111–120 of 124 posts
I am currently trying to use Microsoft Entra ID auth for an MCP server I'm implementing, and I genuinely feel like I must be an idiot. - I can use the `WWW-Authenticate` header to indicate a resource metadata URL for the client. - I can use this to indicate an authorization server (Microsoft Entra) and a scope (for the app registration that handle which app roles each user is given to differentiate different capabili…
Earlier quoted context omitted.
I’m work on a platform for restaurant reviewing with your friends, and (after a few stumbles) MCP definitely seems the way to go. Normies will not hunt down their claude directory and paste a skill file. “Connections” is something they understand, and pasting the mcp or finding it in the marketplace is easier for them. TBD if having agent access to places and reviews is helpful, hah!
"Normies" pasting in MCP sounds like a nightmare from a security perspective.
Before you get too far into the usual “MCP is dead, Skills forever” debate The real valuable capability MCP offers over skills/CLI is isolating the auth flow outside of the agent’s context window, and potentially out of the harness completely. This is valuable from a security perspective obviously. It’s also just a much easier user experience for normies and large businesses adopting AI tools. I hear all the context…
Before you get too far into the usual “MCP is dead, Skills forever” debate The real valuable capability MCP offers over skills/CLI is isolating the auth flow outside of the agent’s context window, and potentially out of the harness completely. This is valuable from a security perspective obviously. It’s also just a much easier user experience for normies and large businesses adopting AI tools. I hear all the context…
Is that really a thing? Everything on the other side of the MCP boundary (at least how I'm using it) is deterministic and about 100x faster (not to mention safer) than inference.
Before you get too far into the usual “MCP is dead, Skills forever” debate The real valuable capability MCP offers over skills/CLI is isolating the auth flow outside of the agent’s context window, and potentially out of the harness completely. This is valuable from a security perspective obviously. It’s also just a much easier user experience for normies and large businesses adopting AI tools. I hear all the context…
> the usual “MCP is dead, Skills forever” debate Is that really a thing? Everything on the other side of the MCP boundary (at least how I'm using it) is deterministic and about 100x faster (not to mention safer) than inference.
It might use the view_pr tool, or `gh pr view`, but in the end it's still performing a deterministic action.
The benefit might be that the GH skill can contain more domain specific information about GitHub, and you only pay the context cost when the skill is read.
Personally I generally avoid MCP and have skills for CLIs -- if one doesn't exist, then I author one. For example I have a CLI for Grafana, Discord, Sentry, etc.
https://github.com/shepherdjerred/monorepo/tree/main/package...
Before you get too far into the usual “MCP is dead, Skills forever” debate The real valuable capability MCP offers over skills/CLI is isolating the auth flow outside of the agent’s context window, and potentially out of the harness completely. This is valuable from a security perspective obviously. It’s also just a much easier user experience for normies and large businesses adopting AI tools. I hear all the context…
I think that this extension points out other benefits to MCP over skills: * centralized control * ease of use for employees * auditing/compliance * deployment model It seems the state of the art for deploying skills is "copy this file and put it in this place" or "check out this repo and add a symlink" or "run this slash command to install the skill". (I'm not aware of any solution that pushes skills out.) These opti…
Earlier quoted context omitted.
> the usual “MCP is dead, Skills forever” debate Is that really a thing? Everything on the other side of the MCP boundary (at least how I'm using it) is deterministic and about 100x faster (not to mention safer) than inference.
Skills can be about as deterministic. Consider GitHub MCP vs skill for GH CLI. It might use the view_pr tool, or `gh pr view`, but in the end it's still performing a deterministic action. The benefit might be that the GH skill can contain more domain specific information about GitHub, and you only pay the context cost when the skill is read. Personally I generally avoid MCP and have skills for CLIs -- if one doesn't…
Earlier quoted context omitted.
> the usual “MCP is dead, Skills forever” debate Is that really a thing? Everything on the other side of the MCP boundary (at least how I'm using it) is deterministic and about 100x faster (not to mention safer) than inference.
Skills can be about as deterministic. Consider GitHub MCP vs skill for GH CLI. It might use the view_pr tool, or `gh pr view`, but in the end it's still performing a deterministic action. The benefit might be that the GH skill can contain more domain specific information about GitHub, and you only pay the context cost when the skill is read. Personally I generally avoid MCP and have skills for CLIs -- if one doesn't…
No its providing a deterministic output. The action it takes is still not determistic, right, since it can be either of the two options.
I don't see the benefit or even the point of "more domain specific knowledge" in a skill especially for the example you shared.
Earlier quoted context omitted.
Skills can be about as deterministic. Consider GitHub MCP vs skill for GH CLI. It might use the view_pr tool, or `gh pr view`, but in the end it's still performing a deterministic action. The benefit might be that the GH skill can contain more domain specific information about GitHub, and you only pay the context cost when the skill is read. Personally I generally avoid MCP and have skills for CLIs -- if one doesn't…
Claude Code uses gh cli just fine without any skills.
With a proper skill it can one-shot even complex commands that require poking to gh api because the basic command set doesn't work. Or it knows how to track a running CI workflow efficiently without having to try three different methods.
Source: I daily drive Claude + gh cli.