# Runsite MCP server — let your agent deploy > Connect Claude Code, Cursor or another MCP client to Runsite. Your agent gets 22 tools to read logs and deploy, limited to the scope of the API key you give it. 1. [Home](/) 2. [Tools](/tools) 3. MCP server MCP v0.1.0 · 22 tools # Your agent can deploy what it just wrote Point an MCP client at one hosted endpoint and it can read your services, follow a failing build to the line that broke it and ship the fix. You don't install or run anything. The agent works with an API key you scope yourself, and secrets stay in the dashboard. `https://mcp.runsite.app/mcp` Authorization: Bearer ak\_live\_… [Read the docs](https://docs.runsite.app/mcp/overview)[Create an API key](https://dashboard.runsite.app/settings/api-keys) agent — runsite mcp 22 tools get_service_health api degraded · last deploy failed 4m ago get_deployment api dp_5c1e build log: missing STRIPE_SECRET_KEY set_env api ["STRIPE_SECRET_KEY"] approval ap_8f21 — you enter the value deploy api wait=true running · 2 instances · healthy Every call is made as the owner of the API key you gave it — nothing wider ## Point a client at it Create a key in the dashboard, drop it into the client you already use, and the tools appear in its next session. The server speaks Streamable HTTP and keeps no state between calls. terminal ``` claude mcp add --transport http runsite \ https://mcp.runsite.app/mcp \ --header "Authorization: Bearer $RUNSITE_API_TOKEN" ``` Reads the key from your shell, so it never lands in a config file. Run \`/mcp\` in Claude Code to confirm the connection. ## What the agent can reach Every tool takes a service name or its id, and acts as the owner of the key you handed over — never wider. The scope beside each name is what a key needs before the tool appears in its list at all. ### Look around What exists on the account, and how it is configured. `whoami`read The account this key belongs to and what it may do `list_projects`read Projects on the account `list_services`read Every web service with its status, plan and public URL `get_service`read Repository, branch, instances and status of one service `list_env`read Variable names on a service — values are always masked `list_databases`read Managed Postgres and Valkey in the workspace `get_database`read One database and its usage; connection URLs are never returned ### Find out what broke Enough context to diagnose a service without opening the dashboard. `get_service_health`read Status, resource usage, last deployment and error lines in one call `get_logs`read Recent container output, capped at 200 lines and 8 KB `get_metrics`read CPU, memory and instance count, with the trend over a period `list_deployments`read Recent deployments with status, commit and duration `get_deployment`read One deployment, plus the build log tail when it failed ### Ship the fix The same lifecycle actions the dashboard performs. `deploy`write Build and release the current commit; wait=true polls until it finishes `restart`write Roll the running containers without rebuilding `start`write Start a stopped service from its existing image `stop`write Stop a service and release its compute; env and disks are kept `create_service`write Create a service from a repository on a connected git provider ### Ask you first Nothing here changes anything until you answer in the dashboard. `set_env`write Request environment variables by name; you type the values `set_secret`admin The same request for project secrets `rollback`write Request a return to an earlier deployment `delete_service`admin Request a deletion, which cannot be undone once approved `check_approval`read Whether you approved, rejected or let the request expire ## Hand over as little as you like A key carries one scope, and the server filters the tool list to match it before the agent ever sees it. Start with a read key while you get a feel for what an agent does with your account, and revoke it in the dashboard the moment you want it to stop. | Scope | Tools | What it allows | | ----- | -------- | -------------------------------------------------------------------------------------- | | read | 13 of 22 | Inspect services, logs, metrics, deployments and databases. Nothing changes. | | write | 20 of 22 | Everything above, plus deploy, restart, stop, create a service and request a rollback. | | admin | 22 of 22 | Everything above, plus requesting project secrets and the deletion of a service. | An agent that loops gets 60 tool calls per minute per key and a refusal after that, so a bad retry loop costs you a minute rather than a bill. ## Secrets stop at the dashboard An agent can tell you a service needs a Stripe key. It cannot be the one holding it. Anything that sets a value, rolls a service back or deletes it goes through the same three-step handshake. 1. 1 ### The agent asks It names the keys it needs set. The values are not part of the request, so there is nothing for the agent to guess or leak. `set_env("api", ["STRIPE_SECRET_KEY"])` 2. 2 ### You answer in the dashboard The tool returns a link and an approval id. You type the values in the dashboard and approve, or reject. Unanswered requests expire. `dashboard.runsite.app/approvals` 3. 3 ### The agent reads the outcome Polling returns pending, approved, rejected or expired — and only that. The value you entered is never sent back to the agent. `check_approval("ap_8f21") → approved` The rest of the surface follows the same rule: `list_env` masks values, `get_database` never returns a connection URL, and logs come back capped at 200 lines so a transcript cannot quietly swallow your whole output. ## Resources and prompts Clients that prefer to attach context rather than call a tool can read the same data as a resource. The two prompts are the routines worth having written down: diagnosing a service, and shipping a change without declaring victory too early. ### Resources `runsite://services` Every web service on the account as JSON, for clients that read resources instead of calling tools. `runsite://service/{id}` One service as JSON, the same shape the dashboard reads. ### Prompts `diagnose_service` Walks the agent through health, deployment, resources and dependencies, and tells it to change nothing. `deploy_and_verify` Deploys, waits, checks health, and asks you before rolling anything back. FAQ ## Frequently Asked Questions Common questions about this service. ### Which clients can connect? Any MCP client that speaks Streamable HTTP and lets you set an Authorization header — Claude Code, Cursor and VS Code are covered by the snippets above. Clients that only launch stdio servers can reach the same endpoint through the mcp-remote bridge. ### Where do I get the API key? In the dashboard under Settings → API keys. Give the key the smallest scope that covers what you want the agent to do: read for inspection only, write to let it deploy and restart, admin only if it needs to request secrets or deletions. Keys can be revoked at any time, which cuts the agent off immediately. ### Can the agent read my secrets? No. list\_env returns variable names with masked values, get\_database never returns a connection URL, and set\_env and set\_secret only carry key names — you type the values in the dashboard. Nothing in the tool surface returns a credential. ### What happens if the agent gets stuck in a loop? The server allows 60 tool calls per minute per API key and refuses the rest with a message telling the agent to wait. Your plan quotas still apply on top of that, so a runaway agent cannot deploy its way past them. ### Do I have to install or run anything? No. The server is hosted at https://mcp.runsite.app/mcp and holds no state between calls — it validates your key against the Runsite API on each request and acts as the owner of that key. There is nothing to update when tools are added. ### Does the agent see tools it is not allowed to use? No. The tool list itself is filtered by the scope of your key, so a read key advertises 13 tools and no deploy tool at all. A call to something outside the scope is refused with an explanation of which scope it would need. ## Your app deserves to be online €5 of credit on signup. Deploy in under a minute. No credit card needed. [Start deploying](https://dashboard.runsite.app/login)[View documentation](https://docs.runsite.app) --- Source: https://runsite.app/tools/mcp