Fetch the full, untruncated definition from DDO (Den Danske Ordbog) for a synset. This tool addresses the issue that DanNet synset definitions (:skos/definition) may be capped at a certain length. It retrieves the complete definition from the authoritative DDO source by following sense source URL...
Part of the Dannet server.
Free to start. No card required.
AI agents call fetch_ddo_definition to retrieve information from Dannet without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though fetch_ddo_definition only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"fetch_ddo_definition": {}
}
}See the full Dannet policy for all 16 tools.
These attack patterns abuse exactly the kind of access fetch_ddo_definition gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Fetch the full, untruncated definition from DDO (Den Danske Ordbog) for a synset. This tool addresses the issue that DanNet synset definitions (:skos/definition) may be capped at a certain length. It retrieves the complete definition from the authoritative DDO source by following sense source URLs. WORKFLOW: 1. Get synset information to find associated senses 2. Extract DDO source URLs from sense data (dns:source) 3. Fetch DDO HTML pages and parse for definitions 4. Find elements with class "definitionBox selected" and extract span.definition content IMPORTANT NOTES: - Looks for CSS classes "definitionBox selected" and child span.definition - DDO and DanNet have diverged over time, so source URLs may not always work - This implementation uses httpx for web requests and regex-based HTML parsing Args: synset_id: Synset identifier (e.g., "synset-1876" or just "1876") Returns: Dict containing: - synset_id: The queried synset ID - ddo_definitions: List of definitions found from DDO pages - source_urls: List of DDO URLs that were attempted - success_urls: List of URLs that successfully returned definitions - errors: List of any errors encountered - truncated_definition: The original DanNet definition for comparison Example: result = fetch_ddo_definition("synset-3047") # Check result['ddo_definitions'] for full DDO definitions # Compare with result['truncated_definition'] from DanNet. It is categorised as a Read tool in the Dannet MCP Server, which means it retrieves data without modifying state.
Register the Dannet MCP server in PolicyLayer and add a rule for fetch_ddo_definition: 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 Dannet. Nothing to install.
fetch_ddo_definition is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the fetch_ddo_definition 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.
Set action: deny in the PolicyLayer policy for fetch_ddo_definition. 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.
fetch_ddo_definition is provided by the Dannet MCP server (https://wordnet.dk/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 16 Dannet tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.