About Gavel MCP by usefulapi
Gavel MCP by usefulapi connects Gavel workflows to MCP clients. It provides workflow and variable lookup, session creation, and access to session documents through a hosted service.
Key features
- 01List available workflows
- 02Retrieve workflow variables
- 03Create workflow sessions
- 04List documents in a session
Use cases
- 01Inspect workflows available in Gavel
- 02Check variables before starting a workflow
- 03Create a session for a workflow
- 04Review documents attached to a session
MCP support
Exposes Gavel workflow lookup and session operations as tools for MCP clients. The hosted endpoint connects using a Gavel subdomain and API key.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://gavel.usefulapi.io/mcpclaude mcp add --transport http io-usefulapi-gavel https://gavel.usefulapi.io/mcp{"mcpServers":{"io-usefulapi-gavel":{"type":"http","url":"https://gavel.usefulapi.io/mcp"}}}Open in Cursor{"servers":{"io-usefulapi-gavel":{"type":"http","url":"https://gavel.usefulapi.io/mcp"}}}Open in VS Code{"mcpServers":{"io-usefulapi-gavel":{"type":"http","url":"https://gavel.usefulapi.io/mcp"}}}{"mcpServers":{"io-usefulapi-gavel":{"serverUrl":"https://gavel.usefulapi.io/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMEGavel MCP by usefulapi
Use your Gavel account from Claude, Cursor, or any MCP client. List workflows and their variables, create workflow sessions and list the documents of a session. Hosted, no local install: connect with your own credentials.
Live endpoint: https://gavel.usefulapi.io/mcp · Homepage: https://usefulapi.io
Connect
- Claude (claude.ai, Desktop): open Customize → Connectors, click + Add → Add custom connector, and paste
https://gavel.usefulapi.io/mcp. - Claude Code:
claude mcp add --transport http gavel https://gavel.usefulapi.io/mcp, then run/mcpto log in. - VS Code: Add to VS Code.
- Cursor and other clients: add the URL as a remote MCP server:
{
"mcpServers": {
"gavel": {
"url": "https://gavel.usefulapi.io/mcp"
}
}
}
Add only the URL. Do not add an Authorization header or an API key to the client config: the server signs you in with OAuth, and the login page asks for your Gavel credentials.
Step-by-step setup, where to find your credentials, and FAQ: https://usefulapi.io/gavel/
On first connect you provide your Gavel subdomain and a Gavel API key (Gavel → Settings → API Keys). You need a Builder or Admin role and a plan with API access. The server validates it and stores it per user. No keys go in config files.
Tools
| Tool | Type | What it does |
|---|---|---|
gavel_list_workflows | read | List workflows |
gavel_get_workflow_variables | read | Get workflow variables |
gavel_create_session | write | Create a workflow session |
gavel_list_session_documents | read | List session documents |
gavel_usage_status | meta | Usage status (free-tier meter) |
gavel_request_feature | meta | Request a missing feature |
gavel_upgrade | meta | Upgrade to Pro (unlimited*) |
gavel_cancel_subscription | meta | Cancel the Pro subscription |
read tools are read-only; write tools mutate data (clients should confirm them); meta tools report usage, manage your subscription or send a feature request.
Pricing
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 50 tool calls / month |
| Pro (per user) | $9/mo or $90/yr (2 months free) | Unlimited* |
*Pro has a fair use limit of 10,000 tool calls a month on this server. For more, write to [email protected].
Pro covers this server only. Subscribe with gavel_upgrade (it returns a Stripe Checkout link). Cancel any time with gavel_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running gavel_upgrade before then undoes the cancel. Or write to [email protected].
License
MIT — see LICENSE. Documentation only; the server is hosted.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.