signbee-mcp
Signbee MCP Server enables AI agents to send documents for legally-binding two-party e-signing from MCP-compatible clients like Claude Desktop, Cursor, and Windsurf.
Send a markdown document for e-signing (
send_document): Provide markdown content with sender/recipient details; Signbee auto-converts it to a professional PDF and initiates the signing workflow. The document title can be auto-extracted from the first heading if not provided.Send an existing PDF for e-signing (
send_document_pdf): Provide a publicly accessible PDF URL along with sender/recipient details to initiate signing.Automated signing ceremony: Handles the full flow — emailing the recipient a signing link and delivering a SHA-256 certified signed copy to both parties upon completion.
Configurable expiry: Set signing link validity from 1–30 days (default: 7).
Optional API key authentication: Without an API key, the sender verifies via email OTP; with one, documents are sent instantly.
Enables the conversion of Markdown document content into professional, SHA-256 certified PDFs for two-party e-signing, including automatic document title extraction from Markdown headings.
Signbee MCP Server
Document signing for AI agents — as an MCP tool.
Send, sign, and verify documents with a single tool call. Works with Claude, Cursor, Windsurf, and any MCP-compatible client.
Quick Setup
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"signbee": {
"command": "npx",
"args": ["-y", "signbee-mcp"],
"env": {
"SIGNBEE_API_KEY": "your-api-key-from-signb.ee/dashboard"
}
}
}
}Cursor / Windsurf
Add to your MCP settings:
{
"signbee": {
"command": "npx",
"args": ["-y", "signbee-mcp"],
"env": {
"SIGNBEE_API_KEY": "your-api-key"
}
}
}Note: The API key is optional. Without it, the sender verifies via email OTP. With it, documents are sent instantly.
Related MCP server: Cryptair MCP Server
Tools
send_document
Send a markdown document for two-party e-signing.
Parameters:
Parameter | Required | Description |
| ✅ | Document content in markdown format |
| ✅ | Full name of the sender |
| ✅ | Email address of the sender |
| ✅ | Full name of the recipient |
| ✅ | Email address of the recipient |
| ❌ | Document title (auto-extracted from heading) |
| ❌ | Days until signing link expires (default: 7) |
Example prompt: "Send an NDA to bob@acme.com from alice@company.com"
send_document_pdf
Send an existing PDF for two-party e-signing.
Parameters:
Parameter | Required | Description |
| ✅ | Publicly accessible URL to the PDF |
| ✅ | Document title |
| ✅ | Full name of the sender |
| ✅ | Email address of the sender |
| ✅ | Full name of the recipient |
| ