{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_2c2w56h9wc8v","handle":"mcp-ferris-search","url":"https://wellknown.network/agents/mcp-ferris-search","links":{"self":"https://wellknown.network/agents/mcp-ferris-search/record.json","html":"https://wellknown.network/agents/mcp-ferris-search","markdown":"https://wellknown.network/agents/mcp-ferris-search/record.md","api":"https://wellknown.network/api/v1/agents/mcp-ferris-search","status":"https://wellknown.network/api/v1/agents/mcp-ferris-search/status","claim":"https://wellknown.network/agents/mcp-ferris-search/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-ferris-search/claim.json","badge":"https://wellknown.network/agents/mcp-ferris-search/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-ferris-search/history","tools":"https://wellknown.network/api/v1/agents/mcp-ferris-search/tools"},"ard":{"identifier":"urn:air::server:mcp-ferris-search","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-ferris-search","summary":"A blazing-fast MCP server for multi-engine web search","description":"# MCP Ferris Search\n\nA blazing-fast MCP (Model Context Protocol) server for multi-engine web search, written in Python.\n\nThis is a Python implementation inspired by the original [ferris-search](https://github.com/lispking/ferris-search) Rust project.\n\n## Features\n\n- **Multi-engine fan-out** — search across multiple engines simultaneously with a single call\n- **9 search engines** — Bing, DuckDuckGo, Brave, Baidu, CSDN, Juejin, Zhihu, GitHub, GitHub Code\n- **7 MCP tools** — `web_search` + 6 content fetchers\n- **No API keys required** for most engines (Brave requires API key)\n- **Proxy support** — HTTP/SOCKS5 proxy via environment variables\n\n## Installation\n\n### From PyPI (recommended)\n\n```bash\npip install mcp-ferris-search\n```\n\n### Using uvx\n\n```bash\nuvx mcp-ferris-search\n```\n\n### From source\n\n```bash\ngit clone https://github.com/your-username/mcp-ferris-search.git\ncd mcp-ferris-search\npip install -e .\n```\n\n## Configuration\n\n### Claude Desktop / Cursor\n\nAdd to your MCP settings:\n\n```json\n{\n  \"mcpServers\": {\n    \"ferris-search\": {\n      \"command\": \"uvx\",\n      \"args\": [\"mcp-ferris-search\"],\n      \"env\": {\n        \"DEFAULT_SEARCH_ENGINE\": \"bing\"\n      }\n    }\n  }\n}\n```\n\n### Environment Variables\n\n| Variable | Default | Description |\n|----------|---------|-------------|\n| `DEFAULT_SEARCH_ENGINE` | `bing` | Default engine when `engines` param is omitted |\n| `ALLOWED_SEARCH_ENGINES` | all engines | Comma-separated allow-list |\n| `BRAVE_API_KEY` | — | Required for Brave search |\n| `GITHUB_TOKEN` | — | Optional, raises GitHub API rate limit |\n| `USE_PROXY` | `false` | Enable HTTP/SOCKS5 proxy |\n| `PROXY_URL` | `http://127.0.0.1:7890` | Proxy address |\n\n## MCP Tools\n\n### `web_search`\n\nSearch the web using one or more engines simultaneously.\n\n```json\n{\n  \"query\": \"rust async runtime\",\n  \"engines\": [\"bing\", \"duckduckgo\"],\n  \"limit\": 10\n}\n```\n\n| Parameter | Type | Default | Description |\n|-----------|------|---------|-------------|\n| `query` | string | required | Search query |…","publisher":{"name":"Ferris Search Team","url":null},"homepage":"https://github.com/lispking/ferris-search","repository":"https://github.com/lispking/ferris-search","version":"0.1.0","license":"Apache-2.0","protocols":["mcp"],"tags":["ai","claude","mcp","search","web"],"pricing":null,"endpoints":[{"url":"pypi:mcp-ferris-search","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"data.web-search","name":"Web Search","confidence":1,"provenance":"derived"},{"slug":"research.web","name":"Deep Web Research","confidence":1,"provenance":"declared"},{"slug":"dev.version-control","name":"Version Control","confidence":0.745,"provenance":"derived"}],"categories":["data","dev","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":"mcp-ferris-search","registry":"pypi","observedAt":"2026-10-28T11:27:13.099Z","publishedAt":"2026-03-31T07:26:36.799094Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-ferris-search","url":"https://pypi.org/project/mcp-ferris-search/","firstSeenAt":"2026-09-10T01:20:44.190Z","fetchedAt":"2026-10-28T11:25:33.086Z","normalizedAt":"2026-10-28T11:25:33.086Z"}]},"firstSeenAt":"2026-09-10T01:20:44.190Z","updatedAt":"2026-10-28T11:27:13.099Z"}