AccuKnox Asset Manager
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 stdio
Tools
search_assets— READ-ONLY. Search and filter cloud infrastructure assets by id, type name, type category, label, region, cloud provider, deployment state and date window; returns a list or a count.get_model_vulnerabilities— READ-ONLY. AI/ML model security issue summary across ML models, LLM models and datasets, broken down by risk factor.data_type_selection— Unified list of the finding data types available to the other finding tools (Cloud Findings, Container Image Findings, STIG Findings, LLM Findings, All Findings, and others).get_finding_config— Retrieve finding configuration metadata for a data type — the valid display_fields, filter_fields and group_by values for a later get_finding call.get_finding— Fetch findings for a data type with ordering, pagination (page / page_size), extra_filters, display_fields, group_by and free-text search.get_finding_filter— Return the dropdown filter values available for a given filter_field and data type.get_finding_funnel— Build a funnel over a finding data type — narrow findings through up to six ordered filter stages and return the count remaining at each stage.
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.