LandingAI ADE TypeScript MCP Server

It is generated with Stainless.

Installation

Direct invocation

You can run the MCP Server directly via npx:

export VISION_AGENT_API_KEY="My Apikey"
export LANDINGAI_ADE_ENVIRONMENT="production"
npx -y landingai-ade-mcp@latest

Via MCP Client

There is a partial list of existing clients at modelcontextprotocol.io. If you already have a client, consult their documentation to install the MCP server.

For clients with a configuration JSON, it might look something like this:

{
  "mcpServers": {
    "LandingAI_ade_api": {
      "command": "npx",
      "args": ["-y", "landingai-ade-mcp", "--client=claude", "--tools=all"],
      "env": {
        "VISION_AGENT_API_KEY": "My Apikey",
        "LANDINGAI_ADE_ENVIRONMENT": "production"
      }
    }
  }
}

Cursor

If you use Cursor, you can install the MCP server by using the button below. You will need to set your environment variables in Cursor's mcp.json, which can be found in Cursor Settings > Tools & MCP > New MCP Server.

VS Code

If you use MCP, you can install the MCP server by clicking the link below. You will need to set your environment variables in VS Code's mcp.json, which can be found via Command Palette > MCP: Open User Configuration.

Open VS Code

Claude Code

If you use Claude Code, you can install the MCP server by running the command below in your terminal. You will need to set your environment variables in Claude Code's .claude.json, which can be found in your home directory.

claude mcp add --transport stdio LandingAI_ade_api --env VISION_AGENT_API_KEY="Your VISION_AGENT_API_KEY here." -- npx -y landingai-ade-mcp

Exposing endpoints to your MCP Client

There are three ways to expose endpoints as tools in the MCP server:

1. Exposing one tool per endpoint, and filtering as necessary
2. Exposing a set of tools to dynamically discover and invoke endpoints from the API
3. Exposing a docs search tool and a code execution tool, allowing the client to write code to be executed against the TypeScript client

Filtering endpoints and tools

You can run the package on the command line to discover and filter the set of tools that are exposed by the MCP Server. This can be helpful for large APIs where including all endpoints at once is too much for your AI's context window.

You can filter by multiple aspects:

• --tool includes a specific tool by name
• --resource includes all tools under a specific resource, and can have wildcards, e.g. my.resource*
• --operation includes just read (get/list) or just write operations

Dynamic tools

If you specify --tools=dynamic to the MCP server, instead of exposing one tool per endpoint in the API, it will expose the following tools:

1. list_api_endpoints - Discovers available endpoints, with optional filtering by search query
2. get_api_endpoint_schema - Gets detailed schema information for a specific endpoint
3. invoke_api_endpoint - Executes any endpoint with the appropriate parameters

This allows you to have the full set of API endpoints available to your MCP Client, while not requiring that all of their schemas be loaded into context at once. Instead, the LLM will automatically use these tools together to search for, look up, and invoke endpoints dynamically. However, due to the indirect nature of the schemas, it can struggle to provide the correct properties a bit more than when tools are imported explicitly. Therefore, you can opt-in to explicit tools, the dynamic tools, or both.

See more information with --help.

All of these command-line options can be repeated, combined together, and have corresponding exclusion versions (e.g. --no-tool).

Use --list to see the list of available tools, or see below.

Code execution

If you specify --tools=code to the MCP server, it will expose just two tools:

• search_docs - Searches the API documentation and returns a list of markdown results
• execute - Runs code against the TypeScript client

This allows the LLM to implement more complex logic by chaining together many API calls without loading intermediary results into its context window.

The code execution itself happens in a Deno sandbox that has network access only to the base URL for the API.

Specifying the MCP Client

Different clients have varying abilities to handle arbitrary tools and schemas.

You can specify the client you are using with the --client argument, and the MCP server will automatically serve tools and schemas that are more compatible with that client.

