#general
Hello everyone 👋
I see the roles/persmissions are defined at the archestra dashboard level, over what an user is able and not able to do. Is there a way, I can get it more workflow levels, for example, APIs for disabling access for a user to A2A Gateway or MCP Gateway or LLM Gateway?
hey looking to join a team, ping me
Hi team! :rotating_light:
Quick question about MCP Gateway tool policies:
I've set
agent-mesh-tools__docker_status to *"Blocked"* in the Tool Policies page, but when I call it through the MCP Gateway, it still executes successfully.*Setup:*
• Gateway:
dac6e444-f791-423b-b724-4df4edae8182• Profile: Default Profile
• Using Authorization Bearer token
• Endpoint:
localhost:9000/v1/mcp/{gateway-id}*Expected:* Policy violation error
*Actual:* Tool runs normally
Is there an additional step needed to enforce policies? Or should policies only apply to LLM Proxy calls, not direct MCP client calls?
Screenshots attached showing the blocked status in UI.
Thanks!
2fast2mcp submission channel?
will all participants get certificates?
Can anyone tell what exactly to build in the #2Fast2MCP hackathon?
@user
when using archestra, (e.g. in the archestra-openclaw example docker setup), do you always get the dual-llm-injection-prevention out of the box for every single request?
Hello everyone! Im finding my way around Archestra, its the first time Im using a tool like this. I wanted to install a Google Workspace MCP server, but I'm facing some issues. Is it supported?
I see MCP servers have recommended protocol of OAuth2.1. But if I were to try adding it to Archestra set up using Add MCP Server to the Private Registry, and select OAuth2.0; will the auth work as usual?
Hi everyone !
I'm a beginner in AI but strong in MERN full stack
Looking for teammates & simple project ideas.
Excited to learn
when you run the archestra/platform docker container, it seems to auto-start another container, kindest/node:v1.35.0, for the mcp control plane. this is an "interesting" pattern. i prefer having all my containers defined in docker-compose
New release! 🚀🚀🚀
1.0.42 (2026-02-10)
Features
Bug Fixes
- cleanup stale sessions and fix catalog config comparison (#2701) (952f431)
- detect "session not found" and retry with fresh session (#2703) (7d9eee6)
- detect stale session with ping (#2705) (7379620)
- revert organization logo preview when upload fails (#2680) (34e61d6)
Miscellaneous Chores
Hi team — quick question about A2A agents.
I’m calling an agent via A2A (
/v1/a2a/{agentId}) and the request reaches the agent, but execution fails with:“LLM Provider API key not configured. Please configure it in Chat Settings.”
I already added an API key in Chat Settings and MCP tools are working fine.
Do A2A agents require a separate provider/model binding in the Agent config itself?
Thanks 👍
Hello @everyone, this is Oswald. I’m currently an undergraduate student, but I already have some experience working with a Simple MCP Server.
I would really appreciate some guidance on how to get started here, because many of the terms being used feel quite technical to me.
👋 Hi everyone, I’m Tushar. Looking forward to hacking together and learning from you all. Great to meet the community!
:halo_wave:1
Hi everyone, I’m Rahul . Looking forward to hacking together and learning from you all. Great to meet the community!
Can we use an model that we have downloaded locally with ollama
and if yes, then can you guide me
Hello! I am trying to chat with my LLM, but it tells me "LLM Provider API key not configured. Please configure it in Chat Settings".
I have already configured a Mistral API key in the settings but it still throws me this error.
I checked the logs and it looks like its using Anthropic API by default. Is there a way to fix this?
Hi archestra team, Archestra Docker quickstart fails on Windows with 'failed to create KinD cluster, kubelet not running'. Any workaround?
Hello everyone,👋
Myself Harsh, a first-year undergraduate student.
I’m excited to participate in this hackathon and collaborate with the community.
I’m open to joining a team and eager to learn, contribute, and grow through this experience.
Looking forward to working with you all.
I watched the stream recording for Archestra, and it was actually great. By the way, what projects are you all working on?
I am using archestra ai's MCP and Agent in my project. So in the submission page it's asking for deployment project link.
Locally i can deploy the agent and MCP servers through archestra development method. So my question is how can i use MCP server and agents through archestra after i deploy my project online? As archestra is not hosted for public that i can use it's api
I've tried deploying Archestra on render.com, but it turns out I cannot expose both :3000 or :9000 ports for admin UI and API access simultaneously. Is there a work around to this?
