Scout MCP Server: Connect Your Coding Agent to Scout

Scout MCP is a local Model Context Protocol server that gives your coding agent direct access to the Scout OS API. Run it once and your agent can list workflows, manage databases, trigger automations, upload files, and interact with agents — all from inside its context window, without writing integration code or copy-pasting credentials manually.

What is MCP?

MCP (Model Context Protocol) is an open standard that lets AI coding agents connect to external tools and services through a structured, discoverable interface. Instead of writing custom integration code for every service, you run an MCP server once and your agent immediately gains access to all the capabilities that server exposes. With Scout MCP running, your agent can:

Query and manage your Scout workflows, agents, and databases
Run workflows and inspect their outputs
Upload files to Scout Drive and sync them to tables
Read run logs and surface failures
Execute triggers and interact with agents in real time

Your agent treats Scout the same way it treats the filesystem or a web search — as a first-class tool it can reason about and act on.

What Scout MCP Exposes

Scout MCP wraps the Scout OS API and exposes it as 13 domain tools covering 79 API endpoints. Each tool accepts an action parameter (list, get, create, update, delete) so your agent can operate on any Scout resource through a consistent interface.

Tool Coverage

Tool	Covers	Actions
`scout_workflows`	Workflows, revisions, environments	list, get, create, update, delete, run, run_with_config
`scout_agents`	Agents	list, get, upsert, delete, interact, interact_sync
`scout_agent_sessions`	Agent sessions	interact_with_session, interact_sync_with_session, interact_async_with_session
`scout_databases`	Databases	list, get, create, update, delete
`scout_tables`	Tables	list, get, create, update, delete, get_schema, sync
`scout_documents`	Documents	list, get, create, update, update_batch, delete, delete_batch
`scout_syncs`	Syncs, sources	list, get, create, update, delete, execute, list_sources
`scout_triggers`	Triggers	list, create, update, delete, execute_slack, execute_telegram, execute_cron
`scout_copilots`	Copilots	list, get, create, update, delete
`scout_logs`	Run logs	list, get_details
`scout_integrations`	Integrations, org	list, list_channels, delete_integration
`scout_drive`	Drive storage	upload, download
`scout_usage`	Usage metrics	get

Resources

Scout MCP also exposes three read-only context resources your agent can inspect at any time without making tool calls:

Resource URI	What it contains
`scout://workflows`	List of all workflows in your organization
`scout://databases`	List of all databases in your organization
`scout://agents`	List of all agents in your organization

Getting Started

Prerequisites

Before starting the Scout MCP server, make sure you have:

Node.js 18 or later installed
A Scout API key — grab one from Settings → API Keys

Install and Start the Server

Install the package

Install Scout MCP globally with npm:

npm install -g scoutos-mcp

Or run it directly without a global install:

npx scoutos-mcp

Set your API key

Export your Scout API key as an environment variable:

export SCOUT_API_KEY="your_api_key_here"

Start the server

Launch the Scout MCP server:

scoutos-mcp

You should see:

Scout MCP server listening on http://127.0.0.1:9987/mcp

Verify the server is healthy

Confirm the server is running and accessible:

curl http://127.0.0.1:9987/health

Connect your agent

Point your MCP-capable coding agent at:

http://127.0.0.1:9987/mcp

Your agent will discover all 13 Scout tools automatically — no additional configuration needed.

Connect Your Agent

Each coding agent configures MCP connections differently. Follow the setup guide for yours:

Claude Code

Add Scout MCP as an MCP server in your Claude Code settings.

Cursor

Configure Scout MCP in Cursor’s MCP settings panel.

Codex

Connect Scout MCP to Codex via the MCP integration settings.

OpenCode

Add Scout MCP as an MCP server in your OpenCode configuration.

