Some urgent fixes to run GPTR smoothly with provider agnostic. Please open issues if you find anything missed!

What's Changed

• 1514 added Tavily installation requirements txt by @thepawarrahul in #1516
• Fix for Frontend Docker build by @CezaryKlus in #1522
• Fix MCP retriever ignoring structured_content; prefer structured data with fallback to content #1480 (solved) by @sriramsowmithri9807 in #1518
• feat: Add PWA capabilities to the frontend by @TheSpaceGod in #1511

New Contributors

• @thepawarrahul made their first contribution in #1516
• @CezaryKlus made their first contribution in #1522
• @TheSpaceGod made their first contribution in #1511

Full Changelog: v.3.3.5...v.3.3.6

Introducing a completely new research experience with our latest NextJS application. You can now chat with research results, deepen research, connect MCPs directly from UI and more!

What's Changed

• feat(llm): stop sending temperature to non‑supporting models by @expphoto in #1485
• fix(frontend): use existing gptr-logo.png for background to stop 404 by @expphoto in #1484
• Update duckduckgo.py by @adityasingla71 in #1491
• Updated the validation logic for max_tokensto allow a maximum of ​​32,000​​ (previously capped at 16,000). by @hc-tec in #1488
• feat: Add support for custom OpenAI base URL for OpenAI-compatible APIs by @borderlessboy in #1499
• Summary: Fix missing WebSocketDisconnect import by @hasbegun in #1497
• Bug fix: Remove the encoding parameter from kwargs to avoid passing an unsupported argument in the LLM call. by @whaler404 in #1494
• Fix critical path traversal vulnerability in file operations by @saharmor in #1438
• feat: add netmind provider by @anhuaxiang in #1459

New Contributors

• @expphoto made their first contribution in #1485
• @adityasingla71 made their first contribution in #1491
• @hc-tec made their first contribution in #1488
• @borderlessboy made their first contribution in #1499
• @hasbegun made their first contribution in #1497
• @whaler404 made their first contribution in #1494
• @saharmor made their first contribution in #1438
• @anhuaxiang made their first contribution in #1459

Full Changelog: v.3.3.3...v.3.3.4

What's Changed

• GPT-5 Support! Less costs, better performance and larger input context windows
• feat: Add Hallucination Evaluation for GPTResearcher + judges library by @julianeagu in #1439
• fix: make exa retriever respect query domains by @mys721tx in #1464
• bug_fix: vectorstore_filter not passed by @viboognesh in #1461
• Update config.md by @sdisaacson in #1465
• feat: Add enhanced Serper API support with country, language, date filters and configurable site exclusion by @hurxxxx in #1472
• Fix scraper FireCrawl markdown error by @hung96ad in #1473

New Contributors

• @julianeagu made their first contribution in #1439
• @mys721tx made their first contribution in #1464
• @viboognesh made their first contribution in #1461
• @hung96ad made their first contribution in #1473

Full Changelog: v.3.3.1...v.3.3.3

What's Changed

• feat: Add Hallucination Evaluation for GPTResearcher + judges library by @julianeagu in #1439
• fix: make exa retriever respect query domains by @mys721tx in #1464
• bug_fix: vectorstore_filter not passed by @viboognesh in #1461
• Update config.md by @sdisaacson in #1465

New Contributors

• @julianeagu made their first contribution in #1439
• @mys721tx made their first contribution in #1464
• @viboognesh made their first contribution in #1461

Full Changelog: v.3.3.1...v.3.3.2

This version focuses on bug fixes and performance improvements. Thank you and welcome to all the new contributors to the community!

What's Changed

• fix: Resolve 'ScrapeResponse' object subscriptable error in FireCrawl scraper by @sriramsowmithri9807 in #1432
• remove spurious file (submodule ref) by @grota in #1440
• fix: linux/arm64 machine cannot pull arm64 image from ghcr by @arielweinberger in #1436
• Add Dockerfile.fullstack - single container for nextjs/backend by @th3w1zard1 in #1433
• fix: langchain dashscope provider out-of-dated by @TRSWNCA in #1455
• Fix zero subtopic error by @Yuxuan1998 in #1454

New Contributors

• @sriramsowmithri9807 made their first contribution in #1432
• @grota made their first contribution in #1440
• @arielweinberger made their first contribution in #1436
• @TRSWNCA made their first contribution in #1455
• @Yuxuan1998 made their first contribution in #1454

Full Changelog: v3.3.0...v.3.3.1

🔗 MCP Integration Now Live 🥳

GPT Researcher now supports Model Context Protocol (MCP) - connect to specialized data sources alongside web search for comprehensive research.

Key Features

• Two-stage intelligent approach: Auto-selects relevant tools and generates contextual research
• Hybrid strategies: Combine web search with MCP servers (RETRIEVER=tavily,mcp)
• Multi-server support: GitHub, financial APIs, academic databases, custom tools
• Zero-config optimization: Works out-of-the-box with sensible defaults

Quick Start

from gpt_researcher import GPTResearcher
import os

# Enable hybrid research
os.environ["RETRIEVER"] = "tavily,mcp"

researcher = GPTResearcher(
    query="What are the latest React patterns?",
    mcp_configs=[{
        "name": "github",
        "command": "npx",
        "args": ["-y", "@modelcontextprotocol/server-github"],
        "env": {"GITHUB_TOKEN": os.getenv("GITHUB_TOKEN")}
    }]
)

context = await researcher.conduct_research()
report = await researcher.write_report()

Use Cases

• Code research: GitHub repos, documentation, technical analysis
• Financial analysis: Market data, stock trends, business intelligence
• Academic research: ArXiv papers, research databases
• Enterprise integration: Internal systems, compliance workflows

Full MCP Documentation | Examples

What's Changed

• MCP client-server Integration for GPTR by @assafelovic in #1424
• Fix #1418: OSError: [Errno 36] File name too long with long Chinese prompt by @qylf0000 in #1428

New Contributors

• @qylf0000 made their first contribution in #1428

Full Changelog: v3.2.9...v3.3.0

Welcome new contributors to the community! Another massive performance boost to GPT researcher with better reasoning model control, improved static UI, additional integrations and bug fixes!

