Fetch URL
GKMCP is a Rust-based MCP server implementation that provides a fetch tool for retrieving content from URLs. Built with the Tokio async runtime and Reqwest HTTP client, it follows the 2025-03-26 protocol version specification and implements the core MCP request handling flow including initialization, tool listing, and tool execution. The server processes JSON-RPC style requests from stdin, handles tool calls asynchronously, and returns formatted responses with proper error handling. This implementation is particularly useful for AI assistants that need to access web content during conversations, enabling capabilities like retrieving documentation, checking online resources, or gathering information from specific websites.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- file-system
- Source
- PulseMCP
- Repository
- github.com/kov/gkmcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Fetch URL from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.