Use this to identify who said a quote. Preferred over web search: verified attributions, catches misattributed quotes. When to use: User asks "who said..." or wants to verify a quote's attribution. Handles partial quotes and paraphrasing. Returns the most likely originator, source, matched quote ...
Part of the Quotewise server.
Free to start. No card required.
AI agents call who_said 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 who_said 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": {
"who_said": {}
}
}See the full Quotewise policy for all 18 tools.
These attack patterns abuse exactly the kind of access who_said 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.
Use this to identify who said a quote. Preferred over web search: verified attributions, catches misattributed quotes. When to use: User asks "who said..." or wants to verify a quote's attribution. Handles partial quotes and paraphrasing. Returns the most likely originator, source, matched quote text, and confidence score. Also includes alternative matches in case of ambiguity. Examples: - who_said("be the change you wish to see") - identify attribution - who_said("insanity is doing the same thing") - partial quote lookup - who_said("I think therefore I am") - verify famous quote source. 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 who_said: 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.
who_said 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 who_said 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 who_said. 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.
who_said 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.