AI Blog

Tagged: mcp

← Back to AI Blog

10 min read

The server was archived, the install still worked

Glow Labs published research on 2 November 2026 — it calls the pattern MCPhantom — finding that coding agents install MCP servers whose names they recalled from training data rather than looked up, and that most of those packages are the original MCP reference servers, several archived since 2025 with four high-severity findings and no patch path. The transferable point is not the vulnerabilities. It is that a lockfile pins versions of dependencies you declared, and this dependency was never declared: a name came out of the model, npx resolved it, and a process now holds your filesystem and your tokens. Every control you already own sits on the wrong side of that step.

8 min read

The project file was open, not uploaded

At MAX on 10 November 2026 Adobe previewed local MCP integrations that let an outside agent act inside Photoshop, Illustrator, Premiere and After Effects, editing native project files on the user's own machine and keeping the layers, vectors, bins and sequences editable. Availability is private beta in early 2027, so there is nothing to install — but the shape is the news: when the MCP server is a running GUI application, the agent's subject is the document that happens to be open, not a path you can allowlist, and the upload step that was quietly carrying your DLP, your audit trail and your undo disappears. Decide now what the unit of permission is, because it is no longer a file.

10 min read

The lockfile arrived for the prompt

Microsoft's APM gives agent configuration content hashes, transitive resolution, drift detection and SBOM export — and its README says why: "Agent context is executable in effect — a prompt is a program for an LLM." The analogy stops where it matters. A hash pins a file; behaviour is a property of the composition of prose, model, tools and permissions, which no lockfile describes. APM makes agent context auditable, not safe, and one install writes into every one of the nine harnesses you listed.

13 min read

MCP Apps vs A2UI vs AG-UI vs OpenAI Apps SDK

Three of these four are not competitors, and picking by feature list gets you the wrong one. They split on a single fact — whether executable code crosses the wire — and that fact, not any feature, decides which surfaces your interface can ever appear on. The genuine either/or is MCP Apps against A2UI: an HTML document in a locked-down iframe, or a declarative component list the client draws with widgets you do not control.

8 min read

The session ID was a command-line flag

CVE-2026-96620 scores 9.2 because of which flag got injected, not because a string reached a shell. The Python Claude Agent SDK forwarded its resume option into the Claude CLI unvalidated, so a session ID beginning with a hyphen became argv — and the reachable flag was --mcp-config, which does not run one command but mounts a tool the model can keep calling. Argument injection into an agent harness is a permission edit that lands upstream of the permission system.

13 min read

llms.txt vs NLWeb vs WebMCP vs a remote MCP server

Four ways to make a website usable by agents, and three of them ask you to publish a surface whose consumer is still hypothetical. A server-log analysis of about 137,000 domains found 97% of llms.txt files were never fetched; WebMCP is a W3C community-group draft behind a Chrome flag; NLWeb has infrastructure backers and flat adoption. Pick by who provably reads it, and by whether the agent needs to read, ask or act — because only one of the four gives you a caller you can identify and revoke.

9 min read

GitHub's MCP server paginated from day one and still overflowed the context window

Pagination bounds how many records come back; the context window is a budget of tokens. GitHub's server kept overflowing at 30 records a page until minimal response types cut project items by 93%, Datadog moved to token-budget pages for the same reason, and because MCP paginates the tool catalog but not the tool call, every host handles the overflow differently.

10 min read

The passport stops at your perimeter

ServiceNow announced AI Passport on 15 October 2026: a cryptographically signed credential, issued from its control tower, that agents and MCP servers check at runtime to establish what they may do. The prevention claim holds exactly as far as the issuer's own enforcement points reach, and an agent's most consequential calls leave them. What the credential durably buys is different and underrated — a binding between an action and the approval that authorised it, recorded as the action happens rather than reconstructed afterwards.

10 min read

The front door closed; the MCP server did not

Amazon, Yelp, Delta, JPMorgan and Schwab all shut third-party AI agents out within four weeks, and every one of them left a different door open. Schwab published both halves of the rule on its 14 October earnings call: agents arriving with a client's password are blocked, while outside models may read balances and research through Schwab's own MCP servers and may not move money. What is being refused is not automation and not AI — it is credential delegation, which no bot-identity standard can fix, because an agent holding the user's password is indistinguishable from the user by design.

