north-mcp-python-sdk

Name: north-mcp-python-sdk
Rating: 77 (1 reviews)
Author: cohere-ai

cohere-ai/north-mcp-python-sdk

A specialized Python SDK extending the Model Context Protocol to support North authentication, user identity validation, and OpenTelemetry integration.

14 11MITUpdated 2026-07-29

Great

View on GitHub Open source file

Overview

The North MCP Python SDK is built on top of the original MCP Python SDK to add native support for North-specific authentication extensions. It enables developers to secure their MCP servers using user ID tokens, access third-party service OAuth connectors on behalf of users, and integrate advanced OpenTelemetry tracking with privacy controls. Additionally, it features built-in health check endpoints and a comprehensive debug mode for troubleshooting authentication workflows.

Capabilities

▸North user identity verification using ID tokens and trusted issuers
▸Accessing third-party OAuth tokens for external service integrations
▸StreamableHTTP transport support for server communication
▸OpenTelemetry helpers for custom spans and trace-log correlation
▸Built-in /health endpoint for Kubernetes liveness and readiness probes
▸Comprehensive debug mode for inspecting headers, tokens, and auth requests

Best for

Developing secure MCP servers that integrate with the North authentication ecosystem, Validating user identity and managing third-party OAuth access tokens within MCP tools, Implementing OpenTelemetry tracing and log correlation for MCP server operations, Running local testing and debugging of authenticated MCP servers using the MCP Inspector

Works with

Claude CodeCodexChatGPTGemini CLICursorGitHub CopilotOpenCode

Evoa Score breakdown= Σ (score × weight)

Task usefulness20%100 → +20.0

実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析

Code quality15%90 → +13.5

実装・指示の品質。 — AIによるSKILL.md/README解析

Maintenance15%100 → +15.0

リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ

Documentation12%36 → +4.3

ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量

Security15%50 → +7.5

危険・不審な挙動が無いか。 — AIによるセキュリティレビュー

Originality10%85 → +8.5

ありふれたラッパーではない独自性。 — AIによる独自性判定

Popularity8%39 → +3.1

コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）

Compatibility5%100 → +5.0

対応AIエージェントの広さ。 — AIによる対応エージェント判定

Weighted total76.9 / 100

ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。ランキングはこのScoreのみで決まり、広告で変わりません。算出方法の詳細 →

Security considerations

Debug mode logs sensitive information including authorization headers and token metadata and must never be enabled in production. Production environments should strictly configure trusted_issuers to verify user ID token signatures.