MCP Servers

What you'll learn

• What MCP is and how it connects AI coding assistants to AutoTalk
• How to configure MCP in Codex and Claude Code
• What tools are available and how to use them

AutoTalk exposes an MCP (Model Context Protocol) server that gives AI coding assistants direct access to your dynadata schemas, example documents, CRUD operations, workflow testing, and more. This lets tools like Codex and Claude Code understand your data models and build agents/workflows without you needing to copy-paste schemas.

Prerequisites

You need an API token to authenticate with the MCP server. See API Tokens for how to create one.

The MCP endpoint is:

https://api.autotalk.io/v1/mcp/dynadata

Codex setup

Add this to your ~/.codex/config.toml:

[mcp_servers.autotalk]
url = "https://api.autotalk.io/v1/mcp/dynadata"
http_headers = { "x-api-key" = "sk-YOUR-API-KEY" }

warning

Use http_headers, not headers. Codex requires the http_headers key for URL-based MCP servers.

Claude Code setup

Add this to your project's .mcp.json or global ~/.claude.json under the mcpServers key:

{
  "mcpServers": {
    "autotalk": {
      "url": "https://api.autotalk.io/v1/mcp/dynadata",
      "headers": {
        "x-api-key": "sk-YOUR-API-KEY"
      }
    }
  }
}

Available tools

The server provides 17 tools grouped into three categories:

Schema tools (10)

Tool	Description
list_dynadata_types	Lists available model types (agents, workflows, clients, etc.)
get_model_definition	Returns field definitions, types, constraints for a model
get_model_json_schema	Returns the JSON Schema for a model type
get_model_relationships	Shows how models reference each other
list_action_types	Lists all workflow/agent action types
get_action_definition	Returns full action definition with fields and outputs
get_cel_reference	Returns CEL variables and functions by context
validate_document	Validates a document against the model schema
get_guide	Returns cookbook-style guides for building agents and workflows
search_example_documents	Searches curated example documents for reusable patterns

Data tools (5)

Tool	Description
create_document	Creates a new document in the database
get_document	Reads a document by type and ID
update_document	Updates an existing document
delete_document	Soft-deletes (tombstones) a document
test_workflow	Tests a workflow in-memory without persisting anything

Function tools (2)

Tool	Description
list_functions	Lists executable server-side functions for a model type
execute_function	Executes a function on a document or collection

Usage tips

• Start with list_dynadata_types to discover available models, then use get_model_definition for field details.
• Use search_example_documents to find reusable patterns before building agents or workflows from scratch.
• Use validate_document to check your document before creating it with create_document.
• Use test_workflow for rapid iteration — it runs workflows in-memory and cleans up automatically.
• For large documents, validate specific sections using the fields parameter or embedded types.

Next steps

• API Tokens — Create and manage API tokens
• Webhooks — Configure outgoing event notifications