#MCP and tools

1091 stories · 135 in 7 days · 462 in 30 days · Topic watch →
Oct 29
Oct 28
ProductsBuildersMulti-sourceSelected23:58
Legora joins Claude for Legal with in-Claude agent integration

The move signals that vertical AI vendors are shifting from standalone apps to embedded agents inside general-purpose assistants, which changes how law firms will buy and evaluate tools. Legal teams already on Claude can pilot Legora-powered research without new procurement or a separate security review, since it runs under existing permissions. Firms weighing Claude for Legal against alternatives like Harvey now get a clearer picture of Anthropic's partner strategy.

Event
WeAreLegora@WeAreLegoraSource
ProductsBuildersMulti-sourceSelected07:26
Drex for Search tops Snowflake's MADQA leaderboard at 94.7%

A 94.7% score on MADQA positions Drex for Search as a serious retrieval option for agents that must cite exact pages from enterprise documents. Its availability as an MCP tool means teams already running Claude Code, Codex, Cursor or OpenCode can plug it in without changing their stack. Developers building document-grounded agents should benchmark it against their current RAG setup.

Event
TestingCatalog@testingcatalogSource
Oct 27
ProductsBuildersSelected00:25
Nous Research Adds Advanced Delegation Modes to Hermes Agent

Per-subagent model routing turns a single orchestrator run into a cost-and-capability optimisation: cheap models for routine subtasks, stronger ones for hard reasoning. Builders running multi-agent workflows can try it to cut token spend without giving up quality on the steps that need it. It applies to Hermes Agent deployments generally, with no region-specific pricing announced.

Official accountNous Research@NousResearchSource
Oct 26
PapersBuildersMulti-sourceSelected23:07
MCP-Injector shows tool faults cut agent scores 60%

Scaling up model size does not buy robustness against broken tools, so engineering effort belongs in framework-level error handling and fault-injected evals rather than bigger models. Teams shipping MCP-based agents in production should test against MCP-Injector-style failure mixes and compare their agent stack choices, since the framework mattered more than the model. The fault calibration is derived from real open-source MCP repository issues, making the findings directly reusable for benchmark design.

Event
DAIR.AI@dair_aiSource
Oct 24
ProductsBuildersMulti-sourceSelected15:31
OpenAI Codex Adds Mid-Conversation Reasoning Switching and CLI Updates

Cached context surviving reasoning-level switches removes the cost penalty for mixing cheap and deep reasoning in one session, changing how developers should budget tokens across a task. Enterprise teams on Windows or behind proxies get sign-in and auth fixes that reduce deployment friction. Practitioners running long Codex sessions can now configure presets once instead of re-specifying settings per run.

Event
Vaibhav Srivastav@reach_vbSource
How-toBuildersOfficialSelected01:54
Amazon SageMaker AI guide to multi-turn reinforcement learning

Training on end-task outcomes rather than labeled intermediate steps removes a major bottleneck for building agents that handle long, stateful workflows. Practitioners can follow the pipeline directly to set up agentic RL on AWS infrastructure, with Bedrock AgentCore handling the agent and reward deployment. The Wordle example makes the rollouts easy to verify, which is useful when adapting the recipe to your own task environment.

Primary sourceAWS Machine Learning Blog@Daniel QuangSource
Oct 23