Tag: mcp

All the articles with the tag "mcp".

• Docs-as-Code as a Knowledge Distribution Stack

  Updated: 22 Sep, 2026

  Markdown, Git, llms.txt, and MCP create human and agent read paths from one source, while AI-mediated pull requests remove Git fluency from writing.

• The MCP Proxy, Live: 206 Tools in 2,100 Tokens

  Updated: 22 Sep, 2026

  A live MCP proxy reduced startup context from about 217,000 to 2,100 tokens across 206 tools. Most sessions now run from a ten-tool always-on set.

• What Actually Differs Across Search APIs Built for Agents

  Updated: 13 Sep, 2026

  Exa, Parallel, Perplexity, and AgentCore span raw retrieval, generated answers, managed research, and monitoring. Comparing them starts with separating those layers.

• A 200 Response Does Not Prove Search Worked

  13 Sep, 2026

  HTTP success proves transport. A credible agent-search evaluation separately tests the contract, evidence, tool calls, lifecycle cleanup, and cost.

• Search Is a Pipeline, Not a Tool

  13 Sep, 2026

  Agent search works as a five-stage pipeline: discovery, extraction, verification, synthesis, and monitoring. Treating it as one tool hides the failures that matter.

• Web Search as a Managed Connector: Wiring Amazon Bedrock AgentCore WebSearch Into Any Agent

  Updated: 13 Sep, 2026

  Amazon Bedrock AgentCore WebSearch is a managed MCP connector backed by an Amazon-operated index, authorized through IAM, and priced at $7 per 1,000 queries.

• MCP Became Stateless: Migrating a Real AgentCore Gateway

  3 Aug, 2026

  MCP 2026-07-28 removes protocol sessions from remote calls. Here is what changed in a working AgentCore WebSearch gateway, what stayed untouched, and how to migrate without breaking older clients.

• Open Data Wasn't Missing. The Interface Was.

  29 Jul, 2026

  A 12-domain benchmark and Sentinel-2 experiment show where the Registry of Open Data MCP server works, where search fails, and what the interface unlocks.