Integration

NewsCatcher CatchAll integration

NewsCatcher CatchAll is a recall-first web search API that turns a plain-language question (for example Series B funding rounds for SaaS startups) into structured event records with source citations. Submit a job and read its records when it completes (typically 10 to 15 minutes), extend it with more records, schedule recurring event monitors, track a watchlist of companies with entities and datasets, organize work in projects, and send results to Slack, Microsoft Teams or any HTTPS endpoint through webhooks. The health, version and CSV download routes are not exposed (the same records come back as JSON), and webhook destination URLs, headers, query parameters and auth settings are stripped from read answers. Jobs and every event monitor run spend API credits in proportion to the records they process. Authentication is a CatchAll API key sent in the x-api-key header; the News API and Local News API use separate keys and hosts.

Connect NewsCatcher CatchAll How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in NewsCatcher CatchAll.Built from the 57 NewsCatcher CatchAll tools below, on the connection you add once.

What you can do with NewsCatcher CatchAll

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Entity, 7 operations

add_entities_to_datasetAdd entities to datasetPOSTAdds one or more existing entities to a dataset. Returns the number of entities added.
create_entityCreate entityPOSTCreates a new company entity and begins background enrichment. Each entity requires a `name` plus at least one of: a `description` or a `domain`.
delete_entityDelete entityDELETEPermanently deletes an entity. The entity is removed from all datasets and the search index. This operation cannot be undone.
get_entityGet entityGETReturns a single entity by ID with all attributes and current status.
list_entitiesList entitiesGETReturns a paginated list of entities belonging to the authenticated organization. Supports filtering by status and entity type, and sorting by name, status, or creation date.
remove_entities_from_datasetRemove entities from datasetDELETERemoves one or more entities from a dataset. The entities themselves are not deleted, they are only removed from this dataset. Returns the number of entities removed.
update_entityUpdate entityPATCHUpdates one or more fields of an existing entity.

Resource, 6 operations

add_resource_to_projectAdd resource to projectPOSTAssigns one or more existing resources to a project in a single request.
assign_webhook_resourceAssign webhook resourcePOSTAttaches a job, event monitor, or event monitor group to the webhook. When the resource completes, the webhook receives a delivery. A single webhook can be assigned to multiple resources. Each resource can have up to 5 webhooks assigned.
list_project_resourcesList project resourcesGETLists the resources (jobs, event monitors, datasets, monitor groups, webhooks) assigned to a project, one page at a time, each with its type, ID, name and creation date. Filter by resource type.
list_webhook_resourcesList webhook resourcesGETReturns a paginated list of resources currently assigned to this webhook.
remove_resource_from_projectRemove resource from projectDELETERemoves a resource from a project. The resource itself is not deleted, it becomes unassigned and continues to exist.
remove_webhook_resourceRemove webhook resourceDELETEDetaches a resource from this webhook. Completions of the resource no longer trigger delivery to this webhook. The webhook and the resource itself are not deleted.

Webhook, 6 operations

create_webhookCreate webhookPOSTCreates a webhook that sends job or event monitor results to an HTTPS URL as a raw payload, a Slack message, a Microsoft Teams card or a custom template. Results reach it once attached with assign_webhook_resource or webhook_ids.
delete_webhookDelete webhookDELETEPermanently deletes a webhook and all its resource assignments: jobs and event monitors stop delivering to it. This cannot be undone.
get_webhookGet webhookGETReturns one webhook's name, type, delivery mode, HTTP method, custom formatter and active flag. Its destination URL, headers, query parameters and auth settings are not returned (they can carry credentials).
list_webhooksList webhooksGETLists your organization's webhooks, one page at a time, with each one's name, type, delivery mode, HTTP method and active flag. The destination URL, headers, query parameters and auth settings are not returned (they can carry credentials).
list_webhooks_for_resourceList webhooks for resourceGETLists the webhooks assigned to a job, event monitor or event monitor group, with each one's name, type and active flag. Destination URLs, headers, query parameters and auth settings are not returned.
update_webhookUpdate webhookPATCHUpdates the fields you pass on a webhook; headers, params and auth each replace the existing value entirely. Set is_active false to stop deliveries without deleting it.

Dataset, 5 operations

create_datasetCreate datasetPOSTCreates a new dataset from a list of existing entity IDs. The optional `description` field here describes the dataset itself, it is separate from the entity-level `description` used for matching.
delete_datasetDelete datasetDELETEPermanently deletes a dataset. The entities within the dataset are not deleted, only the dataset itself. This operation cannot be undone.
get_datasetGet datasetGETReturns a single dataset by ID including entity count and current status.
list_datasetsList datasetsGETReturns a paginated list of datasets belonging to the authenticated organization. Supports filtering by status and sorting by name, status, or creation date.
update_datasetUpdate datasetPATCHUpdates the name or description of a dataset.

Project, 5 operations

create_projectCreate projectPOSTCreates a new project.
delete_projectDelete projectDELETEDeletes a project. By default, assigned resources are unassigned but not deleted. Webhooks are an exception: they are never deleted by this operation, even when `delete_resources` is `true`.
get_projectGet projectGETReturns a single project by ID.
list_projectsList projectsGETReturns all projects visible to the authenticated user.
update_projectUpdate projectPATCHUpdates the name or description of an existing project.

Monitor, 3 operations

delete_monitorDelete monitorDELETESoft-deletes an event monitor you own: its scheduled runs stop immediately and it no longer appears in list_monitors.
list_monitorsList monitorsGETLists your event monitors (and those shared with you), one page at a time, with each one's reference job and query, schedule, timezone, enabled flag and creation date.
update_monitorUpdate monitorPATCHUpdate the webhook assignments, record limit, or schedule of an existing event monitor. Omitted fields are left unchanged. Passing `schedule` replaces the event monitor's current schedule.

