mcpscraper-memory-sdk (Python)
Official Python clients for all 377 unified mcpscraper.dev MCP tools plus the direct 148-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.crm, client.facts, client.files, client.graph, client.library, client.memory, client.recall, client.research, client.schedule, client.storage, client.tables, client.tags, client.vaults, client.video, client.webhooks — one method per tool, snake_case, typed with generated Pydantic models. Use Research for sourced knowledge and CRM for an actual relationship; counterpart operations link records without copying fields. External CRM providers remain unavailable, with no setup or write wrapper. Original Gmail attachment bytes saved to Memory are available through client.files.file_asset_save(...) and client.files.file_asset_get(...).
Use McpToolsClient(api_key="sk_...") for all 377 unified tools, including provider-neutral X-Ray surveys, attribution-impact reporting, and truthful evidence-status operations; it has the same generated namespaces as every other SDK package. The ZIP reader is available as client.web.archive_read(url=...), and the editorial workflow begins with client.editorial.reading_room_guide(focus="workflow"). Scheduled results and saved artifact templates are available under client.schedule; run IDs and cursors remain opaque. 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.
The unified MCP client accepts pages=2 on
client.other.harvest_paa_start(...). It keeps one page as the default, adds
page-two organic results when available, and expands PAA only on the preserved
first page. Poll the same job with harvest_paa_status; pagination remains
nullable for results saved under older contracts.
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 148 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 148 tools via a scraper key) · mcpscraper-cli
1 maintainer
Release files for mcpscraper-memory-sdk 0.37.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| mcpscraper_memory_sdk-0.37.0.tar.gz | 194.8 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| mcpscraper_memory_sdk-0.37.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 775.4 kB
Release files / mcpscraper_memory_sdk-0.37.0.tar.gz
| Download URL | mcpscraper_memory_sdk-0.37.0.tar.gz |
|---|---|
| Size | 194.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
3984819174e98262a36c5eb55d6e4ca315d381cd6cd0534663ac792118c30452
|
|
BLAKE2b-256 checksum How to use checksums |
6e0fc903cb6c12296c3c8e0ca2b7c8b27d379d342102584bb4444a03f253ed92
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.11.14 {"installer":{"name":"uv","version":"0.11.14","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Release files / mcpscraper_memory_sdk-0.37.0-py3-none-any.whl
| Download URL | mcpscraper_memory_sdk-0.37.0-py3-none-any.whl |
|---|---|
| Size | 580.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
39724f8f89f48b33d645ca6dea3d8f1fb40a1800dbed86a8513f1de287524281
|
|
BLAKE2b-256 checksum How to use checksums |
25bf4193dd370a0e8de1ab568323fffec0b3f8ab57ed59b0b6418dda673d56e0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.11.14 {"installer":{"name":"uv","version":"0.11.14","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
