CatchAll (by NewsCatcher)
OfficialRun NewsCatcher CatchAll web-research jobs and manage the surrounding monitors, webhooks, projects, datasets, and entities — all via MCP tools.\n\n- Jobs: submit natural-language queries (submit_query), preview suggested validators/enrichments/dates (initialize_query), check query quality (validate_query), poll status (get_job_status), pull results paginated or as CSV (pull_results, pull_job_csv), expand processing (continue_job), and list/delete jobs.\n- Monitors: create recurring monitors from completed jobs, update limit/webhooks, enable/disable, list, view status and spawned jobs, and pull latest results or CSV.\n- Webhooks: create/list/get/update/delete endpoints, test deliveries, attach/detach to jobs/monitors, view delivery history, and manually trigger deliveries.\n- Projects: create/list/get/update/delete projects, view resource overview, and add/list/remove contained resources.\n- Datasets: create/list/get/update/delete datasets, add/remove/list entities, check status, and create/append from CSV content.\n- Entities: create (single or batch), list, get, update (including external_entity_id), and delete companies/people.\n- Account/meta: check plan limits and usage (get_user_limits), API health (check_health), and version (get_version).
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
Newscatcher CatchAll MCP Server
MCP server for the NewsCatcher CatchAll Web Search API.
Quick Start — Use Our Hosted Server
You don't need to clone or run this repo to use the MCP — NewsCatcher runs a hosted instance:
https://catchall-mcp.newscatcherapi.com/mcp?apiKey=YOUR_CATCHALL_API_KEYGet a CatchAll API key at platform.newscatcherapi.com, then connect:
{
"mcpServers": {
"catchall": {
"type": "http",
"url": "https://catchall-mcp.newscatcherapi.com/mcp?apiKey=YOUR_CATCHALL_API_KEY"
}
}
}Or via Claude Code CLI:
claude mcp add --transport http catchall "https://catchall-mcp.newscatcherapi.com/mcp?apiKey=YOUR_CATCHALL_API_KEY"Full integration docs: https://www.newscatcherapi.com/docs/web-search-api/integrations/mcp
Prefer to run the server yourself (locally or self-hosted)? See Running below.
Related MCP server: Apify-Google-Events-API
Tool To Endpoint Mapping
Jobs
MCP Tool | Method | Endpoint |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Job listing filters:
list_user_jobssupportssearch,ownership,project_id, andmode(baseorlite) filters in addition topage/page_size.
Monitors
MCP Tool | Method | Endpoint |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Webhooks
MCP Tool | Method | Endpoint |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Webhook notes:
create_webhookaccepts an optionalproject_idto attach the webhook to a project on creation.list_webhooksalso accepts an optionalproject_idto filter to webhooks belonging to a specific project.get_webhook_historyqueries in one of two modes — passresource_type+resource_idfor a job/monitor/monitor_group's deliveries, or passwebhook_idfor everything delivered through one webhook (exactly one mode per call). Manual test deliveries (test_webhook) only appear in webhook mode and are recorded withresource_type: "test".
Projects
MCP Tool | Method | Endpoint |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Project resources:
resource_typeis one ofjob,monitor,dataset,monitor_group, orwebhook. A webhook can belong to several projects at once.delete_projectwithdelete_resources=truedeletes the contained jobs, monitors, datasets, and monitor groups, but webhooks are only detached — never deleted — and the response'sdeleted_resourcesreports them under awebhook_unlinkedcount.
Datasets
MCP Tool | Method | Endpoint |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
CSV uploads (v1.6.1):
create_dataset_from_csvandappend_csv_to_datasettake the CSV content in thefileparameter — raw CSV text or standard base64. They never read a path from the server's filesystem, so they stay safe on a remote/hosted MCP. Inline CSV content is capped at a hard 10 MB (after base64 decoding).create_dataset_from_csvalso accepts the new optionalproject_idfield.