10 min read

The token came with the tool list

Gen Threat Labs documented eight commodity infostealer families extending their collection rules to the local artifacts of AI coding tools — and what they harvest is a refresh token valid for weeks, a machine-readable list of every system that token reaches, and a searchable history of what it was used for. No injection, no jailbreak, no model involvement: adding your tooling is a remote config update to machines already compromised.

10 min read

A dropped subscription looks exactly like a quiet week

OpenAI shipped plugin automations on all plans on 29 September 2026 against MCP Events — a draft with no SEP number, in a repository whose README calls its contents exploratory. The draft gets the webhook hardening right and makes the two envelopes that report absence optional, so a revoked permission, a lost buffer and a genuinely quiet upstream all reach your agent as the same empty stream.

10 min read

Safari MCP vs Chrome DevTools MCP vs Playwright MCP vs extension agents

Tool counts decide nothing here. The axis that determines both whether a browser agent can do the job and how bad a hostile page gets is which session it holds — an isolated automation context, a dedicated profile quietly accumulating logins, or your own signed-in browser. Both browser vendors that shipped an MCP server this year deliberately kept your own session out of it, which is why neither does the agentic-shopping demo everyone expected.

11 min read

Four reads and one write — Google Home MCP gated the half nobody was worried about

Google blocked the thing everyone asked about: an agent connected through Home MCP cannot unlock your door. But four of the five tools are reads, and list_home_history hands a third-party agent a queryable record of motion, presence and door events over any window — with no equivalent gate, because nobody has written down what a sensitive read is. Actuation is bounded, legible and reversible. The read side is none of those.

9 min read

Context7 vs DeepWiki vs GitMCP vs Ref: your agent’s documentation is somebody else’s index

Four MCP servers exist to stop a coding agent writing code against an API it half-remembers, and all four work. The axis that decides whether they help is what kind of text comes back: upstream files, snippets extracted from upstream, or prose a model wrote about the code. And none of them closes the failure they are sold against — your agent still does not know which version you run, because none of them reads your lockfile and one of them makes the version a sentence in the prompt.

9 min read

WebMCP makes your page an API, and the session is the only auth it has

WebMCP lets a page hand an AI agent a list of callable tools, and Chrome is shipping it behind a flag while the W3C community group draft is still moving. The part worth arguing about is not discovery but authority: a registered tool executes as your page's own JavaScript, inside the session the logged-in user already established, so your server sees a request it cannot distinguish from a click. You are publishing an API whose only credential belongs to someone who is not the caller.

9 min read

An account toggle is not a power of attorney

On 4 September Docusign said its MCP server opens to every agent on 30 September — Claude, ChatGPT, Gemini, Copilot, Slack, any MCP client — governed by account-level admin controls. The law has allowed an automated agent to bind its principal since 1999, on one condition: the act must be attributable to that person. A per-account toggle attributes a class of acts, which is what carried deterministic scripts and is exactly what a model that negotiates strains. Closing that gap is the deployer’s job, and nothing in MCP does it for you.

10 min read

FastMCP vs the TypeScript SDK vs mcp-go vs rmcp: who negotiates the revision for you

These four are benchmarked on throughput, which is a 1.9 ms spread inside a 50–500 ms upstream call — and ranked on it while the axis with a date attached goes unmeasured. Three of the four implement the 2026-07-28 stateless revision and the most-used Go library does not, but the sharper question is which of them absorbs your dual-revision window instead of turning it into your topology.

11 min read

agentgateway vs ContextForge vs Obot vs Docker MCP Gateway: whose identity reaches the server

The MCP specification settles the negative — as of revision 2026-07-28 a server MUST NOT pass through the token it received from its client — but leaves RFC 8693 token exchange on the roadmap, so four gateways answer the question four different ways. agentgateway and ContextForge exchange the token; Obot attaches the user’s stored upstream token and is mid-migration between the two; Docker MCP Gateway has no user concept at all, which is honest for a workstation and disqualifying for a fleet. Pick on that axis, and notice that Docker’s isolation story is the best of the four on an axis the others do not compete on.

