$ timeahead.in
/ servers/pypi/gpt-researcher
pypi

gpt-researcher

An autonomous agent that conducts deep research on any data using any LLM providers

29k stars20k/wkupdated 3d agogithub ↗
70fair
▣ Overview
WebsiteDocumentationDiscordPyPI versionOpen In ColabDocker Image VersionSkillTwitter FollowGitHub Release

What it does

An autonomous research agent that conducts investigations on a research topic and produces comprehensive reports. It uses a planner-execution-publisher architecture: a planner decomposes the query into focused research questions, execution agents gather information from over 20 web sources in parallel, and a publisher synthesizes findings into detailed reports with citations. The agent supports web research, local document analysis, smart image scraping, and exports to PDF or Word formats. Reports can exceed 2,000 words with proper source attribution.

Who it's for

Researchers and analysts requiring automated report generation, developers building research automation into applications, and organizations needing rapid synthesis of information from multiple sources without manual curation overhead.

Common use cases

  • Generate comprehensive research reports on complex topics in minutes
  • Gather and synthesize information from 20+ sources with proper citation
  • Create fact-checked analytical reports with minimal manual effort
  • Automate recurring research workflows for competitive intelligence and monitoring
  • Export finalized research to PDF, Word, or other formats

Setup pitfalls

  • Requires credentials for multiple services: OPENAI_API_KEY (or compatible LLM provider), TAVILY_API_KEY (search), and optional GEMINI_API_KEY for image generation — 3 secrets detected in scanning
  • Requires Python 3.11 or later
  • Writes research reports and exports to filesystem — verify adequate disk space and write permissions
  • Makes outbound network calls to web sources — may require proxy configuration or firewall allowlist
3 credentials detected in repository history via Gitleaks
▣ Score BreakdownMCPScore = Σ(raw × weight)
DimensionRawWeighted
Security
35%
40
14.0
Freshness
25%
100
25.0
Adoption
20%
92
18.4
Quality
10%
80
8.0
Trust
10%
50
5.0
Total
70.4
⚿ Capabilities & Risk Explainer
fs readfs writenetworkexecsecrets
◆ Risk level: high
fs read + fs write + network + exec + secrets active — can execute code, access credentials, and make external network calls.
⚙ Install config
Claude Desktop · Cursor · Windsurf · VS Code (Copilot) · Claude Code
add to your MCP client config:
{
  "mcpServers": {
    "gpt-researcher-1": {
      "command": "uvx",
      "args": [
        "gpt-researcher"
      ]
    }
  }
}
📈 Score historylast 46 snapshots
5/10/20267/21/2026 · 46 snapshots
⚙ Maintenance health
73/ 100 · is this project alive?
contributors (1y)82
top contributor share48%
releases (1y)15
last release2d ago
ci✓ passing
⛁ Raw data
weekly downloads20k
github stars29k
forks4k
open issues114
license✓ present
readme length16761 chars
last publish0d ago
last commit3d ago
last updated5d ago
install verified✓ pass · 68d ago
owner of this server? claim your listing to get a verified badgeclaim →
🔔 Score drop alerts
get notified by email when this server's score drops 5+ points