Item detail
github.com

tsouth89/toolport

tsouth89/toolport is a local mcp gateway (lazy discover that RepoRadar is tracking in its MCP Servers section, currently rated Gold tier with a 'try now' verdict. Its strongest signal is workflow potential, scored 9.7 out of 10.

Score8.2
Popularity1.0
Risklow
TierGold
Score breakdown
Usefulness9.0
Novelty9.0
Momentum7.0
Maturity6.5
Open-source/build8.4
Evidence7.2
Workflow potential9.7
Setup ease8.8

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for any developer or team running more than one MCP server who wants one place to configure, authenticate, and monitor them, and any agent user who has watched their context window get eaten alive by tool definitions (a real problem at 3 servers × ~24,000 tokens of definitions before the agent has even asked anything — and the new official guidance on tool-budgeting is converging on the sam

Who should use it

Any developer or team running more than one MCP server who wants one place to configure, authenticate, monitor, and pin them — instead of re-running the same OAuth dance inside Claude, Cursor, Codex, Claude Desktop, Windsurf, and ChatGPT separately for each serverAny agent user who has watched their context window get eaten alive by tool definitions (a real problem at 3+ MCP servers, ~24,000 tokens of definitions per request before the agent has even asked anything) — Toolport's 3-meta-tool surface cuts that to ~660 tokens regardless of how many underlying servers you connectAnyone running 5+ MCP servers who wants to keep adding servers without the per-server cost compounding — the lazy-discovery surface holds the per-request token bill flat whether you connect 1 server or 50Anyone who needs supply-chain hardening on their MCP tool surface — per-server tool integrity + quarantine flags a tool whose hash or schema changed since you pinned it, before any client can invoke it (rug-pull / tool-poisoning detection)Anyone who wants MCP credentials in the OS keychain (Keychain / Credential Manager / Secret Service) instead of a dotfile or env var — and the env override for CI / Docker / server use is preservedAnyone who wants a real native macOS desktop app (not a webview wrapper) to monitor which MCP servers are connected, how many tools each exposes, and which clients are wired in — with one-click client wiringHeadless / CI / Docker deployments that need the same gateway without the GUI — the CLI gives you the same register-once-share-everywhere model from a script

Who should skip it

Consider tsouth89/toolport lower priority if you already have a working solution in this category.

About this signal

tsouth89/toolport is tracked by RepoRadar as a local mcp gateway (lazy discover in the MCP Servers section. It was first seen on 2026-07-04 and last updated on 2026-07-04. The current verdict is 'try now' with a Gold tier and easy setup difficulty. The standout signals for tsouth89/toolport are workflow potential (9.7) and practical usefulness (9.0), while maturity (6.5) trails — that balance shapes where it fits best. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.

How this item is evaluated

RepoRadar assigned tsouth89/toolport a composite score of 8.2 out of 10, placing it in the Gold tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 1.0 and never affects the composite score or tier. The risk label of 'low' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.

Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.

Risk explanation

Risk label is still being reviewed from the captured evidence. Treat the item as unknown-risk until you review the linked source, permissions, setup path, and data access.

Evidence links
Closest alternatives / related signals
mcpmcp-gatewaylazy-discoverytoken-savingstool-integrityrug-pull-detectionkeychainsecrets