What did Hlido score 1MCP Agent?

1MCP Agent scored 74/100 (STEADY) in Hlido's independent, hands-on review.

Does any vendor pay Hlido for placement?

No. Hlido takes no money from the agents it rates — scoring weights stay private and the evidence behind every verdict is public.

1MCP Agent

Name: 1MCP Agent review
Item: 1MCP Agent
Rating: 74
Author: Hlido Editor

Infrastructure · tested 2026-08-05 · re-test due 2026-11-05 · by the Hlido desk, not the vendor

In short: A well-argued fix for MCP context sprawl — progressive tool discovery so agents stop carrying the whole tool catalogue in context. Still beta, and honest about it.

4 PASS · 1 FAIL of 5 public-surface claims

Visit 1MCP Agent → scorecard.json

Quick answer

1MCP Agent scores 74/100 (STEADY) on Hlido’s independent, hands-on test (reviewed 2026-08-05). STEADY (74) for a real, well-diagnosed problem (MCP config and context sprawl), a genuine architectural answer (progressive discovery: instructions → inspect → run), and documentation good enough to get a working setup i

Hlido Editor · 2026-08-05

1MCP Agent aggregates MCP servers behind a single runtime (`1mcp serve`) and then does the more interesting thing: instead of injecting every tool schema into an agent's context, it offers a CLI mode where the agent starts with `instructions`, narrows with `inspect`, and only runs the tool it actually needs. The problem statement is stated crisply and is real — configuration sprawl across clients, and context sprawl inside long-running agent loops — and progressive discovery is a genuine architectural answer rather than a repackaging. The documentation is the strong point: a five-minute setup path with copy-pasteable commands, explicit guidance on which path to choose (CLI mode, proxy, or direct streamable HTTP) and why, and per-client setup for Codex, Claude and Cursor. Presets, filters, template-backed servers, and async/lazy loading round it out. The main caution is maturity: the captured version is v0.35.0-beta.3, a pre-1.0 beta, and the surface offers no adoption numbers, named users, or third-party validation. Nothing here is overclaimed — the docs are careful about what each path is for — but a runtime that sits between every agent and every tool is exactly the component where beta status matters.

Why STEADY

STEADY (74) for a real, well-diagnosed problem (MCP config and context sprawl), a genuine architectural answer (progressive discovery: instructions → inspect → run), and documentation good enough to get a working setup in five minutes with explicit path guidance. Held well below VITAL because the captured release is v0.35.0-beta.3 — pre-1.0 — with no adoption evidence or third-party validation, and this is precisely the kind of always-in-the-path component where beta maturity carries weight.

Public-surface checklist

PASS Homepage loads (required)
PASS Primary value prop (required) — 'One runtime for MCP, one thinner workflow for agents'
PASS Cta present (required) — '5-Minute Setup' with npm install -g @1mcp/agent
PASS Pricing or access — Open npm package; no pricing surface (appears free/open)
FAIL Evidence or demo — Documentation and command examples only — no benchmarks or adoption evidence

What we saw

4 screenshots captured by the Hlido engine during the reviewed run (run-c0812a1fdddd54b1-docs-1mcp-app). Our own captures — not vendor marketing material.

1MCP Agent — run screenshot 1 (home.png) — home.png

1MCP Agent — run screenshot 2 (page__VPContent.png) — page__VPContent.png

1MCP Agent — run screenshot 3 (page_.png) — page_.png

1MCP Agent — run screenshot 4 (page_guide_getting-started.png) — page_guide_getting-started.png

What it does well

Diagnoses two distinct real problems — client configuration sprawl and agent context sprawl — and addresses both
Progressive discovery (instructions → inspect → run) genuinely reduces what an agent must hold in context
Documentation gives an explicit five-minute path with runnable commands and per-client setup (Codex, Claude, Cursor)
Clear guidance on choosing between CLI mode, proxy, and direct streamable HTTP, with the trade-off stated for each
Presets and filters let server sets be reused across projects and clients without duplicating config
Async and lazy loading — starts faster and exposes less until something actually needs it

What it fails at

Captured release is v0.35.0-beta.3 — pre-1.0 beta, in a component that sits in the path of every tool call
No adoption numbers, named users, or third-party validation on the public surface
No stated reliability, performance, or overhead figures for the aggregation layer
Adds an operational dependency: if the runtime is down, every aggregated server is unreachable
Not tested hands-on — the context-reduction claim is the one that most needs measuring

Best for

Developers running several MCP servers across multiple AI clients who are tired of duplicating configuration
Long-running agent loops where injected tool schemas are consuming meaningful context
Teams wanting one place to manage server sets, presets and filters

Not recommended for

Production deployments that require a stable 1.0 with a support commitment
Setups with a single MCP server, where the aggregation layer adds cost and no benefit
Anyone who cannot accept a new single point of failure between agents and tools

Pricing & access

Pricing findable on the public surfacePASS Open npm package; no pricing surface (appears free/open) (tested 2026-08-04)

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 2026-08-04.

Related agents

Agent relevance

API CLI MCP Behavioral-testable

Agentic-Commerce Readiness 76/100 · COMMERCE-READY

Independent readiness for agent delegation & transaction. How it’s scored · check live

Built entirely for agent consumption: `1mcp serve` is the runtime, CLI mode is the agent-facing workflow, and proxy plus direct streamable HTTP cover MCP-native clients. Agents are the only intended user.

Agent-friendly score: 9/10

Evidence

Unified MCP runtime via `1mcp serve` aggregating static and template-backed servers — source (2026-08-05) verified
Progressive CLI discovery: instructions → inspect → run — source (2026-08-05) verified
Published as @1mcp/agent on npm with a five-minute setup path — source (2026-08-05) verified
Captured version v0.35.0-beta.3 — pre-1.0 — source (2026-08-05) verified
Adoption, reliability or overhead figures — source (2026-08-05)

scorecard.json · transparency passport · registry · methodology

More: compare agents · best of · developer tools · incident registry

Verdict by Hlido Editor, our automated editorial system · Method: public-surface-tier-1+editorial-narrative-v2 · Methodology version 2026.05 · Next review due 2026-11-05

How this page was produced. The scores, claim verdicts and evidence come from automated hands-on testing of the product’s public surface. The written analysis is drafted by an AI system, and pages publish without a person reviewing each one. Hlido publishes this record and answers for it — tell us if anything here is wrong and we will correct it.

Embed this trust badge

Live, always-current independent score — free to embed on your site or README. No vendor pays for placement.

Markdown

[![Hlido trust score](https://hlido.eu/badge/1mcp-app-agent.svg)](https://hlido.eu/check/?agent=1mcp-app-agent)

HTML

<a href="https://hlido.eu/check/?agent=1mcp-app-agent"><img src="https://hlido.eu/badge/1mcp-app-agent.svg" alt="Hlido trust score"></a>