Entities
MCP Tool | Method | Endpoint |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
external_entity_id(v1.6.3):create_entityandupdate_entityaccept an optionalexternal_entity_idstring — a customer-supplied identifier that links the entity to a record in an external system.project_id(v1.8.0):list_entitiesaccepts an optionalproject_idto filter to entities belonging to a specific project.
Source Groups
MCP Tool | Method | Endpoint |
|
|
|
Source groups (v1.8.0): named, reusable domain allowlists (public groups plus any organization-visibility groups your organization can access).
list_source_groupsreturns each group'sslug,name, anddescription.submit_queryaccepts an optionalsource_groupslist of slugs (max 20 per job) that scopes fetching to those domain allowlists. The attached groups are echoed back assource_groupsin the job status and results.
User & Meta
MCP Tool | Method | Endpoint |
|
|
|
|
|
|
|
|
|
Authentication
API key precedence (highest to lowest):
api_keytool parameterx-api-keyrequest headerAuthorization: Bearer <key>request headerURL query parameter
?apiKey=...CATCHALL_API_KEYenvironment variable
check_health and get_version do not require API key auth.
Hosted deployment (FastMCP Gateway)
When deployed via fastmcp.app, a stateless gateway sits in front of the server. The gateway
forwards HTTP headers to the backend but not URL query parameters. Use the x-api-key
header or CATCHALL_API_KEY environment variable instead of ?apiKey=.
Claude Code / Cursor:
{
"mcpServers": {
"catchall": {
"type": "http",
"url": "https://YOUR-DEPLOYMENT.fastmcp.app/mcp",
"headers": { "x-api-key": "YOUR_API_KEY" }
}
}
}Or via CLI:
claude mcp add --transport http catchall "https://YOUR-DEPLOYMENT.fastmcp.app/mcp" \
--header "x-api-key: YOUR_API_KEY"Direct server access (no gateway): ?apiKey=YOUR_KEY in the URL still works.
Core Workflow (Jobs)
Optional: call
initialize_queryto preview validators/enrichments/date window.initialize_queryis preview-only (it does not create a job) and suggestions are non-deterministic.Submit with
submit_query(queryrequired). You can send onlyquery; omitted optional fields are auto-selected/generated.Optional fields are independent: provide any subset (for example, custom
validatorsonly), omitted ones are still auto-generated.start_date/end_datefilter web page discovery dates, not event dates in extracted content.For event-time accuracy, use event-focused validators/enrichments and verify
event_datein pulled results.Poll
get_job_status: first check after ~1-2 minutes, then every 30-60 seconds, stop oncompletedorfailed.Pull with
pull_results; partial data appears duringenriching.Paginate while
page < total_pagesto retrieve all available records.Use
continue_jobonly to process more records (cost-affecting). It applies only to jobs originally submitted withlimit.continue_job.new_limitis optional; if omitted, API defaults to your plan maximum.page/page_size/total_pagesrepresent already-available records; useprogress_validated < candidate_recordsto detect if more records may still appear.
Limit vs Page Size
limit(submit_query,continue_job) controls how many records are processed and therefore affects cost. If provided, must be >= 10. Omit to retrieve everything up to your plan's maximum.page_size(pull_results,list_user_jobs) controls pagination only and does not affect processing cost.pull_results.page_sizedefault is100.page_sizerange is1..1000.pull_resultsresponse includeserror(failed jobs) andlimit(applied job limit).
API-Enforced Monitor Constraints
create_monitor.backfill=true: reference jobend_datemust be within the last 7 days.create_monitor.backfill=false: reference job age constraint does not apply.Monitor minimum schedule frequency depends on plan.
create_monitorsupports optionallimit(minimum10),backfill(defaulttrue),timezone,webhook_ids, andproject_id.Webhooks are centralized in v1.5.3: register them with
create_webhook, then attach by ID viacreate_monitor.webhook_ids/update_monitor.webhook_ids(no inline webhook config).Monitors are only supported for
basejobs (notlite).enable_monitorsupports optionalbackfill.update_monitorupdateswebhook_ids, runlimit,schedule, and/ortimezone(passwebhook_ids=[]to clear assignments;timezoneis ignored unlessscheduleis also set).list_monitorssupports pagination viapageandpage_sizeplussearch,ownership, andproject_idfilters; it returnstotal,page,page_size,total_pages,monitors.