What's Changed

• Add "Deep Research" option to selection and fix formatting in base.py by @hide-lgtm in #1394
• fix: improve error handling in SerperSearch results processing by @grapestore in #1388
• Update firecrawl-py requirement from ^1.12.0 to ^2.5.3 by @dependabot in #1382
• Add WebSocket support to FastAPI server by @dreroc in #1400
• Fix return statements in PyMuPDFScraper by @kongzii in #1407
• [Integration] New provider AI/ML API Added by @D1m7asis in #1399
• add vllm chat client by @teenaxta in #1409
• Expose **kwargs throughout core modules to unlock LangChain integrations by @teenaxta in #1372
• Massively improve static frontend. by @th3w1zard1 in #1401
• Add REASONING_EFFORT to configuration by @KennyDizi in #1416
• ✨ Containerized Multi-Arch Workflows: Production-Ready Docker, and Robust Dependency Management by @th3w1zard1 in #1411

New Contributors

• @hide-lgtm made their first contribution in #1394
• @dreroc made their first contribution in #1400
• @kongzii made their first contribution in #1407
• @D1m7asis made their first contribution in #1399
• @teenaxta made their first contribution in #1409
• @th3w1zard1 made their first contribution in #1401

Full Changelog: v3.2.8...v3.2.9

Welcome to all the new contributors who have helped fixing so many issues, adding new amazing features and improving performance!

What's Changed

• Fix broken link in llms.md by @robsonos in #1333
• Fix #1323: Ollama model parsing issue in multi-agent mode by @mratsim in #1324
• Add support for o4-mini model in temperature & reasoning-effort config by @arminfabritzek in #1346
• EMBEDDING = ':<sentence-transformers/all-MiniLM-L6-v2>' by @N4SIRODDIN3 in #1313
• feat: Adds support for gigachat embeddings to the gigachat LLM add-on. by @Rai220 in #1280
• fix: nodriver scraper wait timeout behavior by @ewgdg in #1351
• Strip spaces from "self.output_dir" to prevent exception when writing… by @ivan-latunov in #1350
• IBM Granite by @gabe-l-hart in #1278
• Update filtering-by-domain.md by @kicksent in #1370
• Update getting started link to the doc by @irak99 in #1364
• fix firecrawl error: 'ScrapeResponse' object is not subscriptable by @tvoilex in #1363
• Respect my verbosity! by @tClelford in #1362
• fix python3.11 f-string cannot have backslash by @anexplore in #1352
• bugfix. third argument of ResearchAgent has to be tone by @Masao-Taketani in #1376
• Fix a typo in curator.py by @yuefengz in #1371

New Contributors

• @robsonos made their first contribution in #1333
• @mratsim made their first contribution in #1324
• @arminfabritzek made their first contribution in #1346
• @N4SIRODDIN3 made their first contribution in #1313
• @ivan-latunov made their first contribution in #1350
• @gabe-l-hart made their first contribution in #1278
• @kicksent made their first contribution in #1370
• @irak99 made their first contribution in #1364
• @tvoilex made their first contribution in #1363
• @tClelford made their first contribution in #1362
• @anexplore made their first contribution in #1352
• @Masao-Taketani made their first contribution in #1376
• @yuefengz made their first contribution in #1371

Full Changelog: v3.2.7...v3.2.8

Super exciting release that includes 3 big improvements:

• New MCP server for GPT Researcher! Check out the new repo here.
  What makes the MCP server special:
• 🚀 Seamless integration with Claude Desktop via MCP
• 🔎 Transform basic searches into comprehensive research with a single command
• ✨ Get high-quality, validated information from multiple reliable sources
• 📊 Optimize your context window with only the most relevant content
• 🧠 Enable your AI assistant to reason better with well-structured research

MCP Server Docs: https://docs.gptr.dev/docs/gpt-researcher/mcp-server/getting-started

Claude Demo:
https://github.com/user-attachments/assets/ef97eea5-a409-42b9-8f6d-b82ab16c52a8

In addition:

• You can now add a custom prompt to the write_report method. For example: report = researcher.write_report(custom_prompt="write a short answer based on the research findings")
• You can now also run quick web search with your dedicated search engine: search_results = researcher.quick_search(query=query)

What's Changed

• Update to detailed_report.py to include complement_source_urls as a p… by @Laurie2905-JOHN in #1308
• Feature/custom report prompt by @assafelovic in #1309
• feat: Add language support to reports and frontend input by @hurxxxx in #1213
• MCP Server by @assafelovic in #1310
• Frontend goodies by @ElishaKay in #1235

New Contributors

• @Laurie2905-JOHN made their first contribution in #1308

Full Changelog: v3.2.5...v3.2.6