agentcheck
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.
Descriptor
Candidate descriptor · transport http
Tools
get_tiers— List the four checkup tiers (free, basic, full, enterprise) with price and included test quotas.get_free_scan_pool— Read the shared weekly free-scan pool - used, max, remaining and seconds until reset.validate_bot— Check whether a URL is safe and points at a reachable A2A agent or OpenAI-compatible chat API before starting a checkup.start_free_checkup— Start a free-tier checkup of a bot (CheckupRequest - bot_type, bot_url, optional system_prompt, email, industry). Paid tiers go through create_checkout.create_checkout— Create a Stripe Checkout session for a paid tier (CheckoutRequest) and return the redirect URL; testing starts after payment.stream_checkup_progress— Server-sent-events stream of a running checkup's progress by checkup_id.get_checkup_report— Fetch the scored report for a completed checkup by checkup_id.get_exam_status— Poll the status of an exam-mode session (the mode where the customer's bot calls AgentCheck's generated OpenAI-compatible URL).get_public_stats— Aggregate public scan statistics for the landing page; hidden below a scan-count threshold.get_health— Service liveness and version.
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.