Enrichment Output Notes
enrichment.enrichment_confidenceis always present.Company enrichments are structured objects with:
source_textconfidencemetadata.namemetadata.domain_urlmetadata.domain_url_confidence
Error Handling
Tools return:
Pretty JSON string on success.
(v1.8.0) An MCP tool error (
isError=True) for any upstream non-2xx response (badapi_key, invalid/foreignproject_id, not-found ids, validation failures, etc.) or unhandled exception. The error message carries the upstream status code and message, for exampleAPI Error (401): Api key not found. Before v1.8.0, tools swallowed these failures and returned a plain"Error: ..."string as a successful tool result — clients checking onlyisErrorwould see a false success. That has been fixed: every tool now raises aToolErrorinstead of returning an error string, so failures are always reported as real tool errors.
Running
Install dependencies:
pip install -r requirements.txtRun over stdio:
python server.pyRun over HTTP (if fastmcp CLI is available):
fastmcp run server.py:mcp --transport streamable-http --host 0.0.0.0 --port 8000Available Tools
60 toolsadd_dataset_entitiesCInspect
Add existing entities to a dataset.
Inputs: dataset_id (required), entity_ids (required), api_key. Returns: result
add_project_resourcesCInspect
Add one or more resources to a project.
Inputs: resources (required), project_id (required), api_key. Returns: result
append_csv_to_datasetAInspect
Append entities from a CSV file to an existing dataset.
Parses the CSV and appends its entities to the dataset. Each row must
have a name column; include a domain or description column (or both)
for meaningful enrichment. Duplicate rows (by name) are skipped. To create
a new dataset from a CSV, use create_dataset_from_csv instead.
Inputs: file (required), dataset_id (required), api_key. Returns: result
assign_webhook_resourceAInspect
Map a resource (job, monitor, or monitor_group) to a webhook.
Use when:
You want a webhook to fire for a specific job or monitor's deliveries.
Inputs: webhook_id (required), resource_id (required), resource_type (required), api_key. Returns: result
check_healthAInspect
Check API health status.
This tool maps to GET /health and does not require an API key.
Inputs: api_key. Returns: result
continue_jobAInspect
Expand a job by processing more records beyond the initial limit.
This increases the number of records the system processes (which costs additional credits). Only use this when the user wants MORE data processed.
This only applies to jobs originally submitted with limit.
If a job was submitted without limit, there is nothing to continue.
The new_limit must be greater than the previous limit when provided.
If omitted, API defaults to your plan maximum.
Inputs: job_id (required), api_key, new_limit. Returns: result
create_datasetAInspect
Create a new dataset.
Datasets are collections of entities (companies/people). Connect a dataset to
a job via submit_query(connected_dataset_ids=[...]) to narrow retrieval scope.
Inputs: name (required), api_key, entity_ids, project_id, +1 more. Returns: result
create_dataset_from_csvAInspect
Create a new dataset by uploading a CSV file.
The CSV must have at least a name column. For meaningful entity
enrichment each row should also include a domain column or a
description column (or both) — a row with only a name is accepted but
produces lower-quality enrichment. Additional columns are mapped to entity
attributes. Max file size is plan-dependent. To add CSV rows to an
existing dataset, use append_csv_to_dataset instead.
Inputs: file (required), name (required), api_key, project_id, +1 more. Returns: result
create_entities_batchBInspect
Create multiple entities in one call.
Inputs: entities (required), api_key. Returns: result
create_entityAInspect
Create a single entity (a company or person).
name is required plus at least one identifying
field: either description or additional_attributes.company_attributes.domain.
Inputs: name (required), api_key, description, entity_type, +2 more. Returns: result
create_monitorAInspect
Create a recurring monitor from a completed job.
