Skip to main content Announcing Tool Policies: AI agent permissions down to the field Read the announcement
Live 23 Actions

SignWell MCP Server
for AI Agents

Connect your AI agent to StackOne's SignWell MCP server and give it 23 MCP tools out of the box. Auth, tool execution, and security all managed.

SignWell logo
SignWell MCP Server
Built by StackOne StackOne
DrataGPLocalyzeFlipMindtoolsScreenloop

Coverage

23 Agent Actions

Agents can read, write, delete and run operations in SignWell. Extend your agent's capabilities with custom actions.

Authentication

Agent Tool Authentication

Per-user OAuth in one call. Your SignWell MCP server gets session-scoped tokens with zero credentials stored on your infra.

Agent Auth →

Security

Agent Protection

Every SignWell tool response scanned for prompt injection in milliseconds, with 88.7% accuracy, all running on CPU.

Prompt Injection Defense →

Performance

Max Agent Context. Min Cost.

Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every SignWell call.

Tools Discovery →

What is the SignWell MCP Server?

A SignWell MCP server lets AI agents read and write SignWell data through the Model Context Protocol, Anthropic's open standard for connecting LLMs to external tools. StackOne's SignWell MCP server ships with 23 pre-built actions, fully extensible via the Connector Builder, plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.

All SignWell MCP Tools

Every StackOne action for SignWell, ready for your agent. Read, write, delete and run operations, scoped to exactly what you need.

Accounts

  • Get Account

    Retrieve the account's branding, locale, and default settings.

  • Update Account

    Change account branding, locale, and default document settings.

Bulk Sends

  • Create Bulk Send

    Send a document to many recipients at once from a CSV.

  • List Bulk Sends

    Return a paginated list of bulk sends on the account.

Validate Bulk Send CSVs

  • Validate Bulk Send CSV

    Validate a bulk send CSV.

Documents

  • Create Document

    Create and optionally send a new document for signing.

  • Get Document

    Retrieve a document and all of its associated data.

  • Delete Document

    Permanently remove a document and its data from the account.

Document From Templates

  • Create Document From Template

    Create a document from one or more templates.

And Send Documents

  • Update And Send Document

    Update a draft document and send it to recipients.

Reminders

  • Send Reminder

    Send a signing reminder to a document's recipients.

Authentications

  • Update Authentication

    Update recipient authentication settings on a document.

Recipients

  • Update Recipients

    Update the recipients on a document.

Completed Pdfs

  • Get Completed Pdf

    Retrieve the completed PDF for a document.

NOM-151 Certificates

  • Get NOM-151 Certificate

    Retrieve the NOM-151 certificate for a document.

Credentials

  • Get Credentials

    Return the API key and account details for the current connection.

Templates

  • Create Template

    Build a reusable template from uploaded files and fields.

  • Get Template

    Retrieve a template including its placeholders and fields.

  • Update Template

    Modify an existing template's fields, placeholders, and settings.

  • Delete Template

    Permanently remove a template from the account.

Webhooks

  • Create Webhook

    Register a callback URL to receive document event notifications.

  • List Webhooks

    Return all webhook subscriptions configured on the account.

  • Delete Webhook

    Stop event delivery by removing a webhook subscription.

Set Up Your SignWell MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to SignWell in under 10 lines of code.

Agent Frameworks

Claude Desktop
{
  "mcpServers": {
    "stackone": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://api.stackone.com/mcp?x-account-id=<account_id>",
        "--header",
        "Authorization: Basic <YOUR_BASE64_TOKEN>"
      ]
    }
  }
}

SignWell MCP Server FAQ

Does StackOne have a SignWell MCP server?
Yes. StackOne offers a hosted SignWell MCP server with 23 pre-built actions, and every action is tested and QA'd by StackOne. Connect it to Claude, Cursor, and any other MCP client, or to any agent framework through the AI Action SDK. It ships with managed agent authentication, prompt injection defense, and tool discovery with server-side execution that preserve your agent's context window and keep reasoning performance.
SignWell MCP server vs direct API integration: what's the difference?
A SignWell MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software work, where backend code calls SignWell. A SignWell MCP server is for AI agents that discover and call SignWell at runtime, such as MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI. StackOne provides both.
How does SignWell authentication work for AI agents?
SignWell authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK to get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own SignWell account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.
Are SignWell MCP tools vulnerable to prompt injection?
Yes. SignWell MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content, such as documents, messages, tickets, records, or free-text fields, is a potential vector. StackOne Defender scans every tool response before it enters the agent's context. It runs regex patterns in ~1ms, then a MiniLM classifier in ~4ms. Accuracy is 88.7%, and it runs entirely on CPU.
What is the context bloat of a SignWell agent and how do I avoid it?
Context bloat happens when SignWell tool schemas and API responses eat your SignWell agent's memory, preventing it from reasoning effectively. A single SignWell query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery reduces it by loading only the tools relevant to each query.
Can I limit which actions my SignWell agent can access?
Yes. You can limit which actions your SignWell agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my SignWell MCP server?
Yes. You can create custom agent actions for your SignWell MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research SignWell's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a SignWell MCP server?
Skip a SignWell MCP server if your integration is purely software-to-software, because direct SignWell API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call SignWell actions at runtime.
What AI frameworks and AI clients does the StackOne SignWell MCP server support?
The StackOne SignWell MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.

Put your AI agents to work

All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.