Is there a way (a API) that where I can get the current logged in user details? such as email address? or any identifier?
Hello @user@user
I’m trying to run Docker quickstart, but it fails with the error “Unable to create a Kind cluster.”
I’ve already enabled Kubernetes in Docker Desktop and restarted it.
The issue still persists even after multiple attempts since yesterday..
👋 Hi everyone! where is the problem statement for the hackathon?
Hello. I am trying to follow the example in the quickstart
But I get errors when I try to install playwright mcp
These are the docker logs:
👀2
7 repliesFollowing the documentation, a basic
/health api endpoint works. But if try to GET /api/organization I see:I'm using the API key at: Settings > Your Account > API Keys > Create API Key
cURL-H 'Authorization: Bearer archestraredactedAMHqcbsPG'```
Is there something I'm missing?
Can I create a user in Archestra programmatically? I was assuming making a POST call to /api/teams/{id}/members woudl also create members
Is it even possible
Team, reading the channel and can't be more excited to see what you're building. 🚀 🚀 🚀
❤️6☺️1
this error is usually caused by insufficient Docker memory/resources on Windows.
but i tried in Ubuntu Wsl, still got the error
try using github codespaces, that might work.
I have ubuntu
Hi is any other way to deploy the application just the chat bot or agents part not deploying the whole application
Hi team, I've been stuck on this for a while. Here's my issue.
I've an agent called "head" that assigns work to other subagents each responsible for certain MCP tooling. There subagents are working perfectly and I have no qualms with their chats or their MCP tooling.
Now, when I try to go to "head" and send a message to try and use the subagents, it throws an error.
{"code":"unknown","message":"An unexpected error occurred. Please try again.","isRetryable":false,"originalError":{"provider":"cerebras","message":"Error: LLM Provider API key not configured. Please configure it in Chat Settings.","type":"Error","raw":{}}}
For additional context, keys are already configured in the following places -> the main settings, each agent setting also has the API key selected (including "head" itself).
Remediation tried -> docker restart, change API keys, clear out the cache, check env, do the whole thing again from scratch.
Am I using subagents wrong? As per my general understanding of subagents this is how it's supposed to be. There is nothing to say otherwise in the docs as well.
Of course, I can get my project to work by putting all the tools in a single chat (and it does) but that doesn't fully calm my curiosity. Appreciate what you guys do, cheers.
Have a look
Hi Archestra team — I’m running archestra/platform:latest via Docker and hitting an error when trying to create a Personal Token and call an A2A agent endpoint.
Issue: Personal token creation fails and A2A auth doesn’t work.
Error returned:
{
"jsonrpc": "2.0",
"id": 1,
"error": {
"code": -32603,
"message": "Failed query: insert into \"usertoken\" (\"id\", \"organizationid\", \"userid\", \"name\", \"secretid\", \"tokenstart\", \"createdat\", \"lastusedat\") values (default, $1, $2, $3, $4, $5, default, default) returning \"id\", \"organizationid\", \"userid\", \"name\", \"secretid\", \"tokenstart\", \"createdat\", \"lastusedat\"\nparams: default-org,system,Personal Token,7aff233b-0062-4f29-9464-74d09078023a,archestra81fa"
}
}
⚠️ Quick Announcement ⚠️ Update to version 1.0.43 if you had issues with calling subagents from the parent agent.
We’ve fixed the issue when calling subagent from parent agent resulted in
LLM Provider API key not configured. Please configure it in Chat Settings error.Thanks everyone for reporting this bug!
🚀4❤️1🙌1
Hi team — I'm testing an A2A *sub-agent* locally and getting an empty response from message/send.The request succeeds and returns a messageId, but parts.text is empty in the result.
Endpoint:
<http://localhost:9000/v1/a2a/333c740d-7abe-4c8e-b624-17f7dc4beb46>I’m attaching a screenshot of the request/response.
Is there any additional config or step required for sub-agents to return text output?
Response:
{
"jsonrpc": "2.0",
"id": 1,
"result": {
"messageId": "msg-1770910322166-4ok4ag8",
"role": "agent",
"parts": [
{
"kind": "text",
"text": ""
}
]
}
}
We are trying to configure archestra with ollama llm but we are getting an error, any idea how to resolve this
Getting this error when trying to add any mcp in the mcp registry
Read-only live mirror of Archestra.AI Slack
👋Join the discussion withAI enthusiasts!