Monitors re-run a job's query on a schedule. Use the explore -> refine -> automate pattern: submit a job, refine until results match, then create a monitor.
The schedule is defined in natural language (e.g., 'every day at 9 AM EST').
Always include a timezone (in the schedule text or via the timezone arg).
API-enforced constraints apply:
If
backfill=true, reference job end_date must be within the last 7 daysIf
backfill=false, reference job age does not matterMinimum schedule frequency depends on your plan
Webhooks are now centralized: register them with create_webhook, then pass
their IDs here via webhook_ids (there is no inline webhook config anymore).
Inputs: schedule (required), reference_job_id (required), limit, api_key, +4 more. Returns: result
create_projectAInspect
Create a new project.
Projects group related resources (jobs, monitors, datasets, monitor_groups)
so you can organize work and filter listings by project_id.
Inputs: name (required), api_key, description. Returns: result
create_webhookAInspect
Create a new webhook endpoint.
Use when:
You want to register a URL to receive job or monitor result deliveries.
You need a webhook_id to attach to a monitor (via webhook_ids) or a job submission.
Inputs: url (required), name (required), auth, type, +6 more. Returns: result
delete_datasetAInspect
Permanently delete a dataset.
The entities the dataset referenced are not deleted; only the dataset and its entity associations are removed.
Inputs: dataset_id (required), api_key. Returns: result
delete_entityBInspect
Permanently delete an entity.
Inputs: entity_id (required), api_key. Returns: result
delete_jobAInspect
Permanently delete a job and its results.
Use when:
You want to remove a job you no longer need from your account.
Inputs: job_id (required), api_key. Returns: result
delete_monitorAInspect
Permanently delete a monitor and stop its scheduled runs.
Use when:
You want to remove a monitor entirely (use
disable_monitorto only pause it).
Inputs: monitor_id (required), api_key. Returns: result
delete_projectAInspect
Delete a project.
By default the project's resources (jobs, monitors, etc.) are detached but
kept. Set delete_resources=true to also delete the contained resources.
Inputs: project_id (required), api_key, delete_resources. Returns: result
delete_webhookAInspect
Permanently delete a webhook endpoint.
Use when:
You want to remove a webhook from your account.
Inputs: webhook_id (required), api_key. Returns: result
disable_monitorAInspect
Disable a monitor to stop its scheduled runs.
The monitor can be re-enabled later with enable_monitor.
Inputs: monitor_id (required), api_key. Returns: result
enable_monitorAInspect
Enable a previously disabled monitor to resume its scheduled runs.
Inputs: monitor_id (required), api_key, backfill. Returns: result
get_datasetBInspect
Get a single dataset's details.
Inputs: dataset_id (required), api_key. Returns: result
get_dataset_statusAInspect
Get the status history of a dataset (e.g. its enrichment progress over time).
Inputs: dataset_id (required), api_key. Returns: result
get_entityAInspect
Get a single entity's details.
Inputs: entity_id (required), api_key. Returns: result
get_job_statusAInspect
Check the status of a submitted job.
Call this after submit_query to see if your job is ready. Status progression: submitted -> analyzing -> fetching -> clustering -> enriching -> completed/failed
IMPORTANT: Jobs take several minutes to process.
First check after ~1-2 minutes, then poll every 30-60 seconds.
Broad searches can take 10-30+ minutes; for long jobs, poll every 60-120 seconds.
Do NOT call this tool in a tight loop.
Stop polling when status is completed or failed.
Treat submitted, analyzing, fetching, clustering, and enriching
as active states and continue polling.
You don't need to wait for completion to pull results. Partial results are
available during enriching — call pull_results after ~2 minutes, then
poll status every 30-60 seconds and pull again for fresher results.
Do not stop pulling just because an intermediate pull is empty/unchanged.
Use progress_validated vs candidate_records to track whether more
results may still appear (progress_validated < candidate_records).
If transport/session fails, resume using the same job_id.
Inputs: job_id (required), api_key. Returns: result
get_monitor_statusAInspect
Get the status history of a monitor.
