#general
Jul 23July 24, 2026
Hii Irfan here from India Comp Sci Grad with specialization in AI/ML and currently working as a data analytics and also exploring agents, MCP etc
Hi everyone! π
I'm Gitansh Kapoor from New Delhi, India, currently working as a Platform Engineer.
I work across a range of technologies, including Linux, Docker, Kubernetes, Backstage, Harness, GitOps, Serverless CI/CD Platforms. I'm also actively upskilling in the AI-native era, exploring MCP, Harness tooling, Agentic Automation, AIOps, and MLOps.
I joined this hackathon to build something exciting, learn from others, and connect with fellow creators. Looking forward to collaborating, building impactful products, and making some great connections along the way! π π
If anyone would like to connect, feel free to reach out. Sharing my GitHub and LinkedIn below:
GitHub: github.com/GitanshKapoor
LinkedIn: linkedin.com/in/gitansh16k
hi team!
my app uses the slack mcp and does real work in the channel it's connected to. now how do I record that for the submission? because it's just capturing the page it's recording.
can we get an option to submit our own screen recordings? @user @user
@user, after logging into archestra ai with admin credentials we have to change the default credentials ?
Hello! I am Manul from India, working as a backend engineer since past 3 years. I have shipped RAG chatbots and developed distributed backend services at my organisation in insurance domain. I have worked in: TypeScript, Nest.js, Python. Exctied to be a part of the community and contribute!
π2
1 reply
Good morning everyone, how's your progress? π
I am facing rate_limit error , Too many requests. Please wait a moment and try again.
any quick workaround ?
Status: 429
Type: unknown_api_error
Message: Failed after 3 attempts. Last error: 429 status code (no body)
Raw Error:
{
"url": "<http://localhost:9000/v1/cerebras/0ed72c90-cea3-490b-ac3c-d04843dc2fb0/chat/completions>",
"statusCode": 429,
"isRetryable": true,
"responseBody": {
"error": {
"message": "429 status code (no body)",
"type": "unknown_api_error"
}
}
}```
Hey all, weβre having a Q&A webinar for the Hackathon participants today.
It starts in 3 hours - weβll show you hot to build an App in Archestra + answer any questions you have.
π Register here
Hey! Where is the Apps Gallery repo or form to submit my hackathon project as suggested?
Read-only live mirror of Archestra.AI Slack
πJoin the discussion withAI enthusiasts!What we have to do
5 replies
I need to see the actual message content to understand what's being asked. Based on the context, Sharath kumar kamsali is asking "What we have to do" β likely about the hackathon. Let me help with what to do for the hackathon. Hey Sharath! π For the hackathon, here's the gist: *What to build: An interactive app/tool that runs on Archestra β think of it as building something useful using MCP tools and the Archestra platform. How to get started:* 1. Check out the hackathon overview: https://archestra.ai/apps-hackathon 2. Follow the quickstart guide: https://archestra.ai/apps-hackathon/quickstart 3. Browse the technical docs: https://github.com/archestra-ai/archestra/tree/main/docs/pages The quickstart is the best place to begin β it walks you through setting up and scaffolding your first app step by step. What kind of app are you thinking of building? I can help point you to the right docs or tools. π π€ Slack Agent
How do I create MCP servers
I'll grab the latest guidance from the Archestra docs so I can point you the right way. Let me search for a tool to fetch the docs content. No fetch/curl tool is available to me, so let me point you to the docs directly with what I know. Hey! π Great question β creating MCP (Model Context Protocol) servers is at the heart of building for Archestra. Here's the high-level path: *1. What an MCP server is An MCP server exposes tools (functions the agent can call), and optionally resources and prompts. Archestra connects to these servers and lets agents invoke your tools. 2. Best resources to start - Quickstart: https://archestra.ai/apps-hackathon/quickstart β walks you through scaffolding and running your first server end to end. - Technical docs: https://github.com/archestra-ai/archestra/tree/main/docs/pages β deeper reference on configuration, tool definitions, and connection setup. - Official MCP spec/SDKs: https://modelcontextprotocol.io β the SDKs (TypeScript & Python) give you a server skeleton in minutes. 3. Rough flow 1. Pick an SDK (TypeScript or Python are the most common). 2. Define your tools β each with a name, description, and input schema. 3. Implement the handlers that do the actual work. 4. Run the server and register/connect it in Archestra. If you tell me which language you want to use and what your tools should do*, I can give you a more concrete starting point. π π€ Slack Agent
Nice, you've got the GitHub MCP Server open in VS Code! π Looks like you're set up in your
terraform project with the server ready to go. From your screenshot, here's what I can see and suggest: *What you have: - The GitHub MCP Server (v1.6.0) β it's currently installed (you can see the Uninstall / Disable buttons, so it's active). - Three tabs: DETAILS, MANIFEST, and CONFIGURATION. Next steps to actually use it: 1. Click the CONFIGURATION tab β that's where you'll set your GitHub token / auth so the server can talk to GitHub on your behalf. 2. Make sure the server is Enabled (not disabled). 3. Once configured, the tools like issue_read:get, pull_request_read:get_comments, etc. become available to your AI assistant. One thing to note from the details you're reading: that section is about lockdown mode β some tools error out or filter content if the author lacks push access to a repo. Good to keep in mind when testing. Are you trying to connect this GitHub server to your own MCP setup, or build your own MCP server* modeled on this one? Let me know your goal and I'll point you to the exact steps. π π€ Slack Agent π€ Slack Agent