BrandMyLaptop
Sell ad space on your laptop Discussion | Link
Latest News Archive - Page 172
langchain==1.4.0a2
Alpha preview of langchain.mcp — a first-party adapter that turns any MCP server into LangChain tools you can hand straight to create_agent . Connection handling is FastMCP 's, so its client features are available as-is rather than re-implemented behind a narrower interface. pip install " langchain[mcp]==1.4.0a2 " Connect MCPAdapter takes any target fastmcp.Client accepts — transport is inferred, so there is one entry point rather than one per protocol. from langchain . agents import create_agent from langchain . mcp import MCPAdapter async with MCPAdapter ( "https://example.com/mcp" ) as adapter : agent = create_agent ( "anthropic:claude-sonnet-5" , await adapter . get_tools ()) result = await agent . ainvoke ({ "messages" : [{ "role" : "user" , "content" : "..." }]}) Valid targets: a URL, a local script path (launched over stdio), an in-process FastMCP server, a config naming several servers at once, or a fastmcp.Client you built yourself. Tools returned by get_tools() hold the adapter's client, so they stay callable after the context exits — the async with block scopes discovery, not tool lifetime. Auth, caching, timeouts — build the client MCPAdapter takes two arguments: the target and elicitation . Everything else FastMCP supports is configured on a fastmcp.Client that you build and hand over as the target. This is the pattern to reach for whenever you need more than a bare connection: from fastmcp . client import Client from langchain . mcp import MCPAdapter client = Client ( "https://example.com/mcp" , auth = "oauth" , # or a bearer token string, or any httpx auth cache = True , # opt-in response caching timeout = 30 , ) async with MCPAdapter ( client ) as adapter : tools = await adapter . get_tools () Auth accepts "oauth" to run the OAuth flow, a token string for bearer auth, or an httpx.Auth instance for anything custom — see FastMCP's auth docs . Per-server headers and auth can also be set in a multi-server config (below). Caching is opt-in and off by default: cache=True enables it with defaults, honoring the server's own ttlMs and cacheScope hints; a CacheConfig customizes it. The cache is per-client and in-memory. Everything else on fastmcp.Client — timeout , log_handler , progress_handler , message_handler , roots , sampling_handler — works the same way. The adapter passes your client through untouched, so FastMCP behavior is not re-implemented or restricted. One caveat: with elicitation="interrupt" , the adapter clones your client so it does not overwrite a callback you set. Configuration (auth, cache settings, handlers) carries over to the clone; cached entries do not, since the clone gets its own store. adapter.client exposes the underlying client for prompts, resources, and anything else the adapter does not wrap. Multiple servers Point the adapter at a config and it fans out to every server through one connection, presenting a single tool list to your agent. config = { "mcpServers" : { "weather" : { "url" : "https://weather.example.com/mcp" }, "calendar" : { "url" : "https://calendar.example.com/mcp" , "headers" : { "Authorization" : "Bearer ..." }, }, } } async with MCPAdapter ( config ) as adapter : agent = create_agent ( "anthropic:claude-sonnet-5" , await adapter . get_tools ()) With more than one server, tools are namespaced by server name — weather_get_forecast , calendar_create_event — so collisions between servers are impossible. With exactly one server, the adapter connects directly and names are unprefixed. Each entry takes its own headers , auth , transport , and timeout , so servers with different credentials compose in one agent. A local server uses command / args instead of url and is launched over stdio. The config follows FastMCP's MCP JSON schema , so a config you already use elsewhere works here unchanged. Old and new protocol servers, side by side MCP has moved from the initialize handshake to server/discover , and servers in the wild sit on both sides of that line. FastMCP negotiates the era per connection, so the adapter reaches either without you selecting one: # handshake-era server over SSE legacy = MCPAdapter ( "https://legacy.example.com/sse" ) # modern-era server over streamable HTTP modern = MCPAdapter ( "https://modern.example.com/mcp" ) Separate adapters negotiate independently and can run concurrently, each on its own era. This is covered by integration tests that stand up one server of each era and call both. The one rule worth knowing: a multi-server config exposes a single era, so its oldest backend sets the era for the whole fleet. Mixing a handshake-era server into a config pulls the modern backends back to the handshake era — they still work, but era-gated features go with it. Keep a legacy server in its own adapter when you want the others on the modern protocol: async with ( MCPAdapter ({ "mcpServers" : {... modern servers ...