{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_23758dc4am9j","handle":"smart-webfetch-mcp","url":"https://wellknown.network/agents/smart-webfetch-mcp","links":{"self":"https://wellknown.network/agents/smart-webfetch-mcp/record.json","html":"https://wellknown.network/agents/smart-webfetch-mcp","markdown":"https://wellknown.network/agents/smart-webfetch-mcp/record.md","api":"https://wellknown.network/api/v1/agents/smart-webfetch-mcp","status":"https://wellknown.network/api/v1/agents/smart-webfetch-mcp/status","claim":"https://wellknown.network/agents/smart-webfetch-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/smart-webfetch-mcp/claim.json","badge":"https://wellknown.network/agents/smart-webfetch-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:smart-webfetch-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"smart-webfetch-mcp","summary":"Context-aware web fetching MCP server that respects token limits","description":"# Smart WebFetch MCP Server\n\n[![PyPI version](https://img.shields.io/pypi/v/smart-webfetch-mcp)](https://pypi.org/project/smart-webfetch-mcp/)\n[![PyPI downloads](https://img.shields.io/pypi/dm/smart-webfetch-mcp)](https://pypi.org/project/smart-webfetch-mcp/)\n[![Python version](https://img.shields.io/pypi/pyversions/smart-webfetch-mcp)](https://pypi.org/project/smart-webfetch-mcp/)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n\nContext-aware web fetching for LLMs. Prevents context window flooding by checking page size before fetching and providing surgical extraction tools.\n\n## The Problem\n\nStandard web fetch tools dump entire pages into the context window, often:\n- Exceeding token limits\n- Wasting context on navigation, footers, ads\n- Flooding the model with irrelevant content\n\n## The Solution\n\nSmart WebFetch provides 7 tools for intelligent web fetching:\n\n| Tool | Purpose |\n|------|---------|\n| `web_preflight` | Check page size before fetching |\n| `web_smart_fetch` | Fetch with automatic truncation |\n| `web_fetch_code` | Extract only code blocks |\n| `web_fetch_section` | Fetch specific heading/section |\n| `web_fetch_chunked` | Paginated fetching for large docs |\n| `web_fetch_links` | Extract all links from a page |\n| `web_fetch_tables` | Extract tables as markdown |\n\n## Installation\n\n```bash\n# Install from PyPI\npip install smart-webfetch-mcp\n\n# Or with uvx (recommended for MCP)\nuvx smart-webfetch-mcp\n```\n\n## Configuration\n\n### Claude Code\n\n```bash\nclaude mcp add --transport stdio smart-webfetch -- uvx smart-webfetch-mcp\n```\n\n### OpenCode\n\nAdd to your `opencode.json`:\n\n```json\n{\n  \"mcp\": {\n    \"smart-webfetch\": {\n      \"type\": \"local\",\n      \"command\": [\"uvx\", \"smart-webfetch-mcp\"],\n      \"enabled\": true\n    }\n  }\n}\n```\n\n### Claude Desktop\n\nAdd to `claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"smart-webfetch\": {\n      \"command\": \"uvx\",\n      \"args\": [\"smart-webfetch-mcp\"]\n    }\n  }\n}\n``…","publisher":{"name":"Matt Kelly","url":null},"homepage":"https://github.com/mathisto/smart-webfetch-mcp","repository":"https://github.com/mathisto/smart-webfetch-mcp","version":"0.3.0","license":null,"protocols":["mcp"],"tags":["context","fetch","llm","mcp","tokens","web"],"pricing":null,"endpoints":[{"url":"pypi:smart-webfetch-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"data.web-scraping","name":"Web Scraping","confidence":1,"provenance":"derived"},{"slug":"research.web","name":"Deep Web Research","confidence":1,"provenance":"declared"}],"categories":["data","research"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"smart-webfetch-mcp","registry":"pypi","observedAt":"2026-09-10T12:23:36.975Z","publishedAt":"2025-11-28T06:35:49.877753Z","latestVersion":"0.3.0"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"smart-webfetch-mcp","url":"https://pypi.org/project/smart-webfetch-mcp/","firstSeenAt":"2026-09-10T12:22:39.896Z","fetchedAt":"2026-09-10T12:22:39.896Z","normalizedAt":"2026-09-10T12:22:39.896Z"}]},"firstSeenAt":"2026-09-10T12:22:39.896Z","updatedAt":"2026-09-10T12:23:36.975Z"}