Give AI agents secure access to your infrastructure and workflow. With Buddy MCP agents can run pipelines, inspect logs, deploy apps, create sandboxes, publish artifacts and manage domains. Control exactly what they can access with workspace permissions and tool scopes. Works with Claude Code, Cursor, Codex, Copilot and other MCP clients.
Hi Product Hunt!
A coding agent can fix a bug in your repository, but it usually has no access to what happens in your delivery platform. If a pipeline fails, someone still has to check the logs, rerun it, and handle the deployment.
We built Buddy MCP to give agents direct and secure access to that part of the workflow.
It works with Claude Code, Cursor, Codex, Copilot, and other MCP clients. Access can be limited by workspace, permissions, and available tool categories, so an agent only gets the capabilities you choose to give it.
We are especially interested in where teams draw the line today.
Do you already let coding agents interact with delivery workflow and infrastructure, or do they still stop at the repository?
the workspace + tool-scope split is the right call, most MCP integrations I've seen just hand over a single API key with full account access. one thing I'm curious about: if a scoped agent token gets compromised or starts misbehaving mid-pipeline, can you revoke that one token without affecting other agents or human sessions on the same workspace, or is revocation still workspace-wide today?
what about the CLI. many of us are using terminal agents like claude code or codex. is there a CLI for those cases?
When an agent triggers a run or a deploy, who shows up in the audit log - the agent, or me, because it's my token?
Congrats on the launch! Giving AI agents controlled access to real infrastructure feels like a big step beyond just code assistance. Curious — how granular can the permissions get when teams want to limit what an agent can deploy, inspect, or modify?
How granular are the permissions for AI agents? Can you limit an agent to specific pipelines, environments or actions?
Hi Hunters! 👋
I'm Paul, one of the makers behind Buddy.
We use Buddy to build Buddy, so AI access has been a part of our own workflow for quite some time.
One of the things I use it for the most is debugging failed CI builds. It allows me to check the logs from my terminal, figure out what went wrong, push a fix and run the pipeline again without jumping between various tools. The productivity boost is tangible.
The same goes for working with targets. Being able to safely run commands on them means debugging becomes part of the flow instead of a disruption.
We're excited to finally share this with all of you. Would love to hear how you're using MCP clients in your own workflows!
About Buddy AI Access (MCP) on Product Hunt
“Your agent needs more than your repo”
Buddy AI Access (MCP) launched on Product Hunt on September 15th, 2026 and earned 103 upvotes and 15 comments, placing #11 on the daily leaderboard. Give AI agents secure access to your infrastructure and workflow. With Buddy MCP agents can run pipelines, inspect logs, deploy apps, create sandboxes, publish artifacts and manage domains. Control exactly what they can access with workspace permissions and tool scopes. Works with Claude Code, Cursor, Codex, Copilot and other MCP clients.
Buddy AI Access (MCP) was featured in Developer Tools (519.7k followers), Artificial Intelligence (479k followers) and Development (6.2k followers) on Product Hunt. Together, these topics include over 210.4k products, making this a competitive space to launch in.
Who hunted Buddy AI Access (MCP)?
Buddy AI Access (MCP) was hunted by Rafal Sztwiorok. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Buddy AI Access (MCP) stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Rafal Sztwiorok