SignaTrust MCP Server
Enables AI assistants to manage document signing workflows via natural language, including creating envelopes, uploading documents, analyzing contracts, and verifying blockchain anchors.
README
@signatrust/mcp-server
Model Context Protocol (MCP) server for the SignaTrust document signing API. Enables AI assistants like Claude to create envelopes, manage templates, check signing status, and verify blockchain anchors via natural language.
Quick Start
Claude Code
claude mcp add signatrust -- npx -y @signatrust/mcp-server
Then set your API key in the MCP server environment.
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"signatrust": {
"command": "npx",
"args": ["-y", "@signatrust/mcp-server"],
"env": {
"SIGNATRUST_API_KEY": "sk_live_your_key_here"
}
}
}
}
Available Tools
| Tool | Description | Required Scope |
|---|---|---|
list_envelopes |
List envelopes with status filter and pagination | envelopes:read |
get_envelope |
Get full envelope details (signers, docs, blockchain) | envelopes:read |
create_envelope |
Create and send envelope for signing. Accepts documentIds (after upload_document) or templateId (backend copies the template). Supports three-tier securityLevel. |
envelopes:write |
list_templates |
List available document templates | templates:read |
upload_document |
Read a local file and upload it to SignaTrust, returning a document ID for create_envelope |
documents:write |
analyze_document |
Run AI contract analysis on an envelope (Gemini-powered risk/sentiment review, plan-gated) | ai:analyze |
verify_blockchain |
Verify Solana anchor and return composite hash + file hash + explorer URL | envelopes:read |
Three-tier security. create_envelope accepts securityLevel: STANDARD (bearer token only), VERIFIED (adds SMS/email OTP — recommended for employment, vendor, or healthcare consent), or CERTIFIED (adds WebAuthn biometric + device binding — recommended for real estate, high-value, or regulatory signings).
API Key Scopes
Create an API key at Settings > API Keys in your SignaTrust dashboard. Assign scopes based on what tools you need:
| Scope | Tools Enabled |
|---|---|
envelopes:read |
list_envelopes, get_envelope, verify_blockchain |
envelopes:write |
create_envelope |
templates:read |
list_templates |
documents:write |
upload_document |
ai:analyze |
analyze_document |
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
SIGNATRUST_API_KEY |
Yes | - | API key starting with sk_live_ |
SIGNATRUST_API_URL |
No | https://app.signatrust.io |
API base URL |
Natural Language Examples
Once connected, you can ask your AI assistant things like:
- "List all my pending envelopes"
- "Upload ~/Documents/nda.pdf and send it to alice@example.com with VERIFIED security"
- "Show me available templates, then create a lease agreement from the residential template for John Doe"
- "Check the blockchain verification for envelope env_abc123 and show me the composite hash"
- "Run AI analysis on envelope env_xyz — I want to know if there are any risky clauses before the signer reviews it"
Development
# Install dependencies
npm install
# Build
npm run build
# Run tests
npm test
# Run tests with coverage
npm run test:coverage
# Type check
npm run typecheck
# Local smoke test
SIGNATRUST_API_KEY=sk_live_xxx SIGNATRUST_API_URL=http://localhost:3000 node dist/server.js
Architecture
src/
server.ts # Entry point — env validation, MCP server setup, stdio transport
handlers.ts # Tool definitions and handler dispatch (testable)
errors.ts # RFC 7807 ProblemDetails -> MCP tool error mapping
vendor/signatrust-sdk/ # Vendored HTTP client + types (zero external runtime deps)
*.test.ts # Co-located test files
The HTTP client and API types are vendored under src/vendor/signatrust-sdk/ so
this package has no external runtime dependencies beyond @modelcontextprotocol/sdk.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.