Lookup, search, or browse originators. Handles people, proverbs, anonymous sources, and institutions. Use name= for exact match, search= for fuzzy, neither for browsing. When to use: User asks about a person/author, wants to find who said something, or needs to browse by category (poets, philosop...
Risk signalsHigh parameter count (16 properties) · Bulk/mass operation — affects multiple targets
Part of the Quotewise server.
Free to start. No card required.
AI agents call originators to retrieve information from Quotewise 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 originators 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": {
"originators": {}
}
}See the full Quotewise policy for all 18 tools.
These attack patterns abuse exactly the kind of access originators 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.
Lookup, search, or browse originators. Handles people, proverbs, anonymous sources, and institutions. Use name= for exact match, search= for fuzzy, neither for browsing. When to use: User asks about a person/author, wants to find who said something, or needs to browse by category (poets, philosophers, etc). Behaviors: - name provided → resolve and return single originator details - search provided → fuzzy search, return ranked list (optionally filtered by category tags) - Neither → browse by filters (popular, language, min_quotes, category tags, etc.) Category tags filter by originator type (e.g., ["Poets", "Politicians", "Catholic Bishops"]) - works with all modes. Gender filter accepts natural language (e.g., "female", "women", "queer", "trans") - resolved to Wikidata Q-IDs internally. Response format: - Concise (default): slug, full_name, sort_name, quote_count, descriptions_i18n, web_url - Detailed: + biography (500 char excerpt), confidence_tier, similarity_score Response includes ai_hints with suggested next actions and quality signals for agent workflows. Date filters (born_on, died_on, born_year_gte, born_year_lte, died_year_gte, died_year_lte) combine with every other filter via AND. Negative year bounds represent BCE; year 0 is rejected. Examples: - originators(name="Einstein") - exact lookup - originators(search="Shake") - fuzzy search for "Shakespeare" - originators(tags=["Poets"], gender="female") - browse female poets - originators(sort="popular", limit=10) - top 10 by quote count - originators(born_on="04-20") - originators born April 20 (any year) - originators(born_year_gte=-500, born_year_lte=-300) - originators born between 500 BCE and 300 BCE inclusive. It is categorised as a Read tool in the Quotewise MCP Server, which means it retrieves data without modifying state.
Register the Quotewise MCP server in PolicyLayer and add a rule for originators: 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 Quotewise. Nothing to install.
originators 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 originators 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 originators. 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.
originators is provided by the Quotewise MCP server (https://mcp.quotewise.io/). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 18 Quotewise 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.