CLAUDE LABJP
MCP — Support for the 2026-07-28 spec is rolling out across Claude. The protocol moves from bidirectional and stateful to request/response, so MCP servers can now live on serverless and edge infrastructureEXTENSIONS — Three official extensions have landed: MCP Apps for server-rendered UI, Tasks for async and long-running work, and Enterprise Managed Auth for IdP-based org-wide provisioningADOPTION — MCP passed 400 million monthly SDK downloads, roughly 4x growth this year, settling into its role as the standard way to connect agents to applicationsQUOTA — Today, August 19, is the last day of the 50 percent weekly usage boost for Claude Code subscribers. If you have long agent runs queued, this is the windowPRICING — Claude Sonnet 5's introductory rate of $2 per million input tokens and $10 output ends August 31; standard pricing of $3 and $15 takes over on September 1, twelve days outFIX — A bug where MCP v2 connections endlessly reopened subscriptions against servers with fixed timeouts is resolved, and a forward_user_identity setting was added for user attributionMCP — Support for the 2026-07-28 spec is rolling out across Claude. The protocol moves from bidirectional and stateful to request/response, so MCP servers can now live on serverless and edge infrastructureEXTENSIONS — Three official extensions have landed: MCP Apps for server-rendered UI, Tasks for async and long-running work, and Enterprise Managed Auth for IdP-based org-wide provisioningADOPTION — MCP passed 400 million monthly SDK downloads, roughly 4x growth this year, settling into its role as the standard way to connect agents to applicationsQUOTA — Today, August 19, is the last day of the 50 percent weekly usage boost for Claude Code subscribers. If you have long agent runs queued, this is the windowPRICING — Claude Sonnet 5's introductory rate of $2 per million input tokens and $10 output ends August 31; standard pricing of $3 and $15 takes over on September 1, twelve days outFIX — A bug where MCP v2 connections endlessly reopened subscriptions against servers with fixed timeouts is resolved, and a forward_user_identity setting was added for user attribution
TAG

MCP

70 articles
Back to all tags
Related:
Claude Code27automation17claude-code14Claude API7Cowork6troubleshooting6Operations5cowork5skills5TypeScript4production4Stripe4
API & SDK/2026-08-19Intermediate

The listen Stream Kept Reopening Against My Serverless MCP Server

No errors anywhere, yet connections to the MCP server kept piling up overnight. Here is what happens when a fixed platform timeout meets a resubscribe loop, reproduced in a few dozen lines.

API & SDK/2026-07-31Advanced

The 400-Character Preview That Was Still Holding On to a Megabyte

Truncating tool output in your own MCP server does not free the original. Node's sliced strings keep the parent alive. Here is the measured 13-character boundary, which flattening tricks actually work, and a heap-snapshot audit script that counts the retained parents for you.

Claude Code/2026-07-29Advanced

The MCP Server Connects Fine and Still Hands Back Zero Tools — Catching Silent Capability Drift with a Tool Manifest Diff

A missing credential does not break the MCP handshake. initialize succeeds, tools/list succeeds, and the array comes back empty. Here is the measured behaviour, and a preflight that locks the expected tool surface and fails closed before the agent ever starts.

API & SDK/2026-07-28Advanced

The Line That Disappears at 100K: Measuring What Tool-Output Spill Actually Keeps

When agent tool output passes 100,000 characters, the full text spills to a file and the model sees only a head-truncated preview. Here are measured survival rates from a real repository, and the output envelope I built to push decision-relevant lines to the front.

Claude Code/2026-07-27Advanced

Whose Environment Expands That Variable? Fingerprinting Your Effective Managed MCP Policy

Variable references in the Managed MCP allowlist and denylist now resolve from the startup environment and the managed-settings env block. I rebuilt both resolution orders locally to see where verdicts diverge, then wrote a preflight check that reduces the effective policy to a comparable fingerprint.

API & SDK/2026-07-26Advanced

Rebuilding a Remote MCP Server That Never Needed Mcp-Session-Id

The MCP spec release candidate drops the session header. Here is how I audited my own remote server for session coupling and moved it to signed cursors, with measurements.

API & SDK/2026-07-24Advanced

Swapping Agent Config Per Session From One Shared Definition

A design pattern for running one base Managed Agent and overriding its model, prompt, tools, MCP servers, and skills per session with agent_with_overrides — with a validated factory and the operational traps I hit along the way.

Claude Code/2026-07-18Advanced

The MCP Server I Declared Vanished from the List — Designing Config for a Namespace You Share with the Vendor

When a vendor reserves an MCP server name, your .mcp.json declaration goes quiet instead of failing. Here is the preflight check and prefix convention I use to turn that silent gap into a loud stop before an unattended run.

Cowork/2026-07-17Advanced

It Worked on My Machine, but Nobody Could Trigger It — Four Assumptions I Stripped Out of a Cowork Plugin

I bundled four working automation skills into a plugin and shared it. Only one of them ever fired. Here is how I measured skill trigger rate, and the four assumptions — vocabulary, paths, connections, and naming — I had to strip out before it was portable.

Claude Code/2026-07-17Advanced

The Morning My Table Ended in "… 2,847 more rows" — Separating Render Caps from Token Cost in Tool Output

Claude Code 2.1.209 caps markdown tables at 200 rows plus a remainder count. Only the rendering is capped — the model still receives every row. Here is how to measure the gap and redesign tool output around aggregates.

Claude Code/2026-07-16Advanced

The Permission Rules You Added for Safety Are Taxing Every Turn — Auditing the Ruleset Without Loosening It

Version 2.1.209 fixed the per-turn slowdown from large deny/ask rulesets, but the design debt in your rules is still yours. Here are the audit scripts, a shadowing detector, a turn-timing harness, and how to fold enumerated rules into prefix rules safely.

Claude Code/2026-07-16Advanced

Your Overnight Session Wakes Up at 3GB — Four Places Memory Piles Up, and How to Tell Them Apart

The Claude Code process I left running overnight had grown to 3.4GB of resident memory by morning. Here are the four accumulation sources closed in 2.1.209, how to separate what's left in your own setup by sampling RSS slope, and a watchdog pattern that folds a session before it hurts.