mcpproxy-go and mcp-gopls

mcpproxy-go
53
Established
mcp-gopls
50
Established
Maintenance 13/25
Adoption 10/25
Maturity 15/25
Community 15/25
Maintenance 10/25
Adoption 9/25
Maturity 16/25
Community 15/25
Stars: 159
Forks: 20
Downloads:
Commits (30d): 0
Language: Go
License: MIT
Stars: 70
Forks: 11
Downloads:
Commits (30d): 0
Language: Go
License: Apache-2.0
No Package No Dependents
No Package No Dependents

About mcpproxy-go

smart-mcp-proxy/mcpproxy-go

Supercharge AI Agents, Safely

Implements a federated proxy that aggregates hundreds of MCP servers while intelligently compressing tool schemas through a `retrieve_tools` function, reducing token overhead by ~99% and bypassing client tool limits (Cursor's 40-tool cap, OpenAI's 128-function limit). Built in Go with native system-tray UIs across macOS, Windows, and Linux; supports both stdio and HTTP upstream protocols with optional HTTPS/mTLS, Docker isolation, and automatic tool poisoning quarantine that blocks untrusted servers pending manual approval.

About mcp-gopls

hloiseau/mcp-gopls

Model Context Protocol (MCP) server for Go using gopls – LSP-powered analysis, tests, coverage, and tooling.

Exposes LSP capabilities (go-to-definition, hover, completion, formatting, code actions) and Go tooling (test execution, coverage analysis, `go mod tidy`, `govulncheck`, module graph) via MCP tools and resources, enabling AI assistants to perform full-featured code navigation and refactoring. Built on the `mark3labs/mcp-go` library communicating with `gopls` over LSP, with progress streaming for long-running operations and structured logging. Includes curated MCP resources (`workspace/overview`, `workspace/go.mod`) and custom prompts for diagnostic summarization and refactor planning.

Scores updated daily from GitHub, PyPI, and npm data. How scores work