Co-founder @keycardai. 🛠️ @passportjs. ❤️ HTTP 401-403. #openid #oauth #wimse #mcp #x402
San Francisco, CA
Joined July 2006
- Tweets6.4K
- Following2.3K
- Followers3.2K
- Likes8.7K
This is a one-shot prompt, sent to devs on X rather than an LLM. It’ll exist shortly by virtue of tweeting it.
MCP vs CLI for LLMs is the wrong discussion. People are debating at the wrong layer.
Both work incredibly well as long as they are run through a repl like environment that can persist state. The funny thing about CLI is that CLI tools are usually accessed through BASH which happens to be a repl with persistent state (the file system), therefore cli works much better than mcp. But this isn't even close to being an intrinsic property of MCP. Just means that we need better harnesses.
Right now the best repl for this are:
- bash + fs
- jupyter kernels
- codemode type repls, usually quickjs
LLMs understand the concept of forward evolving a system to solve a need very well. This comes from the agentic RL. They understand how to change the state of a codebase or acquire data from databases and then operate on it similarly to humans. But without an execution environment, they actually cannot do this properly.
My bet? Sometime soon someone will (or has already?) create a embeddable, sqlite style mini execution environment that parses bash, typescript, or tool calls into a common IL execution plan that's easy to security check before executing. And design this specifically for durable execution environments. Then we will just connect cli, mcp, webmcp, whatever to that and it accepts any of the input modalities as they can all be represented as each other.
Jared Hanson retweeted
insane 48 hours keeps getting worse... 🤯
banks finding unauthorized AI agents inside customer accounts, some acting on their own, and execs can't tell human from agent or authorized from rogue
every agent needs identity + intent, dynamic, at runtime, scoped to the task and gone the second it's done
SCOOP: Major U.S. banks are detecting unauthorized third-party AI agents inside customer accounts, including some attempting to take actions that appear to be independent of user instructions, sources told Axios.
The findings have alarmed banking executives, who are racing to restrict access to their systems as AI moves at a velocity faster than financial institutions can respond, multiple industry and bank executives told Axios.
Several banks are now preparing for worst-case and even “day after” scenarios, including how to rapidly secure or restore customer accounts if things go wrong, the people said.
Several bank executives told Axios they're struggling to distinguish between human users and AI agents. One executive said banks also struggle to determine whether agents are authorized by customers or potentially operating without their permission, more akin to rogue agent behavior.
Read my latest for Axios here: axios.com/2026/10/22/ai-agen…
Jared Hanson retweeted
We've spent a lot of time at @KeycardAI thinking about how authentication and authorization need to evolve as agents take on more work.
API keys and OAuth scopes were never designed to account for tasks, delegation between agents, or agents acting on their own.
I wrote about how we're approaching this and what we think needs to change.
keycard.ai/blog/defining-aut…
Reading through the PACT spec tonight. The time is now to solve these problems, so it’s great to see a proposal. Unfortunately, it’s hampered by the ahead-of-time registration requirement that plagues all OAuth-based integrations. openpactprotocol.org
Jared Hanson retweeted
For years, clients have either been anonymous or pre-registered. Agents break that model.
We need a way for agents to show up on the open web, establish who they are, interact and transact, and bring a human into the loop when they need more access.
Really excited about the Personal Agent Protocol announcement today and how closely it aligns with the work we’ve been doing at @KeycardAI across MCP, A2A, AAuth, and federated agent identity.
Today we’re announcing Personal Agent Protocol — an open standard @Meta and @SierraPlatform are developing along with industry partners at @Genesys, @instinct, @RocketOTD, @Shopify, @stripe, and @Walmart. It will help define how personal agents interact with businesses and is open for anyone to implement.
Read more: sierra.ai/blog/introducing-p…
Excited to see the first published spec of Personal Agent Protocol later this month! It is right in line with what we at @KeycardAI are building with extensions to OAuth and emerging protocols like AAuth. DMs are open for anyone building services for personal AI to connect to. sierra.ai/blog/introducing-p…
OAuth is tying itself in knots trying to turn clients into federated actors. AI agents need that capability. This is why I’m excited about AAuth.
That said, much like new cloud architecture gave rise to SAML over LDAP, and web 2.0 and mobile brought OAuth and OpenID, the timing and demands of AI create the right moment where a new protocol can emerge.
LLMs can be very insightful. But their writing style (I’m looking at you Claude) can make those insights hard to follow. I often find myself rereading prior chats and noticing important bits I overlooked.
Language is both the oldest technology and the newest technology. This is what makes AI so magical, indicating its potential.
Reading Claude’s written English feels a bit like reading English from over a century ago. The same language, but yet distinctly different. Some emergent new culture shift.