Ross ROSS = Recommend OSS · open-source software intelligence for agents

ref-tools/ref-tools-mcp

Helping coding agents never make mistakes working with public or private libraries without wasting the context window. observed · 2026-08-28

github.com/ref-tools/ref-tools-mcp · homepage · TypeScript · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

59/100

  • Activity 89
  • Release rhythm 35
  • Longevity 35

Flags: no_releases

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 498
  • days_rel: n/a
  • days_push: 68
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

1156 stars · 68 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Ref MCP is a Model Context Protocol server that gives AI coding agents fast, token-efficient access to documentation for public and private APIs, services, and libraries. It uses agentic search with session-aware filtering and relevance-based page section extraction to minimize context window usage.

Use cases

  • let my coding agent look up library documentation without wasting context tokens
  • search API docs from Claude Code or another MCP-compatible agent
  • avoid context rot when an agent reads long documentation pages
  • give an LLM agent up-to-date docs for private internal libraries
  • reduce repeated search results across an agent's session
  • fetch only the relevant sections of a documentation page

When to choose

  • you use MCP-compatible coding agents like Claude Code and want accurate, current library documentation
  • context window usage from documentation lookups is a problem
  • you need documentation access for both public and private libraries

When to avoid

  • your agent does not support the Model Context Protocol
  • you need general web search rather than documentation-focused retrieval
  • you want a fully offline or self-hosted documentation solution

Facets

service · maturity active

search-engine documentation mcp rag developer-tools developer-tools documentation large-language-models cli mcp-server coding-agent documentation-search token-efficient context-management ai-agents nodejs typescript mcp

2 sources

Member repositories

RepositoryRoleHealth v2
ref-tools/ref-tools-mcpmain59

For agents

markdown · JSON · MCP: product_card(name="ref-tools/ref-tools-mcp")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem