Jina AI Reader
This lightweight MCP server by jSwords91 provides web content extraction capabilities through Jina AI's r.jina.ai service, which converts web pages into clean Markdown format optimized for LLM consumption. The implementation features automatic content hashing and caching with stable URI assignment, token counting using tiktoken, and change detection to track content updates over time. Built as a minimal alternative to existing fetch MCP servers, it's particularly useful for AI assistants that need to access and process web content in a token-aware manner with built-in caching to avoid redundant requests.
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 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- social-media
- Source
- PulseMCP
- Repository
- github.com/jswords91/jina-ai-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Jina AI Reader 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.