Use when:
You want to see the timeline of a monitor's state changes (e.g. active, disabled, errored) and any related details.
Inputs: monitor_id (required), api_key. Returns: result
get_projectBInspect
Get a single project's details.
Inputs: project_id (required), api_key. Returns: result
get_project_overviewAInspect
Get a project's resource overview (counts grouped by resource type and status).
Inputs: project_id (required), api_key. Returns: result
get_user_limitsAInspect
Retrieve plan features and current usage limits for your API key.
Use when:
You want to know how many records/jobs/monitors your plan allows.
You want to check current usage against plan limits before running a large job.
Inputs: api_key. Returns: result
get_versionAInspect
Get current API version.
This tool maps to GET /version and does not require an API key.
Inputs: api_key. Returns: result
get_webhookAInspect
Retrieve the full configuration of a specific webhook.
Use when:
You want to inspect a webhook's URL, method, headers, or status by its ID.
Inputs: webhook_id (required), api_key. Returns: result
get_webhook_historyAInspect
Get the webhook delivery history for a resource (job/monitor/monitor_group).
Use when:
You want to see past webhook delivery attempts and their outcomes for a specific job or monitor.
Inputs: resource_id (required), resource_type (required), page, api_key, +1 more. Returns: result
initialize_queryAInspect
Preview suggested validators, enrichments, and date ranges before submitting.
Use when:
You want to inspect/edit auto-generated validators/enrichments before submitting.
You want to preview date adjustments via
date_modification_message.
Do not use when:
You want to start processing immediately with final inputs (use
submit_query).
Key behavior:
Preview-only endpoint: does not create a job and does not start processing.
Suggestions are LLM-generated and not deterministic across calls.
To reuse suggestions, pass them explicitly to
submit_query.
Inputs: query (required), api_key, context, fetch_all_watchlist_news. Returns: result
list_dataset_entitiesBInspect
List the entities contained in a dataset.
Inputs: dataset_id (required), page, search, status, +5 more. Returns: result
list_datasetsCInspect
List your datasets.
Inputs: page, search, api_key, sort_by, +5 more. Returns: result
list_entitiesCInspect
List your entities.
Inputs: page, search, status, api_key, +4 more. Returns: result
list_monitor_jobsAInspect
List all jobs spawned by a monitor.
Returns the history of scheduled runs for a monitor.
Inputs: monitor_id (required), sort, api_key. Returns: result
list_monitorsAInspect
List all your monitors.
Returns all monitors with their schedule, status, reference query, and webhook config.
Inputs: page, search, api_key, ownership, +2 more. Returns: result
list_project_resourcesAInspect
List the resources contained in a project.
Inputs: project_id (required), page, api_key, page_size, +1 more. Returns: result
list_projectsCInspect
List your projects.
Inputs: page, search, api_key, ownership, +1 more. Returns: result
list_resource_webhooksAInspect
List the webhooks mapped to a specific resource (job/monitor/monitor_group).
Use when:
You have a job or monitor ID and want to know which webhooks will fire for it.
Inputs: resource_id (required), resource_type (required), page, api_key, +2 more. Returns: result
list_user_jobsAInspect
List all jobs submitted by you.
Returns your job history with IDs, queries, statuses, and timestamps.
Inputs: page, search, api_key, ownership, +2 more. Returns: result
list_webhook_resourcesAInspect
List the resources mapped to a webhook.
Use when:
You want to see which jobs/monitors a webhook is attached to.
Inputs: webhook_id (required), page, api_key, page_size, +1 more. Returns: result
list_webhooksAInspect
List all your webhooks.
Use when:
You want to see all webhook endpoints configured in your account.
You need to find a webhook_id to pass to monitors (via webhook_ids) or jobs.
Inputs: page, api_key, page_size. Returns: result
pull_job_csvAInspect
Download a job's results as a CSV file.
Use when:
You want the full job output as a CSV for offline analysis or export.
Prefer this over
pull_resultswhen the consumer needs spreadsheet/CSV format.
