Overview
What SearchPulse does
SearchPulse takes a natural-language question and returns a structured, cited answer that an AI agent or research pipeline can use directly.
- GET /v1/search?q=What+is+AWS+Lambda%3F returns the answer, the citations (title, URL and the span of the answer each one supports), the search queries that were run and the token counts.
- mode=standard (default) writes up to 800 output tokens from 1 web search; mode=deep writes up to 1,200 output tokens from up to 2 web searches.
- Questions can be up to 500 characters. A search that does not finish within 25 seconds answers 504 and is not billed.
Where the data comes from
Answers are written by a generative AI model on Amazon Bedrock from Amazon Bedrock Web Search results (Amazon's web index), fetched live for every call, not from a static index. Every source used is returned in citations with its URL and title; show the citation links with any answer you display. Only query metadata (token and citation counts) is kept, for 30 days; the question text is not stored. If the search service is unavailable the API answers 502 and the call is not billed.
Three ways to connect
- REST with an X-API-Key header, described by an OpenAPI 3 schema (https://searchpulse.waltsoft.net/openapi.json ).
- MCP: the tool searchpulse___search (q, mode, api_key) on the Amazon Bedrock AgentCore Gateway, for Claude, Strands Agents and other MCP clients.
- A2A (Agent2Agent 0.3): the agent card at https://searchpulse.waltsoft.net/.well-known/agent-card.json with the skill search.
Who it is for
AI agents that must answer factual questions from current web content, research pipelines that need cited answers, and workflows that query the web without running a browser or scraper.
Billing
On AWS Marketplace every successful call is one unit at $0.30; a deep call (mode=deep) uses 2 units ($0.60). Errors (400, 401, 429, 5xx) are never billed. With x402 (USDC on Base or Solana, no account) a standard call is $0.25 and a deep call $0.40. Rate limit: 50 requests per second (bursts up to 100) and 30 requests per minute per client IP.
Highlights
- Cited web answers in one call: SearchPulse runs live Amazon Bedrock Web Search and returns a written answer with the source URL and title of every citation and the search queries it ran
- Two modes with fixed limits: standard writes up to 800 tokens from 1 web search (one $0.30 unit), deep up to 1,200 tokens from up to 2 searches (2 units); errors and timeouts are not billed
- Agent-ready: REST with an OpenAPI 3 schema, the MCP tool searchpulse___search on Amazon Bedrock AgentCore Gateway and an A2A agent card with the skill search
Details
Features and programs
Financing for AWS Marketplace purchases
Quick Launch
Pricing
Dimension | Description | Cost/unit |
|---|---|---|
API Call | One unit per standard search; a deep search (mode=deep) uses 2 units | $0.30 |
Vendor refund policy
No refunds. Contact support@waltsoft.net for billing questions.
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
- Amazon Bedrock AgentCore
API-Based Agents & Tools
API-Based Agents and Tools integrate through standard web protocols. Your applications can make API calls to access agent capabilities and receive responses.
Additional details
Usage instructions
To get started using the remote MCP server, follow the instructions below:
Available Tools This MCP server (Amazon Bedrock AgentCore Gateway) supports the following tool:
- searchpulse___search - Answers a question from live Amazon Bedrock Web Search results with cited source URLs. Arguments: q (required, at most 500 characters), mode (standard default, or deep), api_key (required).
Prerequisites
- An active subscription to this product. Your API key (it starts with mp_) is stored in your AWS Secrets Manager after you choose Set up your account, and is also shown on the registration page.
- Install Node.js and npm (for mcp-remote), or Python 3.10+ (for the Strands Agents SDK).
Authentication The MCP endpoint needs no connection header. Pass your key as the api_key argument of every tool call; replace YOUR_API_KEY with your actual key below. A wrong or inactive key returns an error with status 401.
MCP endpoint: https://waltsoft-marketplace-gateway-xncyjgs1uh.gateway.bedrock-agentcore.us-east-1.amazonaws.com/mcp
Claude Desktop Edit the configuration file at:
- macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
- Windows: %APPDATA%\Claude\claude_desktop_config.json
Add the below code:
{ "mcpServers": { "waltsoft-searchpulse": { "command": "npx", "args": [ "mcp-remote", "https://waltsoft-marketplace-gateway-xncyjgs1uh.gateway.bedrock-agentcore.us-east-1.amazonaws.com/mcp" ] } } }Then ask, for example: "Use searchpulse___search with q What is AWS Lambda? and api_key YOUR_API_KEY".
Strands Agents (Python)
pip install strands-agents mcp from mcp.client.streamable_http import streamable_http_client from strands.tools.mcp import MCPClient URL = "https://waltsoft-marketplace-gateway-xncyjgs1uh.gateway.bedrock-agentcore.us-east-1.amazonaws.com/mcp" with MCPClient(lambda: streamable_http_client(URL)) as mcp: result = mcp.call_tool_sync("call-1", "searchpulse___search", {"q": "What is AWS Lambda?", "mode": "standard", "api_key": "YOUR_API_KEY"}) print(result["content"][0]["text"])Tool result shape
{"query": "string", "mode": "standard|deep", "answer": "string", "citations": [{"title": "string", "url": "string", "start_index": "integer", "end_index": "integer"}], "search_queries": ["string"], "tokens_used": {"input": "integer", "output": "integer"}, "timestamp": "string"}Show the citation links with any answer you display.
Billing Only successful calls are billed: a standard call is one $0.30 unit and a deep call uses 2 units ($0.60).
Rate Limits
- 50 requests per second (bursts up to 100), and 30 requests per minute per client IP.
- Exceeding returns HTTP 429 Too Many Requests.
- Use retry and exponential backoff to handle limits.
Learn More API Docs: https://searchpulse.waltsoft.net Support: support@waltsoft.net
Support
Vendor support
Email support@waltsoft.net for API questions and integration help. Response within 24 hours.
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.