News for hackers. Stuff that matters.
Re:New tools for building agents by zellyn on Tuesday March 11, 2025 @02:09PM (#43335371)
Notably not mentioned: Model Context Protocol https://www.anthropic.com/news/model-context-protocol
Re:New tools for building agents by nilslice on Tuesday March 11, 2025 @02:25PM (#43335535)
not implementing doesn't mean its not supported https://github.com/dylibso/mcpx-openai-node (this is for mcp.run tool calling with OpenAI models, not generic)

but yes, it's the strongest anti-developer move to not directly support MCP. not surprised given OpenAI generally. but would be a very nice addition!

Re:New tools for building agents by benatkin on Tuesday March 11, 2025 @02:58PM (#43335863)
DeepSeek doesn’t seem to support it either FWIW. Maybe MCP is just an Anthropic thing.
Re:New tools for building agents by nilslice on Tuesday March 11, 2025 @08:50PM (#43338826)
It is not only an Anthropic thing, and it works with any model that supports function calling, which DeepSeek did not when it first launched. That probably has changed since, but I haven't looked!
Re:New tools for building agents by benatkin on Tuesday March 11, 2025 @09:48PM (#43339172)
I don't like it. I don't like the OpenAI API all that much either but at least it's lightweight. I think MCP would fit better on mcp.anthropic.com to go along with their email address [email protected] at the bottom of https://modelcontextprotocol.io/

I wish they'd done a smaller launch of it and gather feedback rather than announcing a supposed new standard which feels a lot like a wrapper.

This here is atrocious https://github.com/modelcontextprotocol/quickstart-resources... It includes this mcp PyPI package which pulls in a bunch of other PyPI dependencies. And for some reason they say "we recommend uv". How is that related to just setting up a tool for an AI to use?

Compare that to this get weather example: https://api-docs.deepseek.com/guides/function_calling/

It makes me not want to use Claude/Anthropic.

Re:New tools for building agents by burningion on Wednesday March 12, 2025 @09:44AM (#43343197)
That example code on DeepSeek doesn't actually include the logic to call a weather API? It just puts a fake answer back in, and you've got to handle the process manually.

The pyproject.toml in the Model Context Protocol example is just showing the new, "best" way to distribute and install Python projects and dependencies. If you haven't used uv before, it makes working with Python projects substantially better.

The Model Context Protocol server lets the model autonomously use the tool and incorporate its result. It's a much cleaner (imo obviously) separation of tool definition and execution.

Re:New tools for building agents by dgellow on Tuesday March 11, 2025 @03:32PM (#43336165)
Do you have experience with MCP? If yes, what do you think of it?
Re:New tools for building agents by singularity2001 on Tuesday March 11, 2025 @07:20PM (#43338173)
not OP but giving Claude access to local files / emails / database / terminal was … futuristic! (until I hit their stupid request limit)
Re:New tools for building agents by consumer451 on Tuesday March 11, 2025 @09:32PM (#43339081)
I have been using Windsurf+Sonnet for a couple months, and recently adding Supabase MCP was a total game changer for velocity. I can't believe I waited so long to configure that.

Querying schema from prompt is great, but also being able to say "I cannot see the Create Project button on the projects list screen. Use MCP to see if user with email [email protected] has the appropriate permissions" is just amazing.

Re:New tools for building agents by smcleod on Tuesday March 11, 2025 @07:21PM (#43338176)
It's great! Easy to work with, makes it quick to build tools and isnt over complicated.
Re:New tools for building agents by knowaveragejoe on Tuesday March 11, 2025 @02:57PM (#43335845)
You can (somewhat) bridge between them:

https://github.com/SecretiveShell/MCP-Bridge

Re:New tools for building agents by esafak on Tuesday March 11, 2025 @02:50PM (#43335778)
How do they compare?
Re:New tools for building agents by cowpig on Tuesday March 11, 2025 @06:25PM (#43337769)
MCP is a protocol, and Anthropic has provided SDKs for implementing that protocol. In practice, I find the MCP protocol to be pretty great, but it leaves basically everything except the model parts out. I.e. MCP really only addresses how "agentic" systems interact with one another, nothing else.