}}) as modern , MCPAdapter ( "https://legacy.example.com/sse" ) as legacy , ): tools = await modern . get_tools () + await legacy . get_tools () Results Each tool is async. An MCP tool that runs and reports failure comes back as a ToolMessage with status="error" carrying the server's own error text, so the agent can correct itself and retry. Transport failures and unconvertible content raise instead — a model cannot act on those. Structured output rides along on the tool message artifact: from langchain . mcp import MCPToolArtifact artifact : MCPToolArtifact | None = tool_message . artifact # None when there is no structured content artifact [ "structured_content" ] Elicitation — servers that ask questions mid-call Some MCP tools need input before they can finish. Opt in, and the request surfaces as a LangGraph interrupt() , so the human already reviewing the agent's work answers the server too. adapter = MCPAdapter ( target , elicitation = "interrupt" ) The capability is opt-in rather than default because declaring it is a promise made on the wire: an agent with no path to a human cannot keep it. Left unset, nothing is declared, and a server whose tool requires an answer declines the call rather than running without one. The run stops with a typed payload, and resumes with one answer per request key: from langgraph . types import Command result = await agent . ainvoke ({ "messages" : [...]}, config ) [ pause ] = result [ "__interrupt__" ] pause . value [ "type" ] # "mcp_elicitation" pause . value [ "tool_name" ] # the tool that is waiting pause . value [ "requests" ] # each question, in the order to ask them answer = { "responses" : { key : { "action" : "accept" , "content" : { "guests" : 4 }}}} result = await agent . ainvoke ( Command ( resume = answer ), config ) Requests narrow on mode : a "form" request carries requested_schema for the answer to satisfy, a "url" request carries an address for the human to visit. Answers narrow on action — "accept" (with content ), "decline" (skip the question, let the call proceed), or "cancel" (abandon the tool call). Requires a checkpointer, as any interrupt does. Sampling and roots are not answered through interrupts; leave those to your client's own handlers. Types for handlers — MCPElicitationInterrupt , MCPElicitationRequest , MCPElicitationResponse , MCPElicitationResume , and the ELICITATION_INTERRUPT_TYPE discriminator — live in langchain.mcp.elicitation . Further reading FastMCP client docs — auth, caching, transports, and handler configuration Client transports — what each target type infers Elicitation — the underlying protocol feature This is an alpha: the interface may shift before 1.4.0 is final. Feedback on the API shape is exactly what we're after.
DLSS 5 leaked and modders are putting Nvidia’s AI effects on everything
Modders are trying out an unofficial version of Nvidia's DLSS 5 on Skyrim, Cyberpunk 2077, GTA V, and a bunch of other games after code for the AI upscaling tech appeared in an early-access build of NBA 2K27. Members of the RenoDX modding channel on Discord reportedly found a way to extract the DLSS "Neural […]
Android 17 Adds OS-Wide ECH to Hide Website Visits From Network Providers
Google on Thursday announced new network security protections in Android 17 to bolster connection privacy, address cellular vulnerabilities, and safeguard the privacy of users' home networks. Topping the list is support for Encrypted Client Hello (ECH), a privacy standard that prevents networks from eavesdropping on which websites a user is visiting. "This new privacy standard works in tandem
Kenyan police fire tear gas at Nairobi protest against import duty hike
Traders frustrated by more than $5,000 duty hike they say will hurt small businesses.
