The MCP tool directory.

Performs web searches using the Brave Search API and returns comprehensive search results with rich metadata. To chain into local-POI enrichment, pass `result_filter=locations` and feed the resulting `locations.results[].id` values into `brave_local_search`. To chain into the AI summarizer, pass `summary=true` and feed the returned `summarizer.key` into `brave_summarizer`.

Paste a brand's store or product link: CartViral imports it, makes 3 AI clips of its best product (2 AI story reels + 1 AI ad creative, 12 credits) and returns a public page to send the brand, with a "Launch your offer" button that carries this account's referral code (30% of what the brand pays CartViral, for life). Max 10 a day. Offers track sales in Shopify, so pitch Shopify brands.

Public workspaces (the store), with owner, convention and file count. Search their contents with query_index(scope='store'). (Humans and agents without a token can read the store's listings as markdown at GET /store.)

Build an itemized CAD quote (motor + installation + propeller + trade-in + HST + financing tier) and return a deep-link URL the customer can open. Optional contact captures a lead in the dealership CRM.

Batch status change for multiple content ideas across one plan. Mirrors bulk_update_content_status (which targets ContentItems) — fail-soft, returns per-id errors. Useful for quickly skipping or approving many ideas without one tool call per idea. Idea IDs are GUIDs (from get_content_plan), not ObjectIds.

Batch status change for multiple content items (e.g. publish or archive several at once). Fail-soft: items that no longer exist are reported in 'errors' and the rest still succeed. If you see 'not found (deleted or never existed)' errors, the IDs are likely from a stale list_content_items response — refetch the list and retry. When publishing, an article whose plan idea has a scheduledDate in the future is scheduled (reported under 'scheduled', goes live automatically on that date) instead of published now, so a batch does not land on the site at once. Pass ignoreSchedule=true to publish them now.

Read resources search on business.google.com on Think with Google - Marketing Research, Insights, and Trends (business.google.com). Use for requests like “search business.google.com for article”; “search business.google.com for description”; “search business.google.com for description — Search thinkwithgoogle.com for description”. Learned from 2 browser traces; chains get_resources_search. Inputs: query e.g. "article". Returns resources, nextPageToken. Read-only on business.google.com.

Read resources search on business.google.com on Think with Google - Marketing Research, Insights, and Trends (business.google.com). Use for requests like “search business.google.com for article”; “search business.google.com for description”; “search business.google.com for description — Search thinkwithgoogle.com for description”. Learned from 2 browser traces; chains get_resources_search. Inputs: query e.g. "article". Returns resources, nextPageToken. Read-only on business.google.com.

Read resources search on business.google.com on Think with Google - Marketing Research, Insights, and Trends (business.google.com). Use for requests like “search business.google.com for article”; “search business.google.com for description”; “search business.google.com for description — Search thinkwithgoogle.com for description”. Learned from 2 browser traces; chains get_resources_search. Inputs: query e.g. "article". Returns resources, nextPageToken. Read-only on business.google.com.

Toggle cache-only mode: no network access; reads served from cache, fetches refused.

Cache inventory: rows per symbol, session bounds, depth in weeks, API-call accounting.

Backfill history for a universe (default: the swarm's 13-symbol universe). After warming, every finalized session is immutable in cache — replays cost zero API calls. Requires network and a valid SWARM_MCP_ACCESS_TOKEN; refused in cache.offline mode.

Run a tailored Discounted Cash Flow (DCF) analysis using the FMP Custom DCF Advanced API. With detailed inputs, this API allows users to fine-tune their assumptions and variables, offering a more personalized and precise valuation for a company.

Run a tailored Discounted Cash Flow (DCF) analysis using the FMP Custom DCF Advanced API. With detailed inputs, this API allows users to fine-tune their assumptions and variables, offering a more personalized and precise valuation for a company.

Create a new event on this identity's calendar

Delete a calendar event

Get details of a specific calendar event

List events on this identity's calendar

Make this identity's calendar public or private. Public calendars are viewable at /identities/:id/calendar.json

Update an existing calendar event

EMERGENCY STOP: stops EVERY run currently executing for the tenant, including runs started by other users and by other applications. Use this when something is burning credits and identifying the specific run would take too long — otherwise prefer cancel_run. Same timing as cancel_run: runs stop at their next checkpoint, not instantly.

Cancel your own open payment request.

Stops a run that is currently executing, and every sub-agent it spawned. Use list_runs and look for Outcome 'running' to find candidates. NOT instant: the run checks for the signal between tool-calling iterations, so a model call already in flight finishes first — expect it to stop within one model turn. Whatever the run produced before stopping is still returned to its caller and still billed; cancelling saves the work that had not happened yet, not the work already done. Cancelling a run that already finished is harmless and reports signalled=0.

Associate one or more candidates to a target Job Opening, Client, or Contact. The body's `data` array contains `Jobids` (or `Clientids` / `Contactids`) plus `ids` of candidates to associate.

Associate one or more candidates to a target Job Opening, Client, or Contact. The body's `data` array contains `Jobids` (or `Clientids` / `Contactids`) plus `ids` of candidates to associate.

Associate one or more candidates to a target Job Opening, Client, or Contact. The body's `data` array contains `Jobids` (or `Clientids` / `Contactids`) plus `ids` of candidates to associate.

Associate one or more candidates to a target Job Opening, Client, or Contact. The body's `data` array contains `Jobids` (or `Clientids` / `Contactids`) plus `ids` of candidates to associate.

Upload a resume (PDF/DOCX) and parse it into a new Candidate record.

Upload a resume (PDF/DOCX) and parse it into a new Candidate record.

Upload a resume (PDF/DOCX) and parse it into a new Candidate record.