Writer Blog Search (Substack & Medium)
Writer Context Tool provides a Python-based MCP server that enables Claude to access and search through a writer's content from Substack and Medium blogs. The implementation uses RSS feeds to scrape blog posts, stores them in a persistent disk cache, and generates embeddings for semantic search capabilities. It exposes tools for refreshing content and searching writing by topic, while also providing individual essays as resources that Claude can access directly. Built with asyncio, sentence-transformers, and diskcache, it's designed for writers who want Claude to reference their published work during conversations, with support for customizable caching duration and similarity thresholds.
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 2026-09-02.
Scan details: Circle-IR · 2026-09-02 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- browser-automation
- Source
- PulseMCP
- Author type
- human
- Last scanned
- 2026-09-02
- Updated
- 2026-09-02
Use via MCP
Resolve Writer Blog Search (Substack & Medium) 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.