MCP server · Knostic

knostic-agentmesh

View descriptor → Knostic provider profile

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.

⚠ Proposed MCP surface. No official hosted MCP server was found for Knostic. The tools below are a candidate set derived from this provider's API, and the link points at the source descriptor rather than a live server. If Knostic publishes an official server, this page will update to it on the next build.

Provider: Knostic Type: Candidate descriptor Transport: http Host: raw.githubusercontent.com

Descriptor

https://raw.githubusercontent.com/api-evangelist/knostic/refs/heads/main/mcp/knostic-mcp.yml

Candidate descriptor · transport http

Tools

list_skills — Search the AgentMesh catalog of AI agent skills with scan status, stars and metadata. Supports full-text search, status filtering and SHA-256 hash lookup.
get_skill — Get full details for one skill including version history, scan results for the selected version, and repository metadata.
get_skill_version_scans — Get all scan results for a specific skill version across scanner versions.
list_mcp_servers — Search the AgentMesh catalog of MCP servers with scan status, stars and metadata.
get_mcp_server — Get full details for one MCP server including version history and scan results.
get_mcp_version_scans — Get all scan results for a specific MCP server version.
list_extensions — Search VS Code / IDE marketplace extensions with risk assessment data. Filter by risk status, marketplace, or VSIX SHA-256 hash.
get_extension — Get full risk detail for one extension including risk level, reasons, and code-snippet evidence with file paths.
scan_skill — Trigger an on-demand security scan of a skill by owner:repo[:skill_name] slug. Returns a scan_id to poll. Consumes one of 30 daily scan credits.
scan_extension — Trigger an on-demand security scan of a marketplace extension by marketplace:id slug. Returns a scan_id to poll. Consumes one of 30 daily scan credits.
list_scans — List this API key's scan history with status and result; response carries remaining daily scan credits.
get_scan — Poll one scan by id. Returns queue position and time estimate while pending, then the result and details once completed.

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.