Inputs: job_id (required), api_key. Returns: result
pull_monitor_csvAInspect
Download the latest monitor run's results as a CSV file.
Use when:
You want the most recent monitor run output as a CSV for offline analysis or export.
Prefer this over
pull_monitor_resultswhen the consumer needs spreadsheet/CSV format.
Inputs: monitor_id (required), api_key. Returns: result
pull_monitor_resultsAInspect
Retrieve the latest results from a monitor.
Returns the most recent run's results including run_info, records, and all_records.
Inputs: monitor_id (required), api_key. Returns: result
pull_resultsAInspect
Retrieve the results of a job.
Can be called before completion for partial results, or after completion for the full set. Returns clustered, validated, and enriched web results. While job status is active, call this repeatedly (typically page=1) to refresh partial output. When job reaches completed, iterate all pages. If job fails, call once more to capture any partial output.
Inputs: job_id (required), page, api_key, page_size. Returns: result
remove_dataset_entitiesAInspect
Remove entities from a dataset (the entities themselves are not deleted).
Inputs: dataset_id (required), entity_ids (required), api_key. Returns: result
remove_project_resourceBInspect
Remove a single resource from a project.
Inputs: project_id (required), resource_id (required), resource_type (required), api_key. Returns: result
remove_webhook_resourceAInspect
Unmap a resource from a webhook.
Use when:
You want to stop a webhook from firing for a specific job or monitor.
Inputs: webhook_id (required), resource_id (required), resource_type (required), api_key. Returns: result
submit_queryAInspect
Create a new CatchAll processing job from a natural-language query.
Use when:
You want to start a new CatchAll web research run from a user query.
You want the API to fetch/process sources and then return structured results.
Do not use when:
You want status for an existing job (use
get_job_status).You want records for an existing job (use
pull_results).
Key rules:
queryis required.You can submit with only
query; omitted optional fields (validators,enrichments,start_date,end_date) are auto-selected/generated by the API.Optional fields are independent: you can pass any subset (for example, custom
validatorsbut noenrichments), and omitted fields are still auto-selected/generated.When
connected_dataset_idsis set, thequerymust describe the topic or event type only (e.g. "M&A activity", "regulatory filings", "executive changes"). Do NOT write things like "for my companies", "for the selected list of companies", or "news about my watchlist" — the entity filtering is applied automatically by the connected dataset. Mentioning companies in the query when a dataset is attached is redundant and degrades retrieval quality.When
connected_dataset_idsis set, entity-relevance validators (e.g.company_is_primary_subject) are generated automatically by the API. Do NOT add them manually tovalidators— they are redundant and may conflict with the auto-generated ones. Only pass validators that describe the event or topic, not entity filtering.start_dateandend_datefilter by web page discovery date, not event date.Discovery dates and extracted event dates can differ. For event-time accuracy, use event-focused validators/enrichments and verify
event_datein pulled results.end_datemust be afterstart_date.Dates outside your plan lookback limits return API 400.
limitcontrols processed record count (cost-affecting). Omit it to retrieve everything up to your plan's maximum. If provided, must be >= 10.validators/enrichmentsmay be passed either as arrays or as JSON-string arrays (for client compatibility).validators[].typemust beboolean(if omitted, it defaults toboolean).enrichments[].typesupported values: text, number, date, option, url, company.
Basic examples:
validators:
[{"name":"is_acquisition_event","description":"true if page describes an acquisition","type":"boolean"}]enrichments:
[{"name":"acquiring_company","description":"Extract acquiring company","type":"company"},{"name":"deal_value","description":"Extract announced deal value","type":"number"}]
Next step:
Save the returned
job_id.Poll
get_job_statusand callpull_results(partial results can appear before completion).
Inputs: query (required), mode, limit, schema, +12 more. Returns: result
test_webhookAInspect
Send a test delivery to a webhook endpoint.
Use when:
You want to verify a webhook URL is reachable and correctly configured before attaching it to a monitor or job.
