CONNECTED RESEARCH

Knowledge map

Explore research through connected companies, technologies and questions. Every relationship links to its evidence.

55 / 55 articles with reviewed reader guides · 202 reviewed relationships

MCP tool-list pinning

MCP tool-list pinningMCP tool-list pinningChanges to the visible tool set during task executionChanges to the visible tool Anthropic Python SDK v1.8.0Anthropic Python SDK v1.8.0

Select a connected node to continue exploring. Open the evidence below to distinguish reporting, analysis and hypotheses.

Conditional hypothesis

MCP tool-list pinning → constrains → Changes to the visible tool set during task execution

The proposed mechanism is that pinning could reduce changes to the tools visible during a task. The article does not report a measured reduction and cautions that unchanged tool names can conceal changes in implementation, parameter interpretation, or accessed data.

Read the evidence
From a mechanistic perspective, the potential value of pinning the list is to reduce changes to the visible tool set during task execution.

Background sources for the article's reasoning: [S3] Anthropic

Read the full research

Reported evidence

Anthropic Python SDK v1.8.0 → enables → MCP tool-list pinning

The release declaration adds SDK support for MCP tool-list pinning in beta. This establishes announced interface support, not stable server-side enforcement or pinning of tool implementations.

Read the evidence
Anthropic v1.8.0 adds inline tool definitions and MCP tool-list pinning (beta), and unifies the evaluated_permission enum in Managed Agents events.[S3]

[S3] Anthropic

Read the full research

Connected research

agent

Agent Control Interfaces Are Taking Shape, but Trustworthy Execution Still Requires Linking Machine Identity and Evidence Chains

What do Agent SDK release notes establish about execution control, and what remains to be tested before tool calls can be stopped and responsibility reconstructed?

The article separates release declarations from runtime outcomes, explains why tool-list pinning does not establish reproducible execution and why visible logs do not establish an accountable evidence chain, and proposes validation tests rather than reporting measured improvements.