{
  "schema_version": "2.0",
  "slug": "augmnt-augments-mcp-server",
  "name": "Augments",
  "agent_url": "https://augments.dev",
  "category": "Coding",
  "run_id": "run-r-publish-v2-augmnt-augments-mcp-server-2026-08-26",
  "run_at": "2026-08-26T09:00:00Z",
  "editor": "Hlido Editor",
  "editorial_method": "public-surface-tier-1+editorial-narrative-v2",
  "methodology_version": "2026.05",
  "methodology_url": "/methodology/public-surface-tier-1/",
  "score": 73,
  "tier": "STEADY",
  "laddoo_score": 73,
  "confidence": "medium",
  "hlido_opinion": {
    "headline": "A focused MCP server that hands Claude Code real type signatures, prose docs and working examples for any npm package — not a curated list — so the model stops guessing from stale training data.",
    "body": "Augments does one thing and states it plainly: it is an MCP server that gives Claude Code types, docs and examples pulled from npm for any package, not a hand-curated subset. The value proposition is sharp and real — coding agents routinely hallucinate APIs or lean on outdated training data, and a tool that injects current type signatures and working examples at the moment of use directly attacks that failure mode (the site frames it as a clean 'before: guesses / after: type signatures, prose docs, working examples'). Setup is a single line (`claude mcp add -s user augments -- npx -y @augmnt-sh/augments-mcp-server`), which is exactly the low-friction path an agent user wants. The reasons it sits mid-STEADY rather than higher: the reviewed public surface is a single landing page, so there is little evidence of depth — how many registries beyond npm, how it handles private packages, version pinning, or rate limits — and there is no visible license, adoption signal, or independent benchmark on the captured surface. It is a promising, well-scoped utility whose ceiling here is set by how little the public page lets us verify.",
    "voice": "Hlido Editor",
    "as_of": "2026-08-26",
    "editor_signature_pending": true
  },
  "tier_rationale": "STEADY (73) because Augments targets a real, specific agent failure mode (guessing npm APIs) with a genuinely agent-native, one-line MCP install and an 'any package, not a curated list' scope. Held at the lower end of STEADY because the public surface is a single page with limited evidence of depth, no visible license or adoption signal, and unverified handling of private packages, versioning and rate limits.",
  "what_it_does_well": [
    "Precisely scoped: current type signatures, prose docs and working examples for any npm package, injected over MCP",
    "Directly attacks a real agent failure — hallucinated or outdated API usage from stale training data",
    "One-line install into Claude Code (`claude mcp add -s user augments ...`)",
    "'Any package, not just a curated list' — no gatekept allowlist"
  ],
  "what_it_fails_at": [
    "Reviewed surface is a single landing page — little evidence of depth or edge-case handling",
    "No visible license, GitHub star count, or independent adoption signal on the captured surface",
    "Unclear handling of private packages, version pinning, monorepos and rate limits",
    "Scope is npm-only on the evidence seen — no other registries or languages demonstrated"
  ],
  "best_for": [
    "Claude Code users who want accurate, current npm type signatures and examples at generation time",
    "JavaScript/TypeScript teams whose agents frequently misuse library APIs"
  ],
  "not_recommended_for": [
    "Teams needing multi-language/multi-registry documentation coverage beyond npm",
    "Users who require a documented license, SLA, or proven handling of private-package auth"
  ],
  "red_flags": [],
  "compared_to": [
    {
      "slug": "oraios-serena",
      "verdict_diff": "Serena gives an agent structural/symbol context about your own codebase; Augments injects external npm package docs and type signatures. Complementary rather than competing — Serena for your code, Augments for the libraries it depends on.",
      "preferred_for_axis": "external-library-docs-vs-own-code-structure"
    },
    {
      "slug": "continue-dev",
      "verdict_diff": "Continue is a full open-source AI coding-assistant framework; Augments is a single-purpose MCP server feeding npm docs into an existing assistant. Continue for the whole assistant, Augments as a targeted context plug-in.",
      "preferred_for_axis": "single-purpose-context-vs-full-assistant"