Inputs: webhook_id (required), api_key, payload. Returns: result
trigger_webhookAInspect
Manually trigger webhook delivery for a resource (job/monitor/monitor_group).
Use when:
You want to (re-)send a webhook delivery on demand instead of waiting for the automatic dispatch — e.g. to replay a missed or failed delivery.
Inputs: webhook_id (required), resource_id (required), resource_type (required), job_id, +1 more. Returns: result
update_datasetBInspect
Update a dataset's name and/or description.
Inputs: dataset_id (required), name, api_key, description. Returns: result
update_entityBInspect
Update an entity's name, description, external_entity_id, and/or attributes.
Inputs: entity_id (required), name, api_key, description, +2 more. Returns: result
update_monitorAInspect
Update a monitor's webhook assignments and per-run limit.
Note: schedule and reference_job_id cannot be modified through this endpoint.
Webhooks are centralized — pass webhook IDs (from create_webhook/list_webhooks).
Inputs: monitor_id (required), limit, api_key, webhook_ids. Returns: result
update_projectAInspect
Update a project's name and/or description.
Only the fields you provide are changed.
Inputs: project_id (required), name, api_key, description. Returns: result
update_webhookAInspect
Update an existing webhook's configuration.
Use when:
You want to change a webhook's URL, method, headers, or other settings.
You want to enable or disable a webhook (set
is_active).Only the fields you provide are updated; omitted fields remain unchanged.
Inputs: webhook_id (required), url, auth, name, +8 more. Returns: result
validate_queryAInspect
Check the quality of a query before submitting a job ("Check Query Quality").
Use when:
You want quick feedback on whether a query is well-formed for CatchAll before spending credits on a job.
You want concrete suggestions to improve a vague or overly broad query.
Do not use when:
You want to preview auto-generated validators/enrichments (use
initialize_query).You want to actually run a search (use
submit_query).
Inputs: query (required), api_key. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 60 tools
Most tools have distinct purposes, and descriptions clearly differentiate similar ones (e.g., initialize_query vs submit_query, pull_results vs pull_monitor_results). However, the high number of tools (60) may cause some confusion, especially for webhook and resource mapping tools.
Tool names generally follow a verb_noun pattern, but the verbs are inconsistent (pull, get, list, check) and there is a mix of 'list' and 'get' for similar retrieval operations. While readable, the pattern is not uniform.
With 60 tools, the surface is very large for an MCP server. Although the domain (news monitoring with datasets, entities, projects, monitors, webhooks) might justify the number, many CRUD operations could be consolidated to reduce cognitive load.
The tool set covers the full lifecycle: job submission, monitoring, webhooks, datasets, entities, projects, and health. All major CRUD operations are present, and there are no obvious gaps for the stated purpose.
Maintenance
Related MCP Connectors
Free US local event search. No signup or API key; 90-day lookahead. Paid commercial and bulk access.
The live web data engine for teams and agents: Search API, Extract API and Deep Search.
Live web search, scraping and crawling API for AI. Get structured, LLM-ready data from any site.
Read-only search of upcoming local events worldwide: music, comedy, AI/tech, arts, food, sports.
Related MCP Servers
AlicenseAqualityBmaintenanceLive search on six engines (Google, Bing, Yandex, Baidu, DuckDuckGo, Ecosia), image search and single/batch page extraction for AI agents. Keeps source engine and rank. Runs against a self-hosted OpenSERP server or OpenSERP Cloud.1910240 npm3MIT- FlicenseNot gradedqualityBmaintenanceEnables natural-language event searches through Google Events, returning structured JSON with dates, venues, ticket links, and map details, plus support for localization, filters, and pagination.2-
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to search event calendars by keyword and list upcoming or date-filtered events from a chosen calendar, returning titles, dates, venues, coordinates, and keywords.91 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to browse public event listings from explore pages and fetch full detail for a single event — titles, descriptions, times, locations, host display names, and aggregate RSVP counts — across eight supported city regions. Keyless and read-only, with no guest lists, contact info, or authentication required.307 npmMIT