The MCP tool directory.

[DANGER: live action] Push a saved agent-created Facebook campaign draft to Meta as draft campaigns/ad sets/ads. ALWAYS confirm with the user before calling. Always confirm with the user before calling.

[DANGER: live action] Create Meta draft campaigns/ad sets/ads from explicit campaign data, ad sets, ad copy, and image URLs. Supports raw externally-hosted image URLs. ALWAYS confirm with the user before calling. Always confirm with the user before calling.

Resolve previously-uploaded Meta ads into reusable creative assets for a campaign draft.

List the user's connected Facebook ad accounts and Pages, with their cached identity info.

Get the upload state and Meta IDs of a single uploaded ad.

List Meta ad sets under a given campaign.

List Meta campaigns for a specific connected ad account (cache-first; refresh from Meta if cold).

List previously-uploaded ads, filterable by ad account and state.

[DANGER: live action] Enqueue an upload of an AdMakeAI-generated ad creative to a Meta ad account / campaign / ad set. Creates a real ad on Meta. ALWAYS confirm with the user before calling. Always confirm with the user before calling.

[write] Validate an ad-creative + ad-account pair for Meta upload (image dimensions, copy length, etc.) without uploading.

Check a specific claim against available evidence from the publication's data, sources, and investigations.

Disables a feature flag in the current environment.

Enables a feature flag in the current environment.

Get the details of an existing feature flag by its slug.

Get a list of all of your existing feature flags matching the criteria specified.

Enables a feature flag for a specific target in the current environment. Currently, supported targets include users and organizations.

Removes a target from the feature flag's target list in the current environment. Currently, supported targets include users and organizations.

Exact FEATURE_ORDER feature vector for symbol at session as_of, with provenance per field. Runs the no-lookahead guard (every feature must equal a fresh causal recomputation at as_of) and the point-in-time provenance guards. Tier-B/C fields without recorded point-in-time evidence are returned as UNSCORABLE — never neutral-filled with 0.0.

Advanced AI-powered web search for technical intelligence. Retrieves up-to-date information including software releases, security advisories, migration guides, benchmarks, developer documentation, and community insights. Supports both standard and streaming responses.

Retrieves details about a Notion entity by its URL or ID. You can fetch the following types of entities: - Page, i.e. from a <page> block or a <mention-page> mention - Database, i.e. from a <database> block or a <mention-database> mention Use the "fetch" tool when you need to see the details of a Notion entity you already know exists and have its URL or ID. Provide the Notion entity's URL or ID in the `id` parameter. You must make multiple calls to the "fetch" tool if you want to fetch multiple entities. Content for pages that are returned use the enhanced Markdown format, which is a superset of the standard Markdown syntax. See the full spec in the description of the "create-pages" tool. Databases can have multiple data sources, which are collections of pages with the same schema. When fetching a database, the tool will return information about all its data sources. Examples of fetching entities: 1. Fetch a page by URL: { "id": "https://www.notion.so/workspace/Product-Requirements-1234567890abcdef" } 2. Fetch a page by ID (UUIDv4 with dashes): { "id": "12345678-90ab-cdef-1234-567890abcdef" } 3. Fetch a page by ID (UUIDv4 without dashes): { "id": "1234567890abcdef1234567890abcdef" } 4. Fetch a database: { "id": "https://www.notion.so/workspace/Projects-Database-abcdef1234567890" } Common use cases: - "What are the product requirements still need to be implemented from this ticket https://notion.so/page-url?" - "Show me the details of the project database at this URL" - "Get the content of page 12345678-90ab-cdef-1234-567890abcdef"

Fetch full document content for a search result.

Fetch and extract content from a web page. Returns the page content in markdown format.

Retrieve Stripe object details by ID. IMPORTANT: Only call this tool after search_stripe_resources is called to get specific object IDs. Do not use this tool to discover or search for objects. This tool fetches the object information from Stripe including all available fields. It is only able to fetch the following resources (prefixes): - Payment Intents (pi_) - Charges (ch_) - Invoices (in_) - Prices (price_) - Products (prod_) - Subscriptions (sub_) - Customers (cus_) It takes one argument: - id (str): The unique identifier for the Stripe object (e.g. cus_123, pi_123). Note that any amount returned is in currency minor units, e.g. cents for USD and yen for JPY.

Fetch full article content from a linux.do post URL

List available analytics tools and metrics for a specific report. Call this before data_query to know which tool_name and metric values are valid.

Retrieves a list of files associated with the authenticated project. Results can be filtered by toolkit and tool slugs.

Generates a presigned URL for uploading a file to S3. This endpoint handles deduplication by checking if a file with the same MD5 hash already exists.

Finalize a draft invoice — IRREVERSIBLE. Validates the data against the target e-invoice format, generates the legally required artifact (XRechnung: standalone CII XML; ZUGFeRD/Factur-X: PDF/A-3 with embedded XML), stores it immutably (GoBD), and locks the invoice against further edits. The format defaults to the customer's preferredInvoiceFormat (tenant default: zugferdPdf); pass format explicitly to override for this invoice — 'xRechnungXml' requires the customer to have a valid Leitweg-ID (set via update_customer). Check eInvoiceIssues on get_invoice first to avoid validation errors. After success, fetch the document with get_invoice_document or email it with send_invoice. Response: { invoice { status:'finalized', format, hasDocument:true, ... } }. Errors: { error: { code: 'invalid_state' | 'validation_failed' (details[] lists each problem) | 'precondition_failed' | 'not_found' | 'bad_input' | 'subscription_required', ... } }.

Resolves a brand, content plan, or workstream name to ids. Pass the ids to the other tools. Optional 'brandId' scopes plan and workstream search to one brand. Empty query lists accessible brands.

Find geological stratigraphic columns, rock layers, and geological history for any location worldwide. Use for geology, bedrock, formations, age dating, and stratigraphic analysis.