ViperJuice/mcp-gateway
MCP Server · tested 2026-09-22 · by the Hlido desk, not the vendor
In short: PMCP — a versioned, PyPI-packaged MCP gateway with strong release/CI discipline but near-zero adoption so far.
9 PASS · 1 FAIL of 10 public-surface claims
Quick answer
ViperJuice/mcp-gateway scores 82/100 (STEADY) on Hlido’s independent, hands-on test (reviewed 2026-09-22). STEADY (82), the repo-surface ceiling: MIT-licensed, PyPI-packaged, tagged releases (v1.19.3), five CI workflows, a 54K-char README, and daily commits. Pricing: Open source (free entry point documented).
PMCP (Progressive MCP) is an MCP gateway published to PyPI and cut into tagged releases up to v1.19.3, with five CI workflows and a large 54K-char README — the engineering hygiene here is notably strong for a long-tail project. The gap is adoption: at 15 stars it is effectively pre-traction, so while the packaging and release discipline are real, there is little external signal that it has been battle-tested. That makes it an interesting pick for a team that values a properly versioned, pip-installable gateway and is comfortable being an early adopter. As with every repo-surface review, the 82 reflects repository health — packaging, releases, CI, docs — not the gateway's measured runtime behavior.
Why STEADY
STEADY (82), the repo-surface ceiling: MIT-licensed, PyPI-packaged, tagged releases (v1.19.3), five CI workflows, a 54K-char README, and daily commits. Not VITAL because gateway runtime correctness needs hands-on testing, and adoption is still negligible (15 stars), so real-world hardening is unproven.
Public-surface checklist
- PASS Repo reachable (required) — GH API 200 for ViperJuice/mcp-gateway
- PASS Readme present (required) — README length 54762
- PASS License present (required) — MIT
- PASS Install documented (required) — install/usage section found in README
- PASS Active 12mo (required) — last push 1d ago
- PASS Releases present — latest v1.19.3
- FAIL Community traction — 15 stars
- PASS Ci or tests — 5 workflow file(s)
- PASS Recent commit 90d — last push 1d ago
- PASS Agent consumable — MCP server markers in README
What we saw
1 screenshot captured by the Hlido engine during the reviewed run (run-820cd0d67341faec-github-com). Our own captures — not vendor marketing material.
What it does well
- Proper release discipline — tagged releases up to v1.19.3
- Published to PyPI (pip-installable) as `pmcp`
- Five CI workflows — the strongest automated gating in this batch
- Very thorough README (54K chars)
- MIT-licensed and actively committed (daily at review time)
What it fails at
- Near-zero adoption (15 stars) — essentially pre-traction
- No external evidence of production hardening
- Runtime gateway behavior was not hands-on tested
Best for
- Early adopters who want a versioned, pip-installable MCP gateway
- Teams that value release/CI discipline over headcount of stars
- Python-first stacks integrating MCP routing
Not recommended for
- Risk-averse buyers who need a widely-adopted, proven gateway
- Anyone who treats star count / community size as a hard requirement
Pricing & access
- ModelOpen source
- Free entry pointYes — a free tier or open-source edition is documented
Derived from Hlido-held evidence only (engine checklist + editorial text); quotes are verbatim from the scorecard; not vendor-supplied; re-derived daily. Verify current prices on the vendor's pricing page. Last verified 2026-07-16.
Compared to
-
VeriTeknik/pluggedin-mcp-proxy
release-discipline
mcp-gateway (PMCP) wins on packaging and release discipline (PyPI + tagged releases + 5 CI workflows); pluggedin-mcp-proxy wins on adoption (132 vs 15 stars) and hub features. Choose based on whether release hygiene or community traction matters more to you.
Agent relevance
CLI MCP
Agentic-Commerce Readiness 63/100 · INTEGRABLE
Independent readiness for agent delegation & transaction. How it’s scored · check live
An MCP gateway distributed as a PyPI package (`pmcp`); agents connect through it as an MCP endpoint. Pip-installable and MCP-native, so directly agent-consumable.
Agent-friendly score: 7/10
Score over time
The longitudinal record — every point is the score as published on that date. Raw series.