This SDK is trying to provide a bunch of code for implementing specific agent codebases. There are a bunch of open source ones already, so this is OpenAI throwing their hat in the ring.

IMO this OpenAI release is kind of ecosystem-hostile in that they are directly competing with their users, in the same way that the GPT apps were.

Re:New tools for building agents by esafak on Tuesday March 11, 2025 @06:38PM (#43337866)
Thank you. Which open source ones do you recommend?
Re:New tools for building agents by cowpig on Tuesday March 11, 2025 @07:23PM (#43338196)
Here's a fairly comprehensive list:

https://github.com/slavakurilyak/awesome-ai-agents

CrewAI is a popular VC-backed one, but two that I think are kind of interesting in the open source space are:

https://github.com/i-am-bee/beeai-framework

https://github.com/lastmile-ai/mcp-agent

... However I think the vast majority of "AI Agent" use-cases in practice right now are actually just workflows, and imo dify is great for those:

https://github.com/langgenius/dify

[edit] worth mentioning [langfuse](https://github.com/langfuse/langfuse), which is more like a platform that addresses the observability/evals/prompt management piece of the puzzle as opposed to a full-on "agent framework". In practice I have not yet run into a case where I needed something like what OpenAI just released, nor crewAI etc (despite it feeling like those cases may be coming)

Re:New tools for building agents by esafak on Wednesday March 12, 2025 @04:06PM (#43347148)
Thanks. mcp-agent lacks tests so I'm skipping it for now: https://github.com/lastmile-ai/mcp-agent/tree/main/tests

I also see there's https://ai.pydantic.dev/ but it lacks MCP support. The MCP site maintains a nice client list:

https://modelcontextprotocol.io/clients#feature-support-matr...

Re:New tools for building agents by TeeWEE on Wednesday March 12, 2025 @04:29AM (#43340962)
Correction: the MCP is a protocol for function calling and getting context into a model. It’s can run locally or over a network.

It does not specify how “agentic” systems interact with each other. Depending on what you mean there.

Re:New tools for building agents by cowpig on Wednesday March 12, 2025 @12:54PM (#43345208)
People are using the word "agentic" to mean this, I think. But yeah it's a dumb, overloaded primarily marketing word. I keep going back and forth on whether I should use the word "agentic"/"agent" at all
Re:New tools for building agents by thenameless7741 on Tuesday March 11, 2025 @06:52PM (#43337976)
it's mentioned in the main thread: https://nitter.net/athyuttamre/status/1899511569274347908

> [Q] Does the Agents SDK support MCP connections? So can we easily give certain agents tools via MCP client server connections?

> [A] You're able to define any tools you want, so you could implement MCP tools via function calling

in short, we need to do some plumbing work.

relevant issue in the repo: https://github.com/openai/openai-agents-python/issues/23

Re:New tools for building agents by koconder on Wednesday March 12, 2025 @12:35PM (#43344993)
100% but this is not the same thing, nor is this going to replace the agent SDK (or visa versa). Agents will always need some form of communication protocol, if we look at the world and agentic frameworks its a sea of logos and without some forms of open standards this would be hard.

I'm currently at Comet and I have personally worked on MCP implementations AND have made some contributions to Agent SDK in the form of a native integration and improvement to test suite.

- https://github.com/comet-ml/opik-mcp

- https://github.com/openai/openai-agents-python/pull/91

Our recent integration shipped on day 1:

- https://www.comet.com/docs/opik/tracing/integrations/openai_...

I think the key to what OpenAI is pushing towards is simplicity for developers through very easy to use components. I won't comment on the strategy or pricing etc, but on first glance as a developer the simple modular approach and lack of bloat in their SDK is refreshing.

Kudos to the team and people working on the edge to innovate and think differently in an already crowded and shifting landscape.