9 min read

A2A Moved In With MCP. The Identity Layer Stayed Outside.

On 20 August Google moved A2A into the Agentic AI Foundation, so both protocols in the standard agent stack now share a board, a roadmap and a trademark holder. What they still do not share is a delegation primitive — and the identity work that would supply one is being stewarded at a different foundation entirely.

11 min read

MCP Registry vs Smithery vs Docker MCP Catalog vs PulseMCP: four indexes, one missing signal

You can look an MCP server up in four places and get four different kinds of answer: who owns the name, who will host it, who built the image, and what exists at all. Only one of them makes a claim about the artefact you are about to run — and none of them has read the tool descriptions, which is where an MCP server actually attacks you.

9 min read

MCP went stateless, and the state just moved

The 2026-07-28 MCP spec deleted the initialize handshake and the session-id header, so a server can now run behind a plain round-robin load balancer. That operational win is real — but statelessness is a transport property, not a system property. The session did not disappear; its bookkeeping moved onto every request, and the durability that long-running agents actually need came back in through the AWS-contributed Tasks extension as explicit handles. Read the two together before you celebrate a simpler protocol.

10 min read

Generative UI Has Two Standards, and They Split Over Who Owns the Catalog

A2UI sends JSON and MCP Apps sends sandboxed HTML — the least consequential difference between them. One has the agent compose components you own, moving the review into your design system; the other installs an interface someone else wrote, moving it to the server boundary. Sort your surfaces by whether you can enumerate them, then pick.

10 min read

Arcade vs Composio vs Pipedream Connect vs Nango: Who Holds the User’s Token

Four platforms that stand between your agent and a user’s Gmail or Salesforce. The catalog sizes they advertise are counted in four different units and are the part you will outgrow; the token vault none of them market is the part you would hate to build. The decision you cannot retrofit is whose name is on the consent screen.

8 min read

Agent Plugins 1.0 Standardises the Bundle and Leaves Trust to Whoever Installs It

Five rival vendors agreed on a directory layout on 6 August, and explicitly declined to agree on install, distribution, permissions, sandboxing or provenance. The format makes one bundle of instructions plus credentialed tool access portable across six clients — which is exactly why the compensating controls are now yours.

11 min read

Auth0 vs Descope vs Stytch vs WorkOS: Agent Auth Is Two Products

Every identity vendor now sells “auth for AI agents”, and the phrase covers two opposite problems: letting an agent into your app, and letting your agent out to someone else’s API. Pick on direction first — and notice that a token vault holding a user’s full grant has relocated the credential rather than shrunk it.

8 min read

MCP 2026-07-28: Statelessness Was the Small Part

The 28 July specification retires the initialize handshake and the Mcp-Session-Id header, and every write-up so far has framed that as plumbing. It is not. Dropping the held-open connection forced Sampling, Roots and Logging onto a twelve-month deprecation clock — and those were the features that made an MCP client a peer rather than a caller. The protocol just settled what it is.

20 min read

Browser-Use vs Stagehand vs Skyvern vs Playwright MCP: Four Answers to How an LLM Should Drive a Web Page

When there is no API, an agent has to drive the browser itself — and four open-source projects disagree on how it should see the page. browser-use reads the DOM, Skyvern looks at pixels, Stagehand lets you dial between code and AI, and Playwright MCP is not an agent at all but the standard browser-tool layer any model can call. Picking one is really two decisions: Python or TypeScript, and a framework or an MCP server.

10 min read

MCP at 97 Million Downloads: How the Model Context Protocol Won — and What's Still Broken at Scale

Two years from Anthropic's launch, MCP isn't a debate — it's a dependency. Every frontier vendor, every major IDE, and one Pinterest team saving 7,000 engineering hours a month all ship against it. The interesting question is no longer *should you use MCP* — it's what fails at this scale and how the 2026 roadmap plans to fix it.