sn
MCP server for SignNow e-signature: templates, invites, embedded signing/editor, status & downloads.
claude mcp add --transport stdio signnow-sn-mcp-server uvx --from signnow-mcp-server sn-mcp serve
How to use
This MCP server exposes the SignNow eSignature workflows to AI agents in a structured way. It enables agents to access SignNow capabilities such as templates and template groups, embedding signing flows, managing invites with ordered recipients, tracking invite status, and downloading final documents. The server supports two transports: STDIO for local tool integrations and Streamable HTTP for remote or container-based usage. You can run the server locally with uvx (or install the package and run the sn-mcp command) and interact with SignNow resources via the MCP endpoints. Tools here include operations to browse templates, create document flows from templates, pre-fill fields, embed signing/sending experiences in your app, track progress, and fetch completed documents.
To use it, start the MCP server in STDIO mode or HTTP mode, then connect your client (Copilot-like agents, Claude, or other MCP-enabled clients) to the appropriate endpoint. For STDIO, you’ll run a command similar to uvx --from signnow-mcp-server sn-mcp serve; for HTTP, you’ll connect to the provided HTTP endpoint (e.g., http://127.0.0.1:8000/mcp) and issue MCP protocol commands through the API. The server translates your high-level prompts into SignNow API calls, returning structured results such as template IDs, invite statuses, and document download URLs.
How to install
Prerequisites:
- Python 3.11+ and pip
- uvx (preferred for quickest setup) or ensure your environment can run Python-based MCP servers
- Access to a SignNow developer account with API credentials (email, password, and API token as required)
Install and run the MCP server (STDIO mode):
# Option A: Install from PyPI (recommended for standard usage)
pip install signnow-mcp-server
# Run the MCP server in standalone STDIO mode
sn-mcp serve
If you prefer using uvx to run without a local installation of the package, install uvx and use the package name as the source:
# Ensure uvx is installed (via your system package manager or Python-based installer)
uvx --from signnow-mcp-server sn-mcp serve
Alternative: run the server via a local source clone in development mode
# 1) Clone & configure
git clone https://github.com/signnow/sn-mcp-server.git
cd sn-mcp-server
# 2) Install editable for development
pip install -e .
# 3) Run STDIO MCP server
sn-mcp serve
For HTTP/Streamable HTTP usage, refer to the configuration guidelines in the README and start the HTTP server accordingly (e.g., sn-mcp http or the equivalent uvx-based HTTP run if supported in your setup).
Additional notes
Environment variables: you will need SignNow credentials and related API settings. Typical variables include SIGNNOW_USER_EMAIL, SIGNNOW_PASSWORD, SIGNNOW_API_BASIC_TOKEN or SIGNNOW_TOKEN, SIGNNOW_APP_BASE and SIGNNOW_API_BASE. If using OAuth, you may also configure SIGNNOW_CLIENT_ID, SIGNNOW_CLIENT_SECRET and RSA/OAuth-related keys. In production, ensure RSA private keys are persisted for OAuth (OAUTH_RSA_PRIVATE_PEM) to avoid invalidating tokens on restart. When using Docker, mount a .env file or pass env vars securely to the container (and prefer HTTP mode for containerized deployments due to STDIO limitations inside containers). If you encounter connectivity issues with the Streamable HTTP endpoint, verify that the HTTP server is listening on the expected host/port and that your client connects to the /mcp path. For debugging, consult the MCP Inspector and client setup guidance in the README to validate the MCP protocol wiring and available tools.
Related MCP Servers
web-eval-agent
An MCP server that autonomously evaluates web applications.
copilot
A VSCode extension that lets you find and install Agent Skills and MCP Apps to use with GitHub Copilot, Claude Code, and Codex CLI.
fhir
FHIR MCP Server – helping you expose any FHIR Server or API as a MCP Server.
unitree-go2
The Unitree Go2 MCP Server is a server built on the MCP that enables users to control the Unitree Go2 robot using natural language commands interpreted by a LLM.
time
⏰ Time MCP Server: Giving LLMs Time Awareness Capabilities
mcp-chain-of-draft
Chain of Draft Server is a powerful AI-driven tool that helps developers make better decisions through systematic, iterative refinement of thoughts and designs. It integrates seamlessly with popular AI agents and provides a structured approach to reasoning, API design, architecture decisions, code reviews, and implementation planning.