Gauth AI Course
AI courses you can watch, quiz through, and create Discussion | Link
Fed's Kevin Warsh warns inflation is too high, sparking bets rate hikes are coming
Fed Chair Kevin Warsh reiterated his commitment to fighting inflation in a major speech — raising expectations that rate hikes may be coming, though he did not clearly spell out a path going forward.
The two types of Israeli settlers
Israeli settlement expansion in the occupied West Bank isn’t just driven by ideology, but also by economic incentives.
myAIcademy
Learn AI skills for your specific role and team Discussion | Link
Cohere Parse 5
Turn complex docs, tables & images into AI-ready data Discussion | Link
Just the rumour of a bug is enough to find an exploit these days
Article URL: https://anil.recoil.org/notes/rumour-is-the-exploit Comments URL: https://news.ycombinator.com/item?id=49480466 Points: 305 # Comments: 108
Germany news: Baltic summit plans hybrid-threat task force
Ministers from countries bordering the Baltic Sea have agreed on a rapid response force to counter hybrid threats. Meanwhile, the far-right AfD has failed to topple a state premier. DW has more updates from Germany.
Big Tech's massive AI spending is putting one of its longtime strengths to the test
There's new risk emerging from Big Tech's massive artificial intelligence buildout.
Nvidia is paying $12.9 billion to keep open models on its chips
I’m Matt Burns, Chief Content Officer at Insight Media Group. Each week, I round up the most important AI developments, The post Nvidia is paying $12.9 billion to keep open models on its chips appeared first on The New Stack .
Meta makes AI glasses slightly less creepy with limit on nonconsensual recording
Meta fixes AI glasses to stop recording any time users cover up the safety light.
In Other News: Log4j RCE Scare, Minimus Shutdown, Iranian Hacker Sanctions
Noteworthy stories that might have slipped under the radar: Manchester Airports Group cyberattack, Carhartt breach data was partly fake, U.S. Bank responds to ransomware gang’s claims. The post In Other News: Log4j RCE Scare, Minimus Shutdown, Iranian Hacker Sanctions appeared first on SecurityWeek .
Germany: Man gets life in jail for US tourist's rape, murder
The crime was unsolved for over three decades before new DNA proof made it possible to arrest and convict the now 81-year-old. His victim, Amy Lopez, was 24 at the time of her murder.
19 Chrome and Edge Extensions Found With Wallet-Stealing and Crypto-Draining Code
Cybersecurity researchers have discovered a cluster of 18 Google Chrome and one Microsoft Edge extensions that were published over the last six months and harbored wallet secret stealing and cryptocurrency draining capabilities. The extensions, per Socket security researcher Karlo Zanki, share similarities in code and tradecraft, with evidence indicating that the campaign may have been active
The iPhone Fold could make concerts even worse
You know the person blocking your view of the concert because their phone is swaying in the air, recording the entire thing? Get ready for the unfolded version of it. This week on The Vergecast, we dive right into the big week of Apple news. First, it's the refreshed Mac Mini and Mac Studio, as […]
GLM-5.3 is now open-weight
Article URL: https://twitter.com/Zai_org/status/2093354097122455713 Comments URL: https://news.ycombinator.com/item?id=49479878 Points: 265 # Comments: 96
GLM-5.3 is now open-weight
https://twitter.com/Zai_org/status/2093354097122455713 https://z.ai/blog/glm-5.3 Comments URL: https://news.ycombinator.com/item?id=49479878 Points: 620 # Comments: 218
GUIs should be fully keyboard-driven
Article URL: https://ckardaris.com/blog/2026/08/28/keyboard-driven-guis.html Comments URL: https://news.ycombinator.com/item?id=49479837 Points: 577 # Comments: 290
Affirm surges on strong outlook; CEO says high gas prices are hitting U.S. shoppers
The national average price for gas is at $4.09 per gallon and was last below $3 on March 2.
Fed has 'work to do' if price rises don't ease for Americans, Warsh says
Kevin Warsh remarks suggest interest rates could be increased if policymakers think inflation is running too high.