    }
  ],
  "evidence_urls": [
    {
      "claim": "MCP server that gives Claude Code types, docs and examples from npm for any package",
      "source": "https://augments.dev ('An MCP server that gives Claude Code types, docs, and examples from npm. Any package. Not just a curated list.')",
      "tested_at": "2026-08-26",
      "verified": true
    },
    {
      "claim": "One-line install via claude mcp add",
      "source": "https://augments.dev ('claude mcp add -s user augments -- npx -y @augmnt-sh/augments-mcp-server')",
      "tested_at": "2026-08-26",
      "verified": true
    },
    {
      "claim": "Positioned to replace guesses/stale training data with real type signatures and working examples",
      "source": "https://augments.dev ('BEFORE Claude guesses or uses outdated training data / AFTER Claude gets type signatures, prose docs, and working examples')",
      "tested_at": "2026-08-26",
      "verified": true
    }
  ],
  "agent_relevance": {
    "has_api": false,
    "has_cli": false,
    "has_mcp": true,
    "has_webhook": false,
    "has_sdk": false,
    "behavioral_testable": true,
    "agent_integration_path": "Installed as an MCP server into Claude Code with a single `claude mcp add` command; the agent then calls it to fetch current type signatures, docs and examples for any npm package at generation time, reducing hallucinated or outdated library usage. Single-purpose and low-friction, intended to sit alongside a coding agent rather than replace it.",
    "agent_friendly_score": 8
  },
  "checklist": [
    {
      "id": "homepage_loads",
      "pass": true,
      "required": true,
      "tested_at": "2026-08-26T09:00:00Z"
    },
    {
      "id": "primary_value_prop",
      "pass": true,
      "required": true,
      "evidence": "Types, docs and examples from npm for any package, over MCP",
      "tested_at": "2026-08-26T09:00:00Z"
    },
    {
      "id": "cta_present",
      "pass": true,
      "required": true,
      "evidence": "claude mcp add one-line install command",
      "tested_at": "2026-08-26T09:00:00Z"
    },
    {
      "id": "pricing_or_access",
      "pass": false,
      "required": false,
      "evidence": "No pricing or license surfaced on the captured page",
      "tested_at": "2026-08-26T09:00:00Z"
    },
    {
      "id": "evidence_or_demo",
      "pass": true,
      "required": false,
      "evidence": "Before/after framing and install command; no live demo captured",
      "tested_at": "2026-08-26T09:00:00Z"
    }
  ],
  "summary": "A focused MCP server that hands Claude Code real type signatures, prose docs and working examples for any npm package — not a curated list — so the model stops guessing from stale training data.",
  "_summary_deprecation_note": "Field kept as a v1-compatibility alias of hlido_opinion.headline. New consumers should read hlido_opinion.{headline,body,voice,as_of}.",
  "staleness_after": "2026-11-24",
  "review_age_days_at_publish": 0,
  "next_review_due_at": "2026-11-24",
  "attestation_url": "/data/attestations/augmnt-augments-mcp-server.json",
  "signature_pending": true,
  "source": "r-publish-editorial-v2",
  "marking_signal": {
    "checked_at": "2026-08-26",
    "source": "r-publish-editorial-enrich",
    "not_applicable": true,
    "note": "Augments serves package documentation and type signatures to a coding agent, not synthetic media for publication. Article-50 marking obligations do not apply. Recorded as not applicable."
  },
  "evidence_images": {
    "run_id": "run-38a81c131ae220b6-augments-dev",
    "base": "https://images.hlido.eu/reviews/augmnt-augments-mcp-server/run-38a81c131ae220b6-augments-dev",
    "files": [
      "home.png"
    ],
    "urls": [
      "https://images.hlido.eu/reviews/augmnt-augments-mcp-server/run-38a81c131ae220b6-augments-dev/home.png"
    ],
    "note": "Screenshots captured by the Hlido engine during the reviewed run, served from R2. `run_id` is the ENGINE run id — it differs from `scorecard.run_id` and is the only one these keys resolve under."
  },
  "pricing_facts": {
    "schema": "pricing-facts/1",
    "pricing_disclosed": {
      "pass": false,
      "evidence": "No pricing or license surfaced on the captured page",
      "tested_at": "2026-08-26"
    },
    "last_verified": "2026-08-26",
    "basis": "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.",
    "derived_at": "2026-08-27"
  }
}