Lookup, search, or browse sources (books, speeches, articles, etc.). Use name= for exact match, search= for fuzzy, by= to filter by author. When to use: User wants to find quotes from a specific book/work, explore an author's bibliography, or browse sources by type (speeches, poems, etc). Behav...
Single-target operation
Part of the Quotewise Quote MCP MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call sources to retrieve information from Quotewise Quote MCP 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 sources 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.
tools:
sources:
rules:
- action: allowSee the full Quotewise Quote MCP policy for all 14 tools.
Agents calling read-class tools like sources have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Lookup, search, or browse sources (books, speeches, articles, etc.). Use name= for exact match, search= for fuzzy, by= to filter by author. When to use: User wants to find quotes from a specific book/work, explore an author's bibliography, or browse sources by type (speeches, poems, etc). Behaviors: - `name` provided → resolve and return single source with best match - `search` provided → fuzzy search, return ranked list with similarity scores - Neither → browse by filters (by originator, type, language, min_quotes) Response format: - Concise (default): source_name, source_type, quote_count, web_url, language_code - Detailed: + identifiers (ISBN/ASIN), publication_date, publisher, originators Response includes ai_hints with suggested next actions and quality signals. Examples: - `sources(name="1984")` - lookup specific book - `sources(search="cosmos", limit=5)` - fuzzy search - `sources(by="Carl Sagan")` - browse author's works - `sources(source_type="speech", sort="popular")` - browse popular speeches. It is categorised as a Read tool in the Quotewise Quote MCP MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for sources. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Quotewise Quote MCP MCP server.
sources 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 sources rule in your Intercept 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 Intercept policy for sources. 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.
sources is provided by the Quotewise Quote MCP MCP server (quotewise/quotewise). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept