Gavel MCP by usefulapi

List workflows and variables; create sessions and list session documents in Gavel.

Should I use this

Quality & Safety

A
Description quality
100%
Schema completeness
83%
Naming quality
80%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~729Tokens (tool definitions)
~990 BTypical response size
Moderate attention impact (0.57% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "gavel": {
      "url": "https://gavel.usefulapi.io/mcp"
    }
  }
}

Remote endpoints

https://gavel.usefulapi.io/mcpstreamable-http

What it can do

Tool inventory

Tools (4)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟢gavel_list_workflows

List the names of all Gavel workflows on the account. API: GET /api/playground?folder=questions.

Input Schema

{
  "type": "object",
  "properties": {},
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
🟢gavel_get_workflow_variables(workflow_name)

Get the variable schema of one workflow: each variable name, data type, input type, label, options and whether it is required. Use it to learn what data gavel_create_session accepts. API: GET /officeaddin?pgtypes=<name>.yml.

Input Schema

{
  "type": "object",
  "properties": {
    "workflow_name": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "The workflow name, case-sensitive, as gavel_list_workflows returns it (with or without \".yml\")."
    }
  },
  "required": [
    "workflow_name"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
🟡gavel_create_session(workflow_name, variables)

WRITE: create a new session of a workflow with pre-filled variables. It does not send or sign anything. Each call creates one more session. Returns session_id and a continuation_url. If all variables are given, the URL opens the document download page; else the user answers only the missing questions. Dates: '2024-05-30T'. Date time: ISO 8601. Multi select: array of option labels. Repeating items: array of objects. Use gavel_get_workflow_variables for the names. API: POST /api/documate/v1/interviews/{name}/new.

Input Schema

{
  "type": "object",
  "properties": {
    "workflow_name": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "The workflow name, case-sensitive, as gavel_list_workflows returns it (with or without \".yml\")."
    },
    "variables": {
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {},
      "description": "Variable name to value. Text or number: plain value. Repeating item: array of objects."
    }
  },
  "required": [
    "workflow_name",
    "variables"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
🟢gavel_list_session_documents(workflow_name, session_id)

List the documents of a completed workflow session: name, format (docx or pdf), type, source template and download URL. This tool returns metadata only. The download URL needs the X-Api-Key header. API: GET /api/documate/v1/data-manager/workflows/{name}/session/{id}/documents.

Input Schema

{
  "type": "object",
  "properties": {
    "workflow_name": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "The workflow name, case-sensitive, as gavel_list_workflows returns it (with or without \".yml\")."
    },
    "session_id": {
      "type": "string",
      "pattern": "^[A-Za-z0-9_-]{4,128}$",
      "description": "The session_id from gavel_create_session."
    }
  },
  "required": [
    "workflow_name",
    "session_id"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded4 tools