no	Depth settings for input parameters.

`connect_nodes`

Connect an output of one node to an input of another — one edge, or many at once via edges.

Parameter	Type	Required	Description
`source_node_id`	string	yes*	The ID of the source node (data flows from here). Required for a single edge; omit at the top level when using `edges`.
`target_node_id`	string	yes*	The ID of the target node (data flows to here).
`source_handle`	string	no	Output parameter name on the source node.
`target_handle`	string	no	Input parameter name on the target node.
`edges`	object[]	no	Connect multiple edges in one call. Each item takes the same fields as a single connect (`source_node_id` and `target_node_id` required). When present, the top-level fields are ignored.

Common handles:

Node Type	Inputs	Outputs
`promptNode`	`messages` (any type), `prompt` (string)	`messages`
`codeNode`	`code` (string)	`result`
`inputNode`	—	`content`
`imageNode`	(from `get_model_params`)	`image`

When you pass edges, the response is { "count": N, "edges": [ ... ] } with one result per edge — an edge that fails (e.g. an unknown handle) is reported individually without aborting the others.

{
  "tool": "connect_nodes",
  "args": {
    "edges": [
      {
        "source_node_id": "abc",
        "target_node_id": "def",
        "target_handle": "prompt"
      },
      {
        "source_node_id": "def",
        "target_node_id": "ghi",
        "target_handle": "messages"
      }
    ]
  }
}

`organize_nodes`

Auto-layout nodes on the canvas based on their connections. Call this after completing all node-creation and connect_nodes operations. The set expands automatically to every node connected to the ones you pass, and nodes the user has positioned manually are never moved — they act as fixed anchors the layout arranges itself around.

Parameter	Type	Required	Description
`node_ids`	string[]	yes	Node IDs to organize; anything connected to them is included automatically.

`delete_nodes`

Delete one or more nodes from the canvas. Also removes any connected edges.

Parameter	Type	Required	Description
`node_ids`	string[]	yes	Array of node IDs to delete.

`delete_edges`

Delete one or more edges (connections) from the canvas without deleting the nodes.

Parameter	Type	Required	Description
`edge_ids`	string[]	yes	Array of edge IDs to delete.

`run_nodes`

Execute one or more nodes on the canvas. Nodes run in dependency order — upstream nodes execute first. Returns status and output parameter names for each node.

Parameter	Type	Required	Description
`node_ids`	string[]	yes	Array of node IDs to execute.

Running nodes may consume credits. Confirm with the user before calling this tool.

Tool Discovery

Find published tools (and the user’s own runchats) and run them directly, without first placing them on a canvas.

These tools operate on the published-tool library, not the current canvas. For inspect_tool and execute_tool the runchat_id in args names the tool to act on — the {runchat_id} in the endpoint URL is only the canvas/auth scope and is ignored by these tools.

`search_tools`

Search published tools and the user’s own runchats by keyword. Returns each tool’s runchat_id, name, description, and its input/output parameter names — enough to run it with execute_tool.

Parameter	Type	Required	Description
`query`	string	no	Keywords to match against tool names and descriptions. Omit to list popular tools.
`limit`	number	no	Max results to return. Defaults to 8, max 25.

`inspect_tool`

Inspect a published tool to see its inputs/outputs and a digest of its internal nodes (models, prompts, code) and connections. Optional — use it to learn how a tool is built or before placing it on a canvas; not required to run a tool.

Parameter	Type	Required	Description
`runchat_id`	string	yes	The `runchat_id` of the tool to inspect (from `search_tools`).

`execute_tool`

Run a published tool and return its outputs, without adding it to a canvas. Provide inputs keyed by the tool’s input parameter names (from search_tools); the result reports any inputs that didn’t match.

Parameter	Type	Required	Description
`runchat_id`	string	yes	The `runchat_id` of the tool to run (from `search_tools`).
`inputs`	object	no	Input values keyed by the tool’s input parameter names. Each value is a string or array of strings.
`version_num`	number	no	Specific published version to run. Defaults to the latest released version.

Running a tool spends the authenticated user’s credits. Confirm before running anything costly.

Media Tools

`get_model_params`

Get full parameter details for one or more models. Returns parameter names, types, and defaults — use these as initial_data keys when creating an imageNode.

Parameter	Type	Required	Description
`model_id`	string	no	A single `api_id` of the model.
`model_ids`	string[]	no	An array of `api_id`s to fetch details for multiple models at once.

`view_image`

Fetch an image from a URL for analysis. If the URL is a webpage rather than an image, a headless browser captures a viewport screenshot of it instead (spends credits).

Parameter	Type	Required	Description
`url`	string	yes	The URL of the image. Supports PNG, JPEG, GIF, WebP, and SVG, plus webpage URLs (screenshotted).
`format`	string	no	For SVG URLs only: `render` (default) rasterises to PNG; `source` returns the raw SVG markup.
`question`	string	no	A specific question about the image. Only used when the calling model can’t view images (or for headless API/MCP callers): a vision model answers and the text is returned. Models with vision get the image attached to answer themselves.

Web Tools

First-party web search and page reading. Both spend the authenticated user’s credits.

`web_search`

Search the web and get title/url/snippet results (Brave licensed index). Follow up with fetch_page on a result URL for full content.

Parameter	Type	Required	Description
`query`	string	yes	The search query.
`count`	number	no	Number of results (1-20, default 8).
`freshness`	string	no	Restrict to the past day (`pd`), week (`pw`), month (`pm`), or year (`py`).

`fetch_page`

Fetch a webpage in a headless browser (JavaScript executed) and return its content. Long pages are windowed: a truncated response includes next_offset — pass it back as offset to page through the rest (each page is a fresh render and billed call).