• --client=<type>: Set all capabilities based on a known MCP client

  • Valid values: openai-agents, claude, claude-code, cursor
  • Example: --client=cursor

Additionally, if you have a client not on the above list, or the client has gotten better over time, you can manually enable or disable certain capabilities:

• --capability=<name>: Specify individual client capabilities
  • Available capabilities:
    • top-level-unions: Enable support for top-level unions in tool schemas
    • valid-json: Enable JSON string parsing for arguments
    • refs: Enable support for $ref pointers in schemas
    • unions: Enable support for union types (anyOf) in schemas
    • formats: Enable support for format validations in schemas (e.g. date-time, email)
    • tool-name-length=N: Set maximum tool name length to N characters
  • Example: --capability=top-level-unions --capability=tool-name-length=40
  • Example: --capability=top-level-unions,tool-name-length=40

Examples

1. Filter for read operations on cards:

--resource=cards --operation=read

2. Exclude specific tools while including others:

--resource=cards --no-tool=create_cards

3. Configure for Cursor client with custom max tool name length:

--client=cursor --capability=tool-name-length=40

4. Complex filtering with multiple criteria:

--resource=cards,accounts --operation=read --tag=kyc --no-tool=create_cards

Running remotely

Launching the client with --transport=http launches the server as a remote server using Streamable HTTP transport. The --port setting can choose the port it will run on, and the --socket setting allows it to run on a Unix socket.

Authorization can be provided via the Authorization header using the Bearer scheme.

Additionally, authorization can be provided via the following headers: | Header | Equivalent client option | Security scheme | | ------------------------ | ------------------------ | --------------- | | x-vision-agent-api-key | apikey | Basic Auth |

A configuration JSON for this server might look like this, assuming the server is hosted at http://localhost:3000:

{
  "mcpServers": {
    "LandingAI_ade_api": {
      "url": "http://localhost:3000",
      "headers": {
        "Authorization": "Bearer <auth value>"
      }
    }
  }
}

The command-line arguments for filtering tools and specifying clients can also be used as query parameters in the URL. For example, to exclude specific tools while including others, use the URL:

http://localhost:3000?resource=cards&resource=accounts&no_tool=create_cards

Or, to configure for the Cursor client, with a custom max tool name length, use the URL:

http://localhost:3000?client=cursor&capability=tool-name-length%3D40

Importing the tools and server individually

// Import the server, generated endpoints, or the init function
import { server, endpoints, init } from "landingai-ade-mcp/server";

// import a specific tool
import extractClient from "landingai-ade-mcp/tools/top-level/extract-client";

// initialize the server and all endpoints
init({ server, endpoints });

// manually start server
const transport = new StdioServerTransport();
await server.connect(transport);

// or initialize your own server with specific tools
const myServer = new McpServer(...);

// define your own endpoint
const myCustomEndpoint = {
  tool: {
    name: 'my_custom_tool',
    description: 'My custom tool',
    inputSchema: zodToJsonSchema(z.object({ a_property: z.string() })),
  },
  handler: async (client: client, args: any) => {
    return { myResponse: 'Hello world!' };
  })
};

// initialize the server with your custom endpoints
init({ server: myServer, endpoints: [extractClient, myCustomEndpoint] });

Available Tools

The following tools are available in this MCP server.

Resource $client:

• extract_client (write): Extract structured data from Markdown using a JSON schema.

  This endpoint processes Markdown content and extracts structured data according to the provided JSON schema.

  For EU users, use this endpoint:

  `https://api.va.eu-west-1.landing.ai/v1/ade/extract`.

• parse_client (write): Parse a document or spreadsheet.

  This endpoint parses documents (PDF, images) and spreadsheets (XLSX, CSV) into structured Markdown, chunks, and metadata.

  For EU users, use this endpoint:

  `https://api.va.eu-west-1.landing.ai/v1/ade/parse`.

• split_client (write): Split classification for documents.

  This endpoint classifies document sections based on markdown content and split options.

  For EU users, use this endpoint:

  `https://api.va.eu-west-1.landing.ai/v1/ade/split`.

Resource parse_jobs:

• create_parse_jobs (write): Parse documents asynchronously.

  This endpoint creates a job that handles the processing for both large documents and large batches of documents.

  For EU users, use this endpoint:

  `https://api.va.eu-west-1.landing.ai/v1/ade/parse/jobs`.

• list_parse_jobs (read): List all async parse jobs associated with your API key. Returns the list of jobs or an error response. For EU users, use this endpoint:

  https://api.va.eu-west-1.landing.ai/v1/ade/parse/jobs.

• get_parse_jobs (read): Get the status for an async parse job.

  Returns the job status or an error response. For EU users, use this endpoint:

  https://api.va.eu-west-1.landing.ai/v1/ade/parse/jobs/{job_id}.