Skip to main content

Cred Semantic Kernel integration — credential delegation plugin for Microsoft Semantic Kernel agents

Project description

cred-semantic-kernel

Microsoft Semantic Kernel integration for Cred. OAuth2 credential delegation for AI agents.

Install

pip install cred-semantic-kernel

Quick Start

import os
import semantic_kernel as sk
from cred_semantic_kernel import CredPlugin

kernel = sk.Kernel()

plugin = CredPlugin(
    agent_token=os.environ["CRED_AGENT_TOKEN"],
    user_id="user_123",
    app_client_id="my_app_client_id",
)

kernel.add_plugin(plugin, plugin_name="cred")

Plugin Functions

The cred plugin exposes one kernel function:

delegate

Parameter Type Description
service string Service slug (e.g. google, github)
scopes string Comma-separated OAuth scopes to request

user_id and app_client_id are pre-configured at construction time, not agent-controlled.

Returns a JSON string with access_token, token_type, expires_in, service, scopes, and delegation_id.

Handling Consent

When the user hasn't connected the service, the delegate function raises ConsentRequiredError. The error's consent_url attribute contains the URL to redirect the user.

from cred import ConsentRequiredError

try:
    result = plugin.delegate(service="google", scopes="calendar.readonly")
except ConsentRequiredError as e:
    print(f"Redirect user to: {e.consent_url}")

Cred Cloud (Coming Soon)

Managed cloud delegation is coming. Join the waitlist.

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

cred_semantic_kernel-1.0.0.tar.gz (4.3 kB view details)

Uploaded Source

Built Distribution

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

cred_semantic_kernel-1.0.0-py3-none-any.whl (3.4 kB view details)

Uploaded Python 3

File details

Details for the file cred_semantic_kernel-1.0.0.tar.gz.

File metadata

  • Download URL: cred_semantic_kernel-1.0.0.tar.gz
  • Upload date:
  • Size: 4.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.3

File hashes

Hashes for cred_semantic_kernel-1.0.0.tar.gz
Algorithm Hash digest
SHA256 1c34331cb45f3d5eba61cf84407c08d087618517742b56686ae55721f59d4270
MD5 e7e61a05a45cea25f6c6160e6386eb01
BLAKE2b-256 bf42feb7d9ff9d798232d40757af3a2702d199a0cf79b07089d8d6fef8655d60

See more details on using hashes here.

File details

Details for the file cred_semantic_kernel-1.0.0-py3-none-any.whl.

File metadata

File hashes

Hashes for cred_semantic_kernel-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 d0e5bd80b9e119bae38c72ce2a401275010b048a1ddb83b0a554dac43225749f
MD5 53db964919357e67ad384253b415123a
BLAKE2b-256 9267d4a387d3024e8cba031f575ae50c34b891dc8f8bab54f1b99772deddb308

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