{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_8pdyt89qfyq9","handle":"mcp-research","url":"https://wellknown.network/agents/mcp-research","links":{"self":"https://wellknown.network/agents/mcp-research/record.json","html":"https://wellknown.network/agents/mcp-research","markdown":"https://wellknown.network/agents/mcp-research/record.md","api":"https://wellknown.network/api/v1/agents/mcp-research","status":"https://wellknown.network/api/v1/agents/mcp-research/status","claim":"https://wellknown.network/agents/mcp-research/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-research/claim.json","badge":"https://wellknown.network/agents/mcp-research/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-research/history","tools":"https://wellknown.network/api/v1/agents/mcp-research/tools"},"ard":{"identifier":"urn:air::server:mcp-research","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-research","summary":"Web research MCP server: search, fetch, academic, twitter, and compound research tools","description":"# mcp-research\n\n<!-- mcp-name: io.github.mabaam/mcp-research -->\n\nMCP server for web research, academic papers, Twitter/X, YouTube, and file ingestion. Eight tools for AI assistants — all via the MCP stdio protocol. Includes credential vault for institutional access, CAPTCHA detection, and token-efficient output.\n\n## Tools\n\n| Tool | Description |\n|------|-------------|\n| `web_search` | 3-tier search cascade: Brave API → DuckDuckGo → HTML scraper |\n| `fetch_url` | Fetch any URL → clean markdown, with SSRF protection and 24h cache |\n| `research` | Compound pipeline: query rewrite → search → parallel fetch → summarize → synthesize |\n| `youtube_essence` | YouTube video → transcript, summary, key points, chapters, quotes |\n| `deep_ingest` | Extract text from files: PDF, DOCX, XLSX, PPTX, audio, video, images |\n| `academic_lookup` | Resolve DOI / ArXiv / PubMed → metadata + full text via institutional access |\n| `twitter_extract` | Extract tweets and threads from X.com/Twitter |\n| `vault_status` | Show loaded credential profiles and dependency status (never exposes secrets) |\n\nAll tools are **read-only** — they fetch and transform content, never modify anything.\n\n## Install\n\n```bash\npip install mcp-research\n```\n\nOr run directly with `uvx` (zero-install):\n\n```bash\nuvx mcp-research\n```\n\nOptional extras:\n\n```bash\npip install 'mcp-research[twitter]'    # yt-dlp for Twitter extraction\npip install 'mcp-research[youtube]'    # yt-dlp + faster-whisper for YouTube\npip install 'mcp-research[academic]'   # PyPDF2 for academic PDFs\npip install 'mcp-research[ingest]'     # PDF, DOCX, XLSX, PPTX, audio support\npip install 'mcp-research[all]'        # everything\n```\n\nCheck your setup:\n\n```bash\nmcp-research doctor\n```\n\n## Usage with Claude Code\n\nAdd to your Claude Code MCP config (`~/.claude/settings.json` or project `.mcp.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"research\": {\n      \"command\": \"uvx\",\n      \"args\": [\"mcp-research\"],\n      \"env\": {\n        \"BRAVE_API_KEY\": \"BSA...\",\n     …","publisher":null,"homepage":"https://maibaam.com","repository":"https://github.com/MABAAM/Maibaamcrawler/issues","version":"0.3.0","license":null,"protocols":["mcp"],"tags":["ai-tools","claude","mcp","model-context-protocol","research","web-search"],"pricing":null,"endpoints":[{"url":"pypi:mcp-research","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"}},"derived":{"capabilities":[{"slug":"content.writing","name":"Writing & Editing","confidence":1,"provenance":"derived"},{"slug":"data.web-search","name":"Web Search","confidence":1,"provenance":"declared"},{"slug":"research.academic","name":"Academic Research","confidence":1,"provenance":"derived"},{"slug":"data.web-scraping","name":"Web Scraping","confidence":0.825,"provenance":"derived"},{"slug":"content.social","name":"Social Media","confidence":0.779,"provenance":"derived"},{"slug":"security.secrets","name":"Secrets Management","confidence":0.779,"provenance":"derived"}],"categories":["content","data","research","security"],"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-research","registry":"pypi","observedAt":"2026-10-28T13:24:35.078Z","publishedAt":"2026-04-09T13:10:16.121506Z","latestVersion":"0.3.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-research","url":"https://pypi.org/project/mcp-research/","firstSeenAt":"2026-09-10T03:19:18.561Z","fetchedAt":"2026-10-28T13:22:21.745Z","normalizedAt":"2026-10-28T13:22:21.745Z"}]},"firstSeenAt":"2026-09-10T03:19:18.561Z","updatedAt":"2026-10-28T13:24:35.078Z"}