mcpscraper-memory-sdk 0.13.1

Official Python clients for all 165 mcpscraper.dev MCP tools and the direct memory API

mcpscraper-memory-sdk (Python)

Official Python clients for all 165 unified mcpscraper.dev MCP tools plus the direct 89-tool memory.mcpscraper.dev API.

This is a thin JSON-RPC client generated against ../../contracts/memory.tools.json, the public contract for the hosted API. It contains no product source — only typed request/response plumbing.

Install

pip install mcpscraper-memory-sdk

Usage

from mcpscraper_memory import MemoryClient, MemoryApiError

client = MemoryClient(api_key="mk_your_key")

try:
    result = client.memory.search(query="competitor pricing pages")
    for hit in result.results or []:
        print(hit["source"], hit["score"])
except MemoryApiError as err:
    print(f"memory call failed: {err}")

Namespaces

client.access, client.capture, client.channels, client.facts, client.library, client.memory, client.recall, client.schedule, client.storage, client.tables, client.vaults, client.video, client.webhooks — one method per tool, snake_case, typed with generated Pydantic models.

Use McpToolsClient(api_key="sk_...") for all 165 unified tools (76 MCP Scraper plus 89 mirrored memory tools); it has the same generated namespaces as every other SDK package. Bulk Gmail, Calendar, Zoom, Meta Marketing, and Resend exports are available through client.connections.export_connected_service_data(...); select meta_ads_insights for daily account/campaign/ad-set/ad reporting or resend_data for the Resend aggregate, and renew expired artifact URLs with client.connections.renew_connected_data_download(artifact_id="artifact_123").

Use client.call_tool_result(name, args) for native MCP image, audio, or resource blocks. The existing call_tool method keeps returning the parsed structured/text value.

Don't have a memory key?

If you already have an mcpscraper.dev API key and don't want to provision a separate mk_... memory key, use mcpscraper-sdk's ScraperClient.memory_tools instead — it exposes this exact same set of 89 tools, dispatched through your scraper API key.

Regenerating models

src/mcpscraper_memory/models/ and _generated_client.py are generated from ../../contracts/memory.tools.json. After editing the manifest, regenerate with:

python scripts/generate_models.py

See also

Repo README (multi-language examples with real sample output) · mcpscraper-memory-sdk on npm (Node) · mcpscraper-sdk on PyPI (also reaches these 89 tools via a scraper key) · mcpscraper-cli