Parameter	Type	Required	Description
`url`	string	yes	The http(s) URL of the page to fetch.
`format`	string	no	`markdown` (default, readable text), `links` (outbound links with anchor text), or `html` (rendered HTML).
`offset`	number	no	Character offset to continue from — use `next_offset` from a previous truncated response. Defaults to 0.

Code File Tools

Every codeNode exposes a uniform file model. JavaScript nodes have an entry file (index.ts, plain JS or TypeScript) plus optional additional files (package.json for npm deps, helper modules, static .html assets) — adding files upgrades the node to the bundler sandbox automatically. Other languages (html, rhino-python, blender-python, revit-csharp) have a single entry file. Entry filenames by language:

`language`	Entry file
`javascript`	`index.ts`
`html`	`index.html`
`rhino-python` / `blender-python`	`index.py`
`revit-csharp`	`index.cs`

Always call read_files (or read_nodes) first to discover the entry path — never guess based on language.

`read_files`

Read content from a code node. Returns each file’s path, line-numbered content, length, and whether it’s the entry file.

Parameter	Type	Required	Description
`node_id`	string	yes	The ID of the code node.
`files`	string[]	no	Specific paths to read. Omit to read all files in the node (recommended when you don’t know paths yet).

Response includes code_mode, entry_file, and a files array of { path, entry, length, content } plus not_found if any requested paths are missing.

`edit_file`

Edit one file in a code node. Two modes:

Targeted edit — pass old_text + new_text. old_text must match exactly (whitespace + indentation) and be unique in the file. Empty new_text deletes the matched span.
Full overwrite — pass only new_text (omit old_text). Replaces the entire file.

Always call read_files first to see current content.

Parameter	Type	Required	Description
`node_id`	string	yes	The ID of the code node.
`file`	string	yes	The file path (e.g. `"index.ts"`, `"package.json"`). Use the path returned by `read_files`.
`new_text`	string	yes	The replacement text (when `old_text` is set) or the full new file contents (when omitted).
`old_text`	string	no	When present: the exact substring to find and replace. Must be unique. When omitted: overwrites file.

`create_files`

Create one or more new files in a JavaScript code node (e.g. package.json, lib/utils.ts, a static index.html asset). JavaScript nodes only — other languages have a single fixed entry file. Adding files upgrades the node to the bundler sandbox automatically. Errors if any path collides with the entry file or an existing file.

Parameter	Type	Required	Description
`node_id`	string	yes	The ID of the JavaScript code node.
`files`	`{ path: string, content: string }[]`	yes	Files to create. Paths must not collide with existing files.

`delete_files`

Delete one or more non-entry files from a JavaScript code node. Cannot delete the entry file.

Parameter	Type	Required	Description
`node_id`	string	yes	The ID of the JavaScript code node.
`files`	string[]	yes	Paths of files to delete.

`read_status`

Read current error messages, status messages, preview errors, and console output for a code node. Use when debugging a failing run.

Parameter	Type	Required	Description
`node_id`	string	yes	The ID of the code node to check.

Skill Endpoint

The Canvas API skill specification is available as a machine-readable document that AI agents can fetch to learn the full tool schema automatically.

GET https://runchat.com/api/skills/canvas

Returns a Markdown document with YAML frontmatter containing the complete tool reference. The response includes:

API description and base URL
All tool schemas with parameter types and descriptions
Common handle names and workflow guidance

This is useful for integrating external AI agents (e.g. Claude, GPT) that need to discover and use the Canvas API programmatically.

API Documentation

Endpoints

Canvas API

Canvas Tools Reference

Typical workflow

Canvas Tools

`get_canvas`

`read_nodes`

Creating nodes

`create_prompt_node`

`create_input_node`

`create_image_node`

`create_code_node`

`create_note`

`place_tool`

`create_artifact_node`

Creating multiple nodes

`update_node`

`connect_nodes`

`organize_nodes`

`delete_nodes`

`delete_edges`

`run_nodes`

Tool Discovery

`search_tools`

`inspect_tool`

`execute_tool`

Media Tools

`get_model_params`

`view_image`

Web Tools

`web_search`

`fetch_page`

Code File Tools

`read_files`

`edit_file`

`create_files`

`delete_files`

`read_status`

Skill Endpoint

​Typical workflow

​Canvas Tools

​get_canvas

​read_nodes

​Creating nodes

​create_prompt_node

​create_input_node

​create_image_node

​create_code_node

​create_note

​place_tool

​create_artifact_node

​Creating multiple nodes

​update_node

​connect_nodes

​organize_nodes

​delete_nodes

​delete_edges

​run_nodes

​Tool Discovery

​search_tools

​inspect_tool

​execute_tool

​Media Tools

​get_model_params

​view_image

​Web Tools

​web_search

​fetch_page

​Code File Tools

​read_files

​edit_file

​create_files

​delete_files

​read_status

​Skill Endpoint

Typical workflow

Canvas Tools

`get_canvas`

`read_nodes`

Creating nodes

`create_prompt_node`

`create_input_node`

`create_image_node`

`create_code_node`

`create_note`

`place_tool`

`create_artifact_node`

Creating multiple nodes

`update_node`

`connect_nodes`

`organize_nodes`

`delete_nodes`

`delete_edges`

`run_nodes`

Tool Discovery

`search_tools`

`inspect_tool`

`execute_tool`

Media Tools

`get_model_params`

`view_image`

Web Tools

`web_search`

`fetch_page`

Code File Tools

`read_files`

`edit_file`

`create_files`

`delete_files`

`read_status`

Skill Endpoint