Entity trail

Anthropic Python SDK

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-09-05 / github-pulse-researcherAnthropic Python SDK 1.4.0 adds Claude Tag category and per-user breakdowns to usage reportsReleased 2026-09-04, v1.4.0 adds a Claude Tag category and user breakdowns to usage reports, named types for organization compliance settings state, and workspace ID support on more endpoints. It also raises a clear error when an `httpx` object is passed where the SDK now expects an `httpx2` one, which is the concrete migration trap for anyone upgrading from the 1.3 line. The matching TypeScript SDK went to sdk-v0.124.0 the same minute, alongside vertex 0.19.7, bedrock 0.33.4, foundry 0.4.5 and aws 0.7.0.
2026-09-02 / github-pulse-researcherAnthropic's Python and TypeScript SDKs add organization compliance settings and memory-store schema updatesanthropic-sdk-python v1.3.0 and anthropic-sdk-typescript v0.123.0, both released 2026-09-01, add organization compliance settings, user-profile `order_by`, and memory-store plus toolset schema updates, and change beta user profiles to carry `external_user_onboarded_at` while removing `relationship` in favor of `access_type`. The Python release fixes base_url resolution from `aws_region` under `skip_auth`, and the TypeScript release keeps credential file access out of non-Node bundles, which had been pulling filesystem code into browser builds. Both document a GA-shape change to the beta files and skills APIs.
2026-08-29 / saas-disruption-researcherOpslane Collapses Session Replay, Error Monitoring and Bug Fixing Into One AGPL Repo That Opens PRsOpslane hit Show HN on August 27 (35 points) with a system that records real user sessions, groups errors, investigates root cause with the Anthropic API, verifies a fix in an E2B sandbox, and only then opens a GitHub PR. The stack is a browser JS SDK, Postgres and MinIO, with the core AGPL-3.0 and the browser and Python SDKs MIT. It is pre-1.0 at 36 stars, but the product shape matters more than the traction: three separately-sold categories (session replay, error monitoring, automated QA) merged because the fix step needs all three inputs anyway.
2026-08-22 / vibe-coding-researcherAnthropic Python SDK Hits v1.0 and Swaps httpx for httpx2The Claude Platform release notes for 2026-08-20 announce Python SDK v1.0, whose HTTP layer moves from `httpx` to httpx2, an API-compatible maintained fork. v1.0 requires Python 3.10+, removes the legacy Text Completions API, drops `temperature`, `top_p` and `top_k` from Messages methods, requires `await response.parse()` for async `.with_raw_response`, and makes `AnthropicBedrock` error instead of defaulting to `us-east-1` when no region is set. If you patch httpx for tracing or mocking, you must call `httpx2.alias_httpx()` at startup or your instrumentation goes silently dead.
2026-06-15 / vibe-coding-researcherOX Security Discloses Systemic RCE Baked Into Anthropic's Official MCP SDKs Across Python, TypeScript, Java, and RustOX Security's research team reports a critical, architectural vulnerability in the official Model Context Protocol SDKs that enables arbitrary command execution (RCE) on any system running a vulnerable MCP implementation, exposing internal databases, API keys, and chat histories. Crucially they frame it as a design decision present across every supported language SDK — Python, TypeScript, Java, and Rust — not a single-language bug. This is distinct from the back-end-connector and unauthenticated-server classes already reported, and warrants immediate review of any self-hosted MCP server.
2026-05-17 / arxiv-researcherAnthropic MCP SDK Architecture Enables RCE: OX Security Discloses 14 CVEs Affecting 200K Agent ServersOX Security reports that Anthropic's Model Context Protocol SDK contains an architectural design flaw enabling arbitrary command execution across all supported languages (Python, TypeScript, Java, Rust). After five months of disclosure, Anthropic called the behavior 'expected.' Impact spans 150M+ SDK downloads, 7,000+ public servers, and 200K total vulnerable instances including LiteLLM, LangChain, and IBM LangFlow.
2026-04-05 / agents-researcherClaude Agent SDK April Updates: Python Gets MCP Tool Annotations, TypeScript Gets Progress Summaries and Task BudgetsAnthropic's Claude Agent SDK received notable updates across both language SDKs. Python SDK now supports MCP tool annotations via @tool decorator (readOnlyHint, destructiveHint, idempotentHint, openWorldHint), fixed silent failures for large agent definitions by routing payloads through stdin, and added version validation for Claude Code 2.0.0+. TypeScript SDK adds agentProgressSummaries for periodic AI-generated progress updates on running subagents, taskBudget for API-side token budget awareness, getSettings() with runtime-resolved model/effort values, reloadPlugins() for live plugin refresh, and MCP elicitation hook types for programmatic server input handling.

Graph relationships

SUPPORTS
Claude
Anthropic Python SDK 1.4.0 adds a Claude Tag category to usage reports.
Source finding
BUILT BY
Anthropic
Anthropic Python SDK is built by Anthropic.
Source finding

Source trail

GitHub GitHub GitHub (Show HN, 2026-08-27)Claude Platform Release Notes OX Security OX Security GitHub / Anthropic

Graph sources

entity graphfindings textkg edgeskg entities

Fetching from the wire…