Status, 3 operations

get_dataset_status_historyGet dataset status historyGETReturns the full status change history for a dataset, ordered chronologically from oldest to newest.
get_job_statusGet job statusGETReturns a job's current stage (submitted, analyzing, fetching, clustering, enriching, completed or failed) and its steps. Poll every 30 to 60 seconds; a job can go back to fetching for a new search turn before it completes.
get_monitor_status_historyGet monitor status historyGETReturns the full execution history of an event monitor as a list of status entries, ordered from newest to oldest.

Job, 2 operations

delete_jobDelete jobDELETESoft-deletes a job you own: it no longer appears in list_jobs, but its data is retained. Deleting an already deleted job also succeeds.
list_monitor_jobsList monitor jobsGETLists the jobs an event monitor has run, with each job's ID and search window (start and end dates), sorted by start date.

Pull, 2 operations

get_job_resultsGet job resultsGETReturns a job's records, one per real-world event, each with a job-specific enrichment object and its source citations, plus the job's settings and progress, one page at a time. Partial records are available from the enriching stage on.
get_monitor_resultsGet monitor resultsGETReturns the records an event monitor has accumulated across all its runs, each with its enrichment object, citations, matched watchlist companies and the dates it was added and updated, plus the monitor's schedule and run dates.

Upload, 2 operations

create_dataset_from_csvCreate dataset from csvPOSTCreates a new dataset by uploading a CSV file. Each row in the CSV becomes an entity. Each row requires a `name` plus at least one of: a `description` or a `domain`; all other columns are optional.
upload_csv_to_datasetUpload csv to datasetPOSTAppends new companies to an existing dataset by uploading a CSV file. Uses the same CSV format as the dataset creation endpoint. The response omits `dataset_name` compared to the create-from-CSV endpoint since the dataset already exists.

Batch, 1 operation

create_entities_batchCreate entities batchPOSTCreates multiple entities in a single request. Each entity is processed independently, a failure in one does not affect others. Each entity requires a `name` plus at least one of: a `description` or a `domain`.

Continue, 1 operation

continue_jobContinue jobPOSTRaises the record limit of a completed job and resumes processing to find more records without starting over; the new records spend API credits. Poll get_job_status again, then read the new records with get_job_results.

Create, 1 operation

create_monitorCreate monitorPOSTCreates an event monitor that re-runs a reference job on a plain-text schedule (for example every day at 12 PM UTC) and accumulates new records (get_monitor_results). Every run is a job that spends API credits; minimum frequency depends on plan.

Disable, 1 operation

disable_monitorDisable monitorPOSTPauses an event monitor: its scheduled runs stop until enable_monitor is called. Nothing is deleted.

Enable, 1 operation

enable_monitorEnable monitorPOSTResumes the scheduled runs of a paused event monitor; every run is a job that spends API credits. With backfill true, the gap since its last job is filled on the next run.

Initialize, 1 operation

initialize_jobInitialize jobPOSTPreviews LLM-generated validators, enrichments and a date range for a query. It creates no job; suggestions are not deterministic, so pass the ones you want to create_job explicitly.

Limit, 1 operation

get_plan_limitsGet plan limitsPOSTReturns the features of your organization's CatchAll plan, each with its value and current usage.

List, 1 operation

list_entities_in_datasetList entities in datasetPOSTReturns a paginated list of entities in a dataset. Supports filtering by status, entity type, and name search.

Overview, 1 operation

get_project_overviewGet project overviewGETReturns resource counts for a project, grouped by type and status. For `jobs` and `monitors`, counts are broken down by status (for example, `completed`, `failed`). For `datasets`, `monitor_groups`, and `webhooks`, only a `total` count is returned.

Source group, 1 operation

list_source_groupsList source groupsGETLists the source groups available to your organization: named domain allowlists curated by NewsCatcher (for example Top 100 US Finance), whose slugs create_job accepts in source_groups.

Submit, 1 operation

create_jobCreate jobPOSTStarts a CatchAll web search job for a plain-language query and returns its job_id. It spends API credits in proportion to the records it processes (test with a small limit). Takes 10 to 15 minutes: poll get_job_status, then call get_job_results.

Test, 1 operation

test_webhookTest webhookPOSTSends a test HTTP request to the webhook's URL now, with its configured method, headers and auth, and returns whether it succeeded, the target's HTTP status code and its response body.

Trigger, 1 operation

trigger_webhookTrigger webhookPOSTSends a webhook delivery for a job or event monitor now, without waiting for the next run: its latest results (or those of job_id) are posted to the webhook's URL. The webhook must already be assigned to the resource.

User, 1 operation

list_jobsList jobsGETLists the jobs you created or that were shared with you, one page at a time, with each job's query, status, processing mode, creation date and sharing details. Filter by text, project, mode or ownership.

Validate, 1 operation

validate_queryValidate queryPOSTChecks whether a query is well-formed and likely to produce good results before submitting a job. Returns a quality assessment with a status level, identified issues, and actionable suggestions.

Webhook history, 1 operation

get_webhook_delivery_historyGet webhook delivery historyGETReturns a paginated delivery log for a given resource, ordered by timestamp descending. Each record shows the webhook dispatched, the HTTP status code returned, delivery outcome, and any error or warning messages.

Use NewsCatcher CatchAll from Claude Code, Cursor or Codex

Connect NewsCatcher CatchAll in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its NewsCatcher CatchAll operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect NewsCatcher CatchAll

Create your workspace
Sign up free. Nothing to install.
Connect NewsCatcher CatchAll once
Add your NewsCatcher CatchAll connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.