Saif Ali Shaik in #general: "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 ..." | Archestra Community

#general

Feb 9February 10, 2026Feb 11 Latest

Tuesday, February 10

Manas Dutta2:34 AMOpen in Slack

Hello everyone 👋

Saif Ali Shaik3:38 AMOpen in Slack

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?

4 replies

Shivaaganesh D4:17 AMOpen in Slack

hey looking to join a team, ping me

Pathan Aymaan6:53 AMOpen in Slack

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!

1 reply

6:55 AM

Join Slack to see the image

Priyanka9:33 AMOpen in Slack

2fast2mcp submission channel?

Priyanka9:43 AMOpen in Slack

anyone knows where can we do submissions?

1 reply

Sweta Agarwal10:51 AMOpen in Slack

will all participants get certificates?

Ayon Paul10:55 AMOpen in Slack

Can anyone tell what exactly to build in the #2Fast2MCP hackathon?

@user

1 reply

Dieter_be11:16 AMOpen in Slack

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?

4 replies

Vedant Thanekar1:15 PMOpen in Slack

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?

3 replies

Saif Ali Shaik2:11 PMOpen in Slack

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?

3 replies

Buelah Evangiline2:18 PMOpen in Slack

Hi everyone !

I'm a beginner in AI but strong in MERN full stack

Looking for teammates & simple project ideas.

Excited to learn

4 replies

Dieter_be2:22 PMOpen in Slack

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

2 replies

Archestra2:56 PMOpen in Slack

New release! 🚀🚀🚀

1.0.42 (2026-02-10)

Features

add custom vault injector (#2698) (09fa98e)
add MCP metrics/tracing (#2699) (8ecdccf)

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

deduplicate metrics sanitizeLabelKey util function (#2709) (85d82ca)
remove "Show Tool calls" toggle button from chat header (#2710) (ea9dfe0), closes #2643
rename "credential type" to "installation type" and replace radio buttons with dropdown (#2711) (950b27e)

Pathan Aymaan2:57 PMOpen in Slack

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 👍

Oswald Shilo2:59 PMOpen in Slack

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.

2 replies

Tushar Khatri3:50 PMOpen in Slack

👋 Hi everyone, I’m Tushar. Looking forward to hacking together and learning from you all. Great to meet the community!

:halo_wave:1

3:55 PM

Hi @user, Just checking the participation criteria. Besides integrating Archestra, are there any specific constraints or guidelines we should follow (e.g., required features, demo expectations, judging criteria)?

5 replies

Rahul4:14 PMOpen in Slack

Hi everyone, I’m Rahul . Looking forward to hacking together and learning from you all. Great to meet the community!

2 replies

DAKSH VERMA4:43 PMOpen in Slack

Can we use an model that we have downloaded locally with ollama

and if yes, then can you guide me

9 replies

Vedant Thanekar5:11 PMOpen in Slack

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?

Join Slack to see the image

3 replies

Rohan Sunwar6:55 PMOpen in Slack

Hi archestra team, Archestra Docker quickstart fails on Windows with 'failed to create KinD cluster, kubelet not running'. Any workaround?

7 replies

Harsh7:40 PMOpen in Slack

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.

Adnan8:06 PMOpen in Slack

Hello can someone please send the link to there website

1 reply

Read-only live mirror of Archestra.AI Slack

👋Join the discussion withAI enthusiasts!

Thread

Saif Ali Shaik3:38 AMOpen in Slack

4 replies

Dominik Broj (archestra team)5:11 AMOpen in Slack

Hey there! Atm all gateways fall under profile permissions. So if someone has profile: read, they can see all three. If they have profile: create , they can create any of them. There's no separate permission per gateway type which is something on our radar.

Saif Ali Shaik7:03 AMOpen in Slack

Thanks for responding, Dom

Got it.

Can I drop you a DM and brainstorm an feasibility of an Idea with you? Although I am doing this as part of hackathon, might be good use of your time as well.

Saif Ali Shaik6:54 AMOpen in Slack

@user - Can I modify these profile permissions through API? I don't see an appropriate API endpoint to do this? Is there a different way to do it?

Dominik Broj (archestra team)7:09 AMOpen in Slack

You can update permissions of the role via PUT /api/roles/<roleId>, for example:

  Authorization: <your-api-key>
  Content-Type: application/json

  {
    "permission": {
      "profile": ["create", "read"],
      "tool": ["read"]
    }
  }```
Here's our API reference <https://archestra.ai/docs/platform-api-reference>

and docs around access control: <https://archestra.ai/docs/platform-access-control>

✅1