Connect your coding agent
Connecting a coding agent takes two things: the seylo-mcp endpoint and a deploy token. The token is shown once, so have your client ready before you issue it.
What you need: an admin to issue the token, and a namespace that is already open to coding agents.
The connection details
Section titled “The connection details”| Endpoint | https://portal.seylo.in/api/mcp |
| Transport | MCP Streamable HTTP. One path, POST only, stateless |
| Authentication | The header Authorization: Bearer <deploy token> |
| Protocol versions | 2026-07-28, 2025-11-25 and 2025-06-18 |
The token screen shows the endpoint in its MCP endpoint field. Copy it from there.
A few things about the transport that clients notice:
- No SSE stream. A
GETto the endpoint answers405. Long-running work is followed by polling, either withoperation_statusor with a task handle. See long-running work. - No session. Seylo issues no
Mcp-Session-Id. Every request carries the token and is authenticated on its own. - Not from a browser. A request carrying a browser
Originother than Seylo’s own is refused. Coding agents send noOrigin, which is the normal case. - Only the bearer token. Seylo has no OAuth flow for this endpoint, and a user’s sign-in session is not accepted.
Issue a token
Section titled “Issue a token”-
Open the dialog.
Admin → Clusters, then Connect a coding agent on the Coding agents card. The button is disabled until some namespace is open to coding agents.
-
Fill it in.
- Label: how you will recognise this token later. Name the person or the
machine, such as
Priya's Claude Code. 1 to 80 characters. - Cluster and Namespace: only open namespaces are listed.
- Capabilities: read-only by default. Tick only what this agent needs.
Tick
deploy,rollbackandput_configonly if the agent should change the cluster. The dialog marks those three “changes the cluster”. See capabilities. - Expires in (days) and Daily deploy cap: see tokens.
- Label: how you will recognise this token later. Name the person or the
machine, such as
-
Press Issue token.
-
Copy the token now.
This is the only time Seylo shows it. Seylo stores only a hash, so nobody can display it again, including a platform admin. If you lose it, revoke it and issue another.
The token screen also shows ready-made connection commands with your token already in them. Run one while the token is still on screen.
Add it to your client
Section titled “Add it to your client”Run the command from the token screen. It has this shape:
claude mcp add --transport http seylo https://portal.seylo.in/api/mcp --header "Authorization: Bearer <deploy token>"Add --scope user to make it available in every project rather than only
the current one.
The token is stored in Claude Code’s MCP configuration. Treat that file as a secret, and don’t commit it to a repository.
The token screen also shows a command for Codex. It has this shape:
export SEYLO_MCP_TOKEN='<deploy token>'codex mcp add seylo --url https://portal.seylo.in/api/mcp --bearer-token-env-var SEYLO_MCP_TOKENCodex reads the token from the SEYLO_MCP_TOKEN environment variable each
time it runs, so the token is never written into Codex’s configuration file.
Set the variable wherever Codex runs. An export line lands in your shell
history; read -rs SEYLO_MCP_TOKEN && export SEYLO_MCP_TOKEN reads it
without echoing it instead.
Token screens before 20 October 2026 exported SEYLO_TOKEN instead. Seylo
now uses SEYLO_MCP_TOKEN for coding agents, so the deploy token does not
collide with other tools that read SEYLO_TOKEN. If you set Codex up the
old way, it keeps working. To move, set SEYLO_MCP_TOKEN, add the seylo
server to Codex again with the command above (remove the old entry first if
Codex says it already exists), and remove SEYLO_TOKEN from your shell
profile.
Seylo hasn’t tested Codex against this server. If that command doesn’t connect, configure Codex as a generic client with the values in the Other MCP clients tab.
Seylo has tested only Claude Code. Any MCP client that supports Streamable HTTP with a custom bearer header should work, but Seylo hasn’t checked any specific one. Configure it with:
- Server URL:
https://portal.seylo.in/api/mcp - Transport: Streamable HTTP. It is sometimes labelled “HTTP” in a client’s settings. Not SSE, and not stdio
- Header:
Authorization: Bearer <deploy token>
Seylo needs nothing else. Where your client keeps that header is up to the client. Prefer a place that isn’t committed to source control.
Check the connection
Section titled “Check the connection”Ask the agent to call list_targets. It should answer with exactly one target,
your cluster and namespace, the capabilities the token carries, and the
per-minute call limits:
{ "targets": [ { "cluster": "acme-dev", "namespace": "shop-dev", "capabilities": ["list_targets", "describe_target", "operation_status", "logs", "observe"], "dailyDeployCap": 20, "issuedFor": "Priya's Claude Code" } ], "callLimits": { "readCallsPerMinute": 60, "writeCallsPerMinute": 10, "writeTools": "deploy, rollback, put_config, request_secret, dashboard_propose, scrape_target_propose", "note": "Per token, rolling one-minute windows, counted separately. A refused call counts. Writes are also bounded by dailyDeployCap." }, "note": "This is the whole of your access. Other namespaces and clusters are not reachable with this token, and no tool here can change that."}A client sees only the tools its token can call. Tools for capabilities that weren’t ticked aren’t listed at all. A client may cache the tool list for up to five minutes.
If something fails, find the message on troubleshooting.