MCP Server

The Runbear MCP server is a hosted Model Context Protocol endpoint that lets an AI client — Claude Code, Claude Desktop, Cursor, and other MCP-compatible tools — read and manage the agents in your Runbear organization. Instead of clicking through the dashboard, you can describe what you want in natural language ("update the Support agent's instructions", "schedule the Standup agent for 9am") and your client makes the change through the MCP server.

This is the opposite direction from Custom MCP: there, Runbear is the client that connects out to your tools. Here, Runbear is the server that your AI client connects into to manage your agents.

Early access

The Runbear MCP server is in early access and the tool set is expanding quickly. It requires an MCP client that supports remote servers with OAuth (Claude Code, Claude Desktop, Cursor, and most modern clients qualify). Some advanced agent settings remain dashboard-only for now — see Limitations.

What you can do

From any connected MCP client you can:

Manage agents — list agents, read their full configuration, and create or update an agent's name, model, and instructions.
Edit instructions and contexts — add, update, or remove the named context blocks that make up an agent's behavior.
Connect apps and tools — search the Runbear app catalog (Notion, Slack, Stripe, Linear, and more) and attach integrations to an agent.
Set up triggers and schedules — create event-based triggers or recurring/one-time scheduled jobs, and run them on demand.
Deploy to Slack — install an agent into a Slack workspace, join channels, and go live.
Inspect runs — pull recent execution traces to debug behavior and improve your agents.

Connect

The server URL is:

https://api.runbear.io/mcp

When you add the server, your client opens a Runbear sign-in window so you can authorize access (see Authentication). After you approve, the client stores the token and you can start issuing commands.

Claude Code

claude mcp add --transport http runbear https://api.runbear.io/mcp

Run any Runbear command afterward and Claude Code will prompt you to sign in the first time.

Claude Desktop / claude.ai

Open Settings → Connectors → Add custom connector, paste https://api.runbear.io/mcp, click Connect, and complete the Runbear sign-in.

Cursor, VS Code, Windsurf, Zed, and other clients

Clients with native remote-MCP support can add the URL directly. For clients that connect through mcp-remote, use:

{
  "mcpServers": {
    "runbear": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://api.runbear.io/mcp"]
    }
  }
}

Authentication and permissions

The Runbear MCP server is protected by OAuth 2.0. Authorization is handled by Runbear's identity provider, which your MCP client discovers automatically from the server — you never paste an API key or token by hand.

Every connection is:

Tied to your user account — the server acts as you, with your permissions.
Scoped to your organization — you can only see and change agents in the org you belong to.
Revocable — disconnect the server in your client at any time.

Access is governed by least-privilege scopes:

Scope	Grants
`read:agents`	Read agents, contexts, attached tools, and triggers
`write:agents`	Create and update agents, contexts, integrations, and triggers
`deploy:agents`	Deploy agents to Slack and join channels
`read:traces`	View execution traces (requires an Admin or Owner role)

Available tools

Tools are grouped by what they manage. The catalog is growing, so your client may show additional helper tools (for example, Pipedream account resolution and trigger-component discovery) beyond the ones listed here.

Agents

Tool	Purpose
`list_agents`	List the agents in your organization
`get_agent`	Read an agent's full configuration (model, instructions, contexts)
`create_agent`	Create a new agent
`update_agent`	Update name, description, model, max tokens, or system instruction
`get_personal_agent`	Read your personal agent

Instructions and contexts

Tool	Purpose
`list_contexts`	List the named context blocks attached to an agent
`create_context`	Add a new context block
`update_context`	Update an existing context block
`delete_context`	Remove a context block

Apps and integrations

Tool	Purpose
`search_apps`	Search the Runbear app catalog (Notion, Slack, Stripe, Linear, …)
`attach_app`	Attach a managed app or MCP from the catalog
`list_agent_tools`	List the integrations attached to an agent
`detach_tool`	Remove an integration from an agent
`connect_app_to_agent` / `verify_app_to_agent`	Start and confirm an in-conversation OAuth connection

Triggers and schedules

Tool	Purpose
`list_triggers` / `get_trigger`	List triggers and scheduled jobs, or read one in detail
`create_external_trigger`	Create an event (webhook) trigger
`create_scheduled_job`	Create a recurring (cron) or one-time scheduled run
`update_trigger` / `delete_trigger`	Modify or remove a trigger or scheduled job
`run_trigger_now`	Run a trigger or scheduled job immediately
`list_supported_trigger_types`	Browse the available event-trigger types

Slack

Tool	Purpose
`list_slack_installations`	List the Slack workspaces an agent can reach
`list_slack_channels` / `list_slack_users`	List channels or users in a workspace
`get_slack_install_link`	Get a link to install the agent into a workspace
`join_slack_channels`	Have the agent join specific channels
`deploy_to_slack`	Deploy the agent to Slack

Observability

Tool	Purpose
`list_recent_agent_traces`	List recent runs, with runtime and errors
`get_agent_trace`	Read a single run in detail

Example prompts

List my Runbear agents and show the model each one uses.
Update the Support agent's instructions to always greet the user by name.
Add a context block to the Sales agent describing our refund policy.
Search the app catalog for Linear and attach it to the Triage agent.
Schedule the Standup agent to run every weekday at 9am in #team-standup.
Deploy the Onboarding agent to our Slack workspace.
Show me the last 10 runs of the Billing agent and any errors.

Security

You stay in control. The server acts with your account's permissions and only within your organization. Disconnect it from your client at any time to revoke access.
Writes are explicit. Your client asks before each change, and operations that deploy or modify agents require the corresponding scope.
Never paste credentials into chat. When an integration needs a secret (API keys, bearer tokens, custom MCP headers), set it up in the Runbear dashboard at https://app.runbear.io/agents/<agentId>/integrations, where credentials are stored in the vault and masked. Conversation transcripts are retained by your client and LLM provider, so secrets pasted into chat would be exposed in scrollback and logs.

Limitations

The MCP server covers the core agent-management workflow. A few things are still dashboard-only:

Advanced model settings (temperature, reasoning effort) are configured in the dashboard.
Knowledge base sync setup is configured in the dashboard.
Scheduled jobs currently target Slack channels and DMs.

We're closing these gaps — expect the tool set to grow.

Custom MCP — connect your MCP servers and tools to a Team Agent (Runbear as the client)
Team Agent overview — what a Team Agent is and how it works
Model Context Protocol — the open standard behind MCP

On this page