Search AWS documentation using the official AWS Documentation Search API. ## Usage This tool searches across all AWS documentation for pages matching your search phrase. Use it to find relevant documentation when you don't have a specific URL. ## Search Tips - Use specific technical terms rat...
Single-target operation
Part of the AWS Documentation MCP Server MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call search_documentation to retrieve information from AWS Documentation MCP Server 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 search_documentation 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:
search_documentation:
rules:
- action: allowSee the full AWS Documentation MCP Server policy for all 5 tools.
Agents calling read-class tools like search_documentation 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.
Search AWS documentation using the official AWS Documentation Search API. ## Usage This tool searches across all AWS documentation for pages matching your search phrase. Use it to find relevant documentation when you don't have a specific URL. ## Search Tips - Use specific technical terms rather than general phrases - Include service names to narrow results (e.g., "S3 bucket versioning" instead of just "versioning") - Use quotes for exact phrase matching (e.g., "AWS Lambda function URLs") - Include abbreviations and alternative terms to improve results - Use guide_type and product_type filters found from a SearchResponse's "facets" property: - Filter only for broad search queries with patterns: - "What is [service]?" -> product_types: ["Amazon Simple Storage Service"] - "How to use <service 1> with <service 2>?" -> product_types: [<service 1>, <service 2>] - "[service] getting started" -> product_types: [<service>] + guide_types: ["User Guide, "Developer Guide"] - "API reference for [service]" -> product_types: [<service>] + guide_types: ["API Reference"] ## Result Interpretation Each SearchResponse includes: - search_results: List of documentation pages, each with: - rank_order: The relevance ranking (lower is more relevant) - url: The documentation page URL - title: The page title - context: A brief excerpt or summary (if available) - sections: Table of contents (when available) - these section titles can be used with the read_sections tool for targeted content extraction - facets: Available filters (product_types, guide_types) for refining searches - query_id: Unique identifier for this search session Args: ctx: MCP context for logging and error handling search_phrase: Search phrase to use search_intent: The intent behind the search requested by the user limit: Maximum number of results to return product_types: Filter by AWS product/service guide_types: Filter by guide type Returns: List of search results with URLs, titles, query ID, context snippets, and facets for filtering. It is categorised as a Read tool in the AWS Documentation MCP Server MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for search_documentation. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the AWS Documentation MCP Server MCP server.
search_documentation 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 search_documentation 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 search_documentation. 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.
search_documentation is provided by the AWS Documentation MCP Server MCP server (awslabs.aws-documentation-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.