google-surf-mcp

Dependency freshness

Declared = lowest version the kit's dependency file (package.json, pyproject.toml or requirements.txt) allows. Latest = the npm "latest" tag or the newest PyPI release. TypeScript, the Stripe SDK, FastAPI and other 0.x packages are shown but not counted in the verdict.

What's in the stack

Framework

Vite

AI

Anthropic SDK

Testing

Vitest

Detected from declared dependencies. A listed package means it's installed, not necessarily fully wired up.

What the README says you get

• AI
  Graph hybrid retrievalGraph hybrid retrieval: Fresh web results, papers, stored content, codebases, and the project graph are searched independently.
• Analytics
  Local graph analysis and exportLocal graph analysis and export: PageRank, PPR, connected components, and Louvain communities run without a separate Neo4j server.
• API
  Seven MCP toolsSeven tools are available by default: `search` / `search_parallel` / `extract` / `scholar_search` / `project_memory_search` / `project_memory` / `health`.
• API
  API-key-free browser searchBrowser search needs no API key.
• Data
  Automatic project memoryAutomatic project memory: Search results, extracted bodies, and code repositories are stored in the current project.
• Data
  Ontology and data lineageOntology and data lineage: Web sources, papers, code, plans, experiments, and decisions become typed entities and relations.
• Data
  Cross-project knowledge reuseCross-project knowledge reuse: Projects remain isolated but selected projects can be searched together.
• Other
  Web, paper, codebase searchWeb, paper, and codebase search: Google web search is the default, while Scholar is used for paper-specific metadata.
• Other
  Web and PDF extractionWeb and academic document extraction: HTML and PDF extraction returns available titles, authors, DOIs, publication metadata, and body text.
• Other
  Structured codebase searchStructured codebase search: Tree-sitter links files, symbols, imports, and calls from local projects and relevant GitHub repositories.
• Other
  Durable research historyDurable research history: Session intent, plans, experiments, failures, and decisions supplied by the MCP host are stored as revisions and linked to their supporting evidence.
• Other
  Dedicated logged-out Chrome profileDedicated logged-out profile that never reads or copies the user's Chrome profile
• Other
  CAPTCHA detection and recoveryCAPTCHA detection and environment-specific recovery
• Other
  SearchApi provider fallbackSearchApi can be configured as an optional primary provider or fallback.

Extracted from the kit's README by a local AI model (deepseek-flash) on Oct 1, 2026. Every item is checked against an exact README quote. A README claim is the maker's description, not something we tested.