mcpField
S
SearchPipe

SearchPipe

Remote
searchpipe.techSearch0Updated today

About SearchPipe

SearchPipe is a web search API and managed MCP server for developers building AI agents. It returns ranked results with source URLs and can include an AI-generated answer or raw page content.

Key features

  1. 01Ranked web search results
  2. 02Source URLs and result scores
  3. 03Optional AI-generated answers
  4. 04Optional full page content
  5. 05Remote access over Streamable HTTP

Use cases

  1. 01Grounding agent responses in current web results
  2. 02Retrieving source links for research
  3. 03Including an answer with search results

MCP support

Exposes the `searchpipe_search` tool through a remote MCP endpoint using Streamable HTTP. MCP clients can provide an API key in the URL or an Authorization header.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://searchpipe.tech/mcp/
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

All endpoints
Streamable HTTPhttps://searchpipe.tech/mcp/Auth required

Tools

2
ParameterTypeRequiredDescription
querystringYes
api_keyanyNo
max_resultsintegerNo
include_answerbooleanNo
include_raw_contentbooleanNo

Details

From the project README

SearchPipe Integrations

MCP SearchPipe

Official integration packages for SearchPipe — a web search API and MCP server for developers building AI agents.

This repository contains:

  • Remote MCP endpoint — connect any MCP client to SearchPipe via Streamable HTTP (no local install needed)
  • LangChain SDK — pip install langchain-searchpipe for retriever, tool, and answer components
  • Python SDK — pip install searchpipe, official thin client over the Search API
  • TypeScript SDK — npm install searchpipe, official zero-dependency client (ESM + CJS)

The SearchPipe server itself is a managed service at searchpipe.tech. Self-hosting is available on request.

MCP Access (Remote)

Add to your MCP client config (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "searchpipe": {
      "url": "https://searchpipe.tech/mcp/?api_key=sp-your-api-key-here"
    }
  }
}

Or use an Authorization header instead of URL parameter:

{
  "mcpServers": {
    "searchpipe": {
      "url": "https://searchpipe.tech/mcp/",
      "headers": {
        "Authorization": "Bearer sp-your-api-key-here"
      }
    }
  }
}

See claude_desktop_config.json.example for a ready-to-copy template.

LangChain Integration

pip install langchain-searchpipe

See langchain-searchpipe/README.md for full usage examples (retriever, tool, answer components).

Official SDKs

Both SDKs are thin wrappers over POST /search — same parameters, same response shape as the REST API.

Python (sdks/python/):

pip install searchpipe
from searchpipe import SearchPipe

client = SearchPipe(api_key="sp-YOUR_KEY")
resp = client.search("FastAPI tutorial", max_results=5, include_answer=True)
print(resp.answer)
for r in resp.results:
    print(r.score, r.title, r.url)

JavaScript / TypeScript (sdks/typescript/):

npm install searchpipe
import { SearchPipe } from "searchpipe";

const client = new SearchPipe({ apiKey: "sp-YOUR_KEY" });
const resp = await client.search({ query: "FastAPI tutorial", maxResults: 5, includeAnswer: true });
console.log(resp.answer);

Both default to https://searchpipe.tech and read the key from SEARCHPIPE_API_KEY. See each SDK's README for the full API, error classes, and self-hosting options.

Getting an API Key

  1. Sign up at searchpipe.tech
  2. Verify your email
  3. Go to Dashboard → API Keys → copy your sp- key
  4. New accounts receive free credits to try the service

Tool Schema

searchpipe_search

Run a web search with optional AI-generated answer.

ParameterTypeRequiredDefaultDescription
querystring✅—Search query
max_resultsinteger—5Number of results (1–20)
include_answerboolean—falseInclude AI-generated answer
include_raw_contentboolean—falseInclude full page content
api_keystring——API key (or use env var / URL param)

Returns: Tavily-style SearchResponse with query, answer, results[].

Links

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.