Skip to main content
Glama

Skim

Skim gives agents clean Markdown from public web pages and PDFs, structured extraction, site crawls, page watches and on-demand Signals. It uses a Skim card-plan key for the Claude plugin.

Claude directory plugin

The plugin is now isolated in plugins/skim. Select that folder, not the repository root, for the existing Claude directory entry after Karilyn reviews and approves this change. No directory resubmission is performed by this branch.

From the repository root, run:

node plugins/skim/claude-plugin/build.mjs
node --test plugins/skim/claude-plugin/test.mjs

No dependency install is required. The build checks committed readable source instead of generating a bundle. The plugin has its own sensitive user-config setting; it does not inherit a machine API key or wallet. A local Node program may still need human review. Passing local checks is not directory approval.

Related MCP server: web-scraper

Separate npm client

The existing general-purpose skim-mcp client remains in src/ and dist/, outside the Claude plugin folder, and is not imported or launched by the plugin. Its implementation, package entrypoint, wallet support, and Glama/Smithery launch configuration are unchanged. See the published npm package for that separate client.

Documentation · Support · Privacy · Terms

MIT License.

Available Tools

1 tool
read_urlAInspect

Fetch any URL and return clean, agent-ready Markdown via Skim (skim402.com). Strips nav, ads, and boilerplate; preserves the article body plus structured metadata (title, byline, published date, language, excerpt). Pays $0.002 per call in USDC on Base over the x402 protocol — no API keys, no signup. Use this whenever you need to read web content: articles, docs, blog posts, GitHub READMEs, research papers, etc.

Inputs: url (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.4/5.0

    Scored across 1 tool

    Disambiguation5/5

    Only one tool exists, so there is no ambiguity. Agents will correctly select it for the web content retrieval task.

    Naming Consistency5/5

    The single tool 'read_url' follows a clear verb_noun pattern. Naming is consistent and descriptive within the scope.

    Tool Count3/5

    A single tool server is borderline appropriate. While it serves a focused purpose, the tool count is minimal, leaving agents with no alternatives or complementary operations.

    Completeness4/5

    The tool covers the core functionality of fetching and converting web content to Markdown. Minor gaps include lack of error handling details or support for batch operations, but the surface is complete for its stated purpose.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables extracting clean Markdown from any webpage by paying $0.005 USDC per call via the x402 protocol, with automatic wallet-based payment settlement.
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables extracting clean, structured markdown from any URL—stripping nav, ads, and scripts—for RAG pipelines and AI research agents, with pay-per-call micropayments via x402.
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Lets AI agents make automated USDC micro-payments on Base mainnet via x402/MPP to unlock clean structured data from URLs and other pay-per-call tools like Markdown reading, security scans, wallet enrichment, and settlement proof, with no API key or subscription.
      1
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables agents to convert any URL into clean, structured, agent-optimized content with a single paid call, paying $0.02 USDC per successful extraction via x402 on Base without API keys or accounts.
      MIT