Skip to main content

Pure-Python SMR API client and MCP server.

Project description

managed-research

Pure-Python public SMR surfaces for Managed Research.

Current scope:

  • SMR API client
  • SMR MCP stdio server
  • generated-schema sync path for public SMR contracts

Out of scope for this slice:

  • runtime internals
  • sandbox/session control
  • private backend models

Install

pip install -U managed-research

For local development:

uv sync --extra dev

Run the MCP server

uv run managed-research-mcp

The package reads SYNTH_API_KEY and SYNTH_BACKEND_URL from the environment.

Python API surface:

from managed_research import ManagedResearchClient

client = ManagedResearchClient(api_key="sk_...")
projects = client.list_projects()

Sync exported public schemas

uv run python scripts/sync_public_schemas.py --source /path/to/exported/schemas

If you prefer environment configuration, set MANAGED_RESEARCH_SCHEMA_SOURCE instead of passing --source.

There is also a console entrypoint:

uv run managed-research-sync-schemas --source /path/to/exported/schemas

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

managed_research-0.1.0.tar.gz (67.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

managed_research-0.1.0-py3-none-any.whl (59.9 kB view details)

Uploaded Python 3

File details

Details for the file managed_research-0.1.0.tar.gz.

File metadata

  • Download URL: managed_research-0.1.0.tar.gz
  • Upload date:
  • Size: 67.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.9.6

File hashes

Hashes for managed_research-0.1.0.tar.gz
Algorithm Hash digest
SHA256 a1c82a1d49aaabef95bf5f3546ed9dcad264c1c3bde78cfea02959661203c3b5
MD5 198d755c918b01e694e81bbacd3e1a10
BLAKE2b-256 ba377d7022206cc0870f5122641b1e70d674aa3138fbe1e6f09fb4c29065ea2a

See more details on using hashes here.

File details

Details for the file managed_research-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for managed_research-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 5747c689aa80a2460b570ee25c72cf52c0ef7cac13bc24b854074e3a792f5769
MD5 98b1f4565578ede6b0dc654d26271e0a
BLAKE2b-256 d34b956aba0e20d8cf1435b1f86eb755f04ff7c0b4c4661693e8c5631d65b6d9

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page