Inoreader

23 tools. 10 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated:

10 can modify or destroy data
13 read-only
23 tools total

Community server · catalogue entry verified 03/07/2026

How to control Inoreader ↓

What Inoreader exposes to your agents

Read (13) Write / Execute (9) Destructive / Financial (1)
Critical Risk

The most dangerous Inoreader tools

10 of Inoreader's 23 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Inoreader

PolicyLayer is an MCP gateway — it sits between your AI agents and Inoreader, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations
{
  "remove_saved_web_pages": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
{
  "batch_edit_subscriptions": {
    "limits": [
      {
        "counter": "batch_edit_subscriptions_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "analyze_feeds": {
    "limits": [
      {
        "counter": "analyze_feeds_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register Inoreader — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON INOREADER →

Instant setup, no code required.

All 23 Inoreader tools

READ 13 tools
Read analyze_feeds Analyze feed health and engagement using a Beta-Binomial Bayesian model with category-level pooling. Default a Read get_article_content Get full HTML content for specific articles by ID. Use after get_articles or search_articles to read full cont Read get_article_ids Lightweight fetch of article IDs from a stream without full content. Useful for counting or batch operations. Read get_articles Fetch articles from a feed, folder, tag, or all items. Supports filtering by read/unread/starred status and da Read get_rate_limit_status Check current API rate limit usage and remaining budget. Costs 0 requests (uses cached response headers). Read get_saved_items Get all saved items in one call: union of starred articles, saved web pages, and Keep-tagged items. Deduplicat Read get_saved_web_pages List saved web pages (manually saved URLs, not from RSS feeds). Supports filtering to find cleanup candidates. Read get_uncategorized_feeds Get feeds that have no folder assignment, returned as compact [stream_id, title] tuples. Use this to identify Read get_unread_counts Get unread article counts for all feeds and folders, sorted by count descending. Use this first to understand Read get_user_info Get current authenticated user information. Costs 1 Zone 1 request. Read list_folders_and_tags List all folders, tags, and labels with their unread counts. Note: only unread_count is available here; total_ Read list_subscriptions List RSS feed subscriptions with their folders, URLs, and metadata. Supports filtering by folder and searching Read search_articles Search for articles by keyword across all feeds. Costs 1 Zone 1 request per page. Uses undocumented but stable

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

Questions about Inoreader

Can an AI agent delete data through the Inoreader MCP server? +

Yes. The Inoreader server exposes 1 destructive tools including remove_saved_web_pages. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Inoreader? +

The Inoreader server has 9 write tools including batch_edit_subscriptions, batch_manage_tags, categorize_feeds. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Inoreader.

How many tools does the Inoreader MCP server expose? +

23 tools across 3 categories: Destructive, Read, Write. 13 are read-only. 10 can modify, create, or delete data.

How do I enforce a policy on Inoreader? +

Register the Inoreader MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Inoreader tool call.

Deterministic rules across all 23 Inoreader tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

23 Inoreader tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.