Tool4LM
This MCP server provides an all-in-one toolkit for local LLMs with web search, document processing, academic research, and mathematical computation capabilities, requiring no API keys. Built by khanhs-234 using TypeScript with the MCP SDK, it integrates multiple search engines (SearXNG, DuckDuckGo), scholarly databases (arXiv, Crossref, Wikipedia), and document formats (PDF, HTML, Markdown) with full-text search via MiniSearch indexing. The implementation includes SSRF protection for web requests, Mozilla Readability for content extraction, MathJS for calculations, and sandbox-based document management, making it valuable for researchers and developers who need a self-contained research assistant that works entirely offline without external API dependencies.
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
- database
- Source
- PulseMCP
- Repository
- github.com/khanhs-234/tool4lm
- Author type
- human
- Last scanned
- 2026-09-02
- Updated
- 2026-09-02
Use via MCP
Resolve Tool4LM 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.