scrunch

Endpoint

Hosted endpoint · transport streamable-http

Connect

This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):

For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:

If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:

Tools

• get_presence_metrics — Brand mention rate (presence) over time; include_competitors compares brands side by side.
• get_position_metrics — How often the brand appears top/middle/bottom within AI responses, relative to other brands mentioned.
• get_sentiment_metrics — Sentiment breakdown (positive, mixed, negative) for brand mentions.
• get_citations_metrics — AI-cited URLs broken down by ownership: brand-owned, competitor-owned, third-party.
• generate_explorer_chart — Builds a Scrunch Explorer chart from a metric/breakdown/filter spec and returns a deep link.
• create_explorer_dashboard — Creates a saved Explorer dashboard of metric tiles and returns a deep link.
• list_responses — Lists individual AI responses (observations) for a brand; ids-only by default, limit 10 / max 100.
• get_response — Fetches a single AI response by ID with evaluation data, citations, and competitor analysis.
• list_prompt_variants — Lists the prompt variants Scrunch is monitoring for a brand, with filters.
• create_prompt — Adds a new seed prompt, optionally with category, key topics, persona, platforms, and tags.
• archive_prompt — Archives (soft-deletes) a seed prompt so it stops running; history is preserved.
• unarchive_prompt — Restores previously archived prompts so they resume running.
• get_tags — Returns all tags currently configured for a brand.
• add_tag_to_prompts — Appends one tag to up to 500 prompts; existing tags preserved, tag created if new.
• remove_tag_from_prompts — Removes one tag from a list of prompts; other tags unaffected.
• list_brands — Lists the brands in the organization.
• create_brand — Creates a new brand.
• update_brand — Updates brand configuration.
• list_competitors — Lists tracked competitors for a brand.
• create_competitor — Adds a competitor to a brand.
• update_competitor — Updates a competitor record.
• archive_competitor — Archives a competitor (soft delete).
• list_personas — Lists the personas metrics can be sliced by.
• create_persona — Creates a persona.
• archive_persona — Archives a persona (soft delete).
• update_persona_on_prompts — Reassigns a persona across a set of prompts.
• import_agent_traffic — Imports AI bot / agent traffic events into Scrunch.
• export_agent_traffic — Exports Scrunch's AI bot crawl data (e.g. as CSV for spreadsheets).
• list_scrunch_help_collections — Lists Scrunch help-doc collections.
• get_scrunch_help_article — Fetches a Scrunch help-doc article.
• fetch_scrunch_url — Server-side fetch of a Scrunch URL / deep link.
• get_caller_identity — Returns the identity of the authenticated MCP caller.
• get_current_date — Returns the server's current date for relative date phrasing.

About MCP

The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.

Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.