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

mark3labs/mcp-go

A Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools. observed · 2026-08-28

github.com/mark3labs/mcp-go · homepage · Go · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

83/100

  • Activity 97
  • Release rhythm 85
  • Longevity 46
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: 4
  • age_days: 644
  • days_rel: 21
  • days_push: 21
  • n_releases_24m: 88

Full methodology

Adoption not part of the score

9035 stars · 878 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A Go SDK implementing the Model Context Protocol (MCP), letting developers build MCP servers that expose tools, resources, and prompts to LLM applications. It supports multiple transports (stdio, StreamableHTTP, SSE, in-process) with a high-level, type-safe API.

Use cases

  • build an MCP server in Go that exposes tools to Claude or other LLM clients
  • connect my Go backend's data sources to LLM applications via MCP
  • expose internal APIs as MCP tools for AI agents
  • run an MCP server over stdio for desktop AI apps
  • serve MCP over HTTP with server-sent events
  • add OAuth-protected MCP resources

When to choose

  • you are writing MCP servers or clients in Go
  • you want a high-level, low-boilerplate SDK covering tools, resources, and prompts
  • you need multiple transport options including stdio and HTTP

When to avoid

  • you need MCP support in another language like Python or TypeScript
  • you require advanced MCP capabilities that are still in progress
  • your project is not related to LLM-tool integration

Facets

library · maturity active

mcp sdk api-framework http-server auth large-language-models developer-tools apis backend go cross-platform cli model-context-protocol llm-tools stdio-transport server-sent-events tool-integration ai-agents web-server

3 sources

Member repositories

RepositoryRoleHealth v2
mark3labs/mcp-gomain83

For agents

markdown · JSON · MCP: product_card(name="mark3labs/mcp-go")

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