Skip to main content
The Runchat agent has access to a set of built-in tools for interacting with your canvas, editing code, loading skills, and more. The tools available depend on the current permission level. In plain language, the agent can:
  • Read everything on your canvas, including node configurations and error messages
  • Create and connect new nodes, organize layouts, and update parameters
  • Edit code in Code nodes with surgical replacements rather than full rewrites
  • Run nodes and execute workflows on your behalf (Edit and run permission only)
  • Search, inspect and run published tools (both from the community and your own private tools)
  • Load domain-specific skills before writing code
  • Create, update and publish workflows (when used from the dashboard, REST API or MCP)
The rest of this page lists the underlying tools by category.

Canvas Tools

Reading the canvas

These tools are available at all permission levels:
  • Get canvas (get_canvas), see all nodes and edges on the canvas. For large canvases, paginate with the offset parameter.
  • Read nodes (read_nodes), inspect the full state of specific nodes by ID, including inputs, outputs and configuration.

Creating and editing nodes

These tools require Edit canvas or Edit and run permission:
  • Create node, add new nodes to the canvas. The agent can create all node types: Agent (promptNode), media nodes named after their model (imageNode), Code (codeNode), Input (inputNode), Note (noteNode), and Runchat workflow nodes (runChatNode).
  • Connect nodes, wire data between nodes by specifying source and target handles.
  • Update node, modify an existing node’s label, model, or input values.
  • Delete nodes, remove nodes from the canvas.
  • Delete edges, disconnect nodes without deleting them.
  • Organize nodes, auto-layout nodes after creating or modifying a workflow.

Running nodes

Requires Edit and run permission:
  • Run nodes, execute nodes in dependency order with their current inputs and connections.

Code File Tools

Every Code node — regardless of mode — exposes a uniform file model. Each mode has a single entry file (index.js, index.html, index.py, index.cs). JavaScript nodes can also hold additional files like package.json or helper modules. The same tools work across all modes:
  • Read files, read content from one or more files in a code node with line numbers. Omit files to read everything (recommended when you don’t yet know paths). Available at all permission levels.
  • Read status, check error and status messages for debugging. Available at all permission levels.
These require Edit canvas or Edit and run permission:
  • Edit file, targeted edit (pass old_text + new_text) or full overwrite (pass only new_text).
  • Create files, add new files (package.json, helper modules, static assets) to a JavaScript code node. JavaScript nodes only — this upgrades the node to the bundler sandbox automatically.
  • Delete files, remove non-entry files from a JavaScript code node. JavaScript nodes only.

Media Tools

  • Get model parameters, fetch the full parameter details for a generative model before creating an imageNode. This tells the agent what inputs the model accepts (e.g. prompt, image_url, resolution).
  • View image, fetch and display images from URLs in tool results.

Team Tools

Available when agent teams are turned on (Hobby plan or higher):
  • Spawn agent, start a specialist teammate with its own brief and credit budget. Lead agent only.
  • Send message, message one teammate or the whole team.
  • List team, see who is on the team and what each agent is doing.
  • Tasks, add, claim and complete items on the team’s shared task list.

Workspace Tools

Available when the agent workspace is turned on (Hobby plan or higher):
  • Exec (workspace_exec), run a shell command in the sandbox.
  • Write, edit and patch (workspace_write, workspace_edit, workspace_apply_patch), create files, make targeted replacements, or change several files in one patch.
  • Read, list and grep (workspace_read, workspace_list, workspace_grep), inspect and search files.
  • Publish (workspace_publish), upload a file from the sandbox so it can be added to the canvas.

Custom Tools

The agent finds and uses the tools it needs on its own, including web search and page fetching. You never need to add tools to the chat.
  • Search Tools, search for public tools published by the community and private tools published by your team.
  • Inspect Tool, view the workflow of a specific tool.
  • Execute Tool, with run permissions, run the tool.
Common patterns:
  • Two-step research for better images, ask the agent to “search first, then pull images from the projects you find” rather than grabbing search thumbnails. You’ll get higher-resolution imagery straight from the source.
  • Group on the canvas, once images are nodes on the canvas, the agent can read them and group by palette, narrow to a brief, or compare two.
  • Pick a format, ask for Notes when each item has mixed content (image, description, link).
  • Deep dive a result, pick one project from the search and ask the agent to dig further. It can follow links to find architect statements, materials, press coverage, then consolidate everything onto the canvas.

Next steps