G2 MCP Server
G2's first-party remote MCP server. Exposes G2 buyer intent data, competitive intelligence, the product/category catalog and review analytics to MCP clients over OAuth 2.0. Read-only across the catalog and intent surfaces; research boards are the only writable resource.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Documentation
Documentation link · transport
Tools
list_products— Browse and filter the G2 product catalogshow_product— Retrieve product detailslist_my_products— List products owned by the authenticated accountlist_categories— Browse G2 categoriesshow_category— Retrieve category detailslist_standard_product_reviews— Retrieve product reviewslist_market_intelligence_product_reviews— Retrieve reviews with B2B firmographic datalist_vendors— Browse vendorsshow_vendor— Retrieve vendor detailsbrowse_buyer_intent— Query buyer intent signalsbrowse_product_buyer_intent— Retrieve buyer intent for a single productbrowse_competitive_intelligence— Analyze competitor evaluation activityshow_buyer_intent_dashboard— Display the buyer intent dashboardlist_research_boards— List research boardsshow_research_board— Display a research boardcreate_research_board— Create a research boardupdate_research_board— Update a research boarddelete_research_board— Delete a research boardlist_research_board_products— List products on a research boardadd_products_to_research_board— Add products to a research boardremove_products_from_research_board— Remove products from a research board
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.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.