Configuration

Customize Port and Host

Start the server on a different port or host if the defaults conflict with another process:

scoutos-mcp --port 3333 --host 127.0.0.1

Run with Docker

If you prefer to run Scout MCP in a container:

docker build -t scoutos-mcp .
docker run -p 9987:9987 -e SCOUT_API_KEY=your_api_key_here scoutos-mcp

Restrict Access with a Bearer Token

Lock down the MCP server so only trusted clients can connect by setting a bearer token before starting:

export MCP_SERVER_BEARER_TOKEN="your_secret_token"
scoutos-mcp

Clients must then include this header with every request:

Authorization: Bearer your_secret_token

Environment Variables

SCOUT_API_KEY

string

required

Your Scout API key. Used to authenticate all requests Scout MCP makes to the Scout OS API.

PORT

number

The port the MCP server listens on. Defaults to 9987.

HOST

string

The host address the MCP server binds to. Defaults to 127.0.0.1.

MCP_SERVER_BEARER_TOKEN

string

When set, the MCP server requires clients to present this value as a Bearer token. Leave unset for local development with no client auth.

Example Usage

Once Scout MCP is connected, here are practical things you can ask your agent to do.

Explore your workspace

List my Scout workflows and explain what each one does.

Show my databases and summarize which tables look customer-related.

Find the agent named "SDR Assistant" and show its current configuration.

Run and debug workflows

Run workflow wf_abc123 with this sample payload and summarize the output:
{ "company": "Acme Corp", "contact_email": "hello@acme.com" }

Check recent Scout run logs and surface any failures from today.
Show me the error details for any failed runs.

Manage data

Upload this CSV to Scout Drive and then sync it to the customers table.

Create a new database called "Support Tickets" with a table that has
columns: ticket_id, status, priority, and summary.

Work with triggers

List all my Scout triggers. Which ones are active?
Show me the last time each trigger fired.

Update the Slack trigger on workflow wf_abc123 to only respond
in the #support channel.

Monitor usage

How much of my Scout quota have I used this month?
Break it down by workflow if possible.

Troubleshooting

Issue	What to check
Agent cannot connect	Confirm `scoutos-mcp` is running and the URL matches your configured host and port.
`401` or auth errors	Verify `SCOUT_API_KEY` is set in the environment before starting the server. Restart the server after setting it.
Server starts but tools are missing	Make sure you are on the latest version: `npm update -g scoutos-mcp`
Works in one agent but not another	Confirm each agent points at `http://127.0.0.1:9987/mcp` and reload its MCP config.
Health check fails	Run `curl http://127.0.0.1:9987/health` locally; if it fails, stop and restart the server.
Bearer token errors	Confirm the value of `MCP_SERVER_BEARER_TOKEN` and the client `Authorization` header match exactly.
Port conflict on startup	Another process is using port 9987. Start with `--port 3334` or another free port.

After updating scoutos-mcp with npm update -g scoutos-mcp, restart the server for changes to take effect. Your agent will re-discover the updated tool list automatically.

References

Scout MCP on GitHub

Source code, changelogs, and open issues for the Scout MCP server.

Scout API Reference

Full reference for all 79 Scout API endpoints exposed through Scout MCP.

MCP Specification

The open standard Scout MCP implements for agent-to-service communication.

​What is MCP?

​What Scout MCP Exposes

​Tool Coverage

​Resources

​Getting Started

​Prerequisites

​Install and Start the Server

​Connect Your Agent

Claude Code

Cursor

Codex

OpenCode

​Configuration

​Customize Port and Host

​Run with Docker

​Restrict Access with a Bearer Token

​Environment Variables

​Example Usage

​Explore your workspace

​Run and debug workflows

​Manage data

​Work with triggers

​Monitor usage

​Troubleshooting

​References

Scout MCP on GitHub

Scout API Reference

MCP Specification

What is MCP?

What Scout MCP Exposes

Tool Coverage

Resources

Getting Started

Prerequisites

Install and Start the Server

Connect Your Agent

Configuration

Customize Port and Host

Run with Docker

Restrict Access with a Bearer Token

Environment Variables

Example Usage

Explore your workspace

Run and debug workflows

Manage data

Work with triggers

Monitor usage

Troubleshooting

References