WDS MCP Tools

Use the WDS MCP tools from IDEs and agentic systems to manage stored jobs, fetch individual pages, run hierarchical Traversal plans, inspect results, schedule recurring runs, and search retrieval-indexed content. The companion WDS MCP Prompts compose these tools into complete workflows.

What You Can Do

Create, read, list, and delete job configurations in the default MCP tenant.
Fetch one absolute URL and read its downloaded content in chunks.
Store and run multi-level Traversal configurations, then inspect run status, errors, and cursor-paginated data.
Create, read, and delete automatic Traversal schedules when Scheduling is enabled.
Search indexed content when Retrieval is enabled.
Delete a job, its associated data, or the complete default MCP tenant.

Quick Start

Ensure the WDS API Server and its MCP endpoint are reachable, for example at http://localhost:2807/mcp.
Connect the MCP server in your IDE; see the MCP Server overview.
Call WdsUpsertJobConfig, then use WdsFetchChunked, a Traversal workflow, or WdsRetrieve.

Tools at a Glance

Jobs and Downloads

WdsGetJobs: Lists jobs in the default MCP tenant for discovery and lifecycle monitoring
WdsGetJobConfig: Reads the named job’s current crawler configuration before inspection or replacement
WdsUpsertJobConfig: Creates or replaces the named job’s top-level crawler configuration, including start URLs, request settings, restart behavior, crawl scope, and retrieval indexing options
WdsFetchChunked: Starts or resumes downloading one absolute URL with the named job’s crawler settings. Use the returned task ID with GetChunk to read content
WdsGetChunk: Reads all or part of a task’s downloaded page. If the download is pending, call GetChunk again with the same task ID
WdsGetDownloadTaskStatus: Inspects a task’s download state and HTTP attempt history to troubleshoot pending, failed, or completed downloads
WdsDeleteJob: Deletes the named job and cleans up its Traversal config, schedule, tasks, run history, downloaded and scraped data, retrieval-index data, and service-side settings in the default MCP tenant
WdsDeleteTenant: Deletes the default MCP tenant and cleans up its jobs, download tasks, Traversal configs, schedules, tasks and run history, cached and scraped data, and retrieval-index data across backing services

Traversal

WdsGetTraversalConfig: Reads the named job’s saved TraversalConfig so its multi-level crawl and scrape plan can be inspected or reused
WdsUpsertTraversalConfig: Validates and stores the named job’s TraversalConfig multi-level crawl and scrape plan in the Traversal runner. This does not start a run
WdsDeleteTraversal: Deletes the named job’s saved TraversalConfig, schedule, tasks, and run history from the Traversal runner. This does not delete the job
WdsRunTraversal: Requests a Traversal run using the named job’s current job config and TraversalConfig, reusing an active run instead of starting a duplicate. Use the returned run number for later inspection
WdsListTraversalRuns: Lists recent Traversal run summaries for the named job, newest first, so clients can find run numbers and completion state
WdsGetTraversalRunInfo: Inspects the progress and configuration used by one Traversal run
WdsGetTraversalRunErrors: Investigates failed downloads from one Traversal run and the parent pages that discovered them
WdsGetTraversalRunData: Reads a batch of scraped data produced by a Traversal run. Continue with the returned cursor until no cursor remains
WdsTraversalAll: Replaces the named job’s TraversalConfig with a root-level plan that follows links subject to optional maxDepth, scrapes page content with the optional conversion, and requests a run while reusing an active run when present

Scheduling

WdsGetTraversalSchedule: Reads the named job’s saved automatic Traversal schedule. A saved TraversalConfig is required
WdsUpsertTraversalSchedule: Creates or replaces the named job’s TraversalSchedule for automatic runs. A saved TraversalConfig is required. This configures future runs and does not start one immediately
WdsDeleteTraversalSchedule: Deletes the named job’s TraversalSchedule and stops future scheduled starts. A saved TraversalConfig is required. This does not delete the job, Traversal config, or previous runs

Retrieval

WdsRetrieve: Searches retrieval-indexed crawled content in the default MCP tenant to find evidence relevant to a question, optionally restricted to one named job