get_by_tag

THE RISK

Low Risk

Why get_by_tag needs a policy

This tool retrieves and queries markdown content by tag from a local knowledge base. It produces no side effects—no data is created, modified, deleted, or executed. It is a straightforward read operation with negligible risk of misuse.

From the tool's definition Tool name 'get_by_tag' and description 'Get blog content by its tag' indicate retrieval of existing content with no modification. Arguments are 'tag' (filter) and 'limit' (pagination), both read-only parameters.

Documented attack patterns abuse exactly the kind of access get_by_tag gives an agent:

POLICY

How to control get_by_tag

PolicyLayer is an MCP gateway — it sits between your AI agents and Library MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for get_by_tag:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_by_tag": {}
  }
}

get_by_tag is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register Library MCP — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Library MCP tools

Execute rebuild Rebuild text index. Useful for when contents have changed on disk Read get_by_date_range Get posts published within a date range. Args: start_date: the start date Read get_by_slug_or_url Get a post by its slug or URL. Args: identifier: the slug, URL, or path f Read get_by_text Get blog content by text in content. Args: query: text for an exact match Read list_all_tags List all tags sorted by number of posts and most recent post. Read search_tags Search for tags matching the provided query. Args: tag_query: partial or

All 7 Library MCP tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about get_by_tag

What does the get_by_tag tool do? +

Get blog content by its tag. Args: tag: the tag associated with content limit: the number of results to include. It is categorised as a Read tool in the Library MCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_by_tag? +

Register the Library MCP server in PolicyLayer and add a rule for get_by_tag: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Library MCP. Nothing to install.

What risk level is get_by_tag? +

get_by_tag is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_by_tag? +

Yes. Add a rate_limit block to the get_by_tag rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block get_by_tag completely? +

Set action: deny in the PolicyLayer policy for get_by_tag. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides get_by_tag? +

get_by_tag is provided by the Library MCP server (lethain/library-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Library MCP tool call.

Start from Library MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →