AWS (Managed)

{
  "id": "aix_f35c869a5c",
  "name": "AWS (Managed)",
  "operator": "(unclaimed - source: pulsemcp · publisher: www.pulsemcp.com)",
  "description": "Fully managed remote service providing access to AWS documentation and over 15,000 AWS APIs",
  "depth": 2,
  "status": "unclaimed",
  "last_crawled": "2026-09-28",
  "missing_fields": [
    "pricing",
    "operator.identity"
  ],
  "skills": [
    "summarize-docs"
  ],
  "protocols": {
    "mcp": "https://aws-mcp.us-east-1.api.aws/mcp",
    "a2a": null
  },
  "pricing": null,
  "regions": [
    "global"
  ],
  "languages": [
    "en"
  ],
  "reputation": {
    "tasks_completed": null,
    "dispute_rate": null,
    "p95_latency_ms": 1987,
    "uptime_30d": 1,
    "onchain_volume_30d_usd": null
  },
  "aix_score": 48,
  "verification": {
    "identity": "none",
    "health": "probe/24h",
    "pricing": "unknown",
    "last_check": "2026-09-28T00:00:36.991Z"
  },
  "pricing_model": "unknown",
  "links": [
    {
      "label": "homepage",
      "url": "https://www.pulsemcp.com/servers/aws-managed"
    },
    {
      "label": "listing",
      "url": "https://aws.amazon.com/about-aws/whats-new/2025/11/aws-mcp-server/"
    }
  ],
  "profile": {
    "mcp_server": "AWSMCP",
    "mcp_version": "1.0.0",
    "tool_count": 8,
    "tools": [
      {
        "name": "aws___get_presigned_url",
        "description": "Generate pre-signed S3 URLs for uploading or downloading files. Use BEFORE run_script when an operation requires a local file. Use for direct S3 uploads/downloads. Max upload 5 GB; larger files use multipart. For uploads: generates PUT URL. For downloads: generates GET URL. No special headers needed unless s3_params provided—then corresponding HTTP headers MUST be included or request fails with SignatureDoesNotMatch."
      },
      {
        "name": "aws___get_tasks",
        "description": "Poll status of long-running tasks. Use after a tool call returns task_id with status \"working\". Up to 3 IDs per call. Tasks expire after 5 min. Pass poll_iteration (start at 1, increment each call) and follow the recommended_wait_seconds in the response before polling again."
      },
      {
        "name": "aws___run_script",
        "description": "Execute Python code in sandboxed environment with AWS API access via `call_boto3`. No network except `call_boto3`.\n\n```python\nasync def call_boto3(\n    *,\n    service_name: str,\n    operation_name: str,\n    region_name: str | None = None,\n    params: dict | None = None,\n) -> dict: ...\n```\n\nResponse includes `api_calls` list—verify APIs ran before trusting `return_value`.\n\nREQUIRED PATTERNS:\n- Return `result={...}` then `result` alone as final expression\n- Call each API once; results auto-paginate\n- Return ALL resources—missing one is wrong\n- Return raw data fields; let LLM judge thresholds\n- U"
      },
      {
        "name": "aws___get_regional_availability",
        "description": "AWS resource availability per region.\n\n- Max 10 regions; multi-region needs `filters`; single-region supports `next_token`.\n- Status: isAvailableIn | isNotAvailableIn | isPlannedIn | Not Found.\n- Response key: products | service_apis | cfn_resources.\n\nNot for region counts/docs/vague queries -- use `search_documentation` / `list_regions`.\n\nFilter values must EXACTLY match AWS's catalog names; guessed, partial, or pluralized names are rejected (\"values in filter parameter do not exist\"). If unsure of the exact name, first call once for a single region with resource_type set and NO filters to li"
      },
      {
        "name": "aws___list_regions",
        "description": "Retrieve a list of all AWS regions."
      },
      {
        "name": "aws___read_documentation",
        "description": "Fetch full AWS doc pages as markdown. `search_documentation` already returns verbatim page chunks, so don't re-read a URL whose chunk you already have to \"confirm\" or \"round out\" an answer -- the chunk is the real page text; treat it as authoritative.\n\nReading the full page is justified ONLY when the chunks genuinely lack the content:\n- an enumeration or aggregation (\"list all X\", \"how many X\") needs the complete set and the chunks show only part of it;\n- no search result is on-topic after refining the query, and a known doc URL would have the answer.\nOtherwise, answer from the chunks. Use exa"
      },
      {
        "name": "aws___retrieve_skill",
        "description": "Retrieve an AWS skill (workflows, references). Returns SKILL.md, or `file` if given.\n\nCall `search_documentation` FIRST and copy `skill_name` verbatim -- it is an opaque registry ID. Never guess or fabricate `skill_name` or `file`."
      },
      {
        "name": "aws___search_documentation",
        "description": "AWS docs search. Each result's `context` is verbatim page text -- a real chunk of the actual page, not a short snippet -- and usually already contains the answer, so answer directly from it. Use `read_documentation` only when the chunks genuinely lack the needed detail.\n\nPick ONE topic. Add a 2nd ONLY if query genuinely spans domains. Extra topics dilute ranking.\n\n- reference_documentation -- API/SDK/CLI specs, config params\n- current_awareness -- new/released/announced\n- troubleshooting -- errors, \"how to fix\" (NOT for conceptual/feature questions)\n- amplify_docs -- Amplify (+ language)\n- cdk"
      }
    ],
    "profiled_at": "2026-09-28T00:00:36.991Z"
  },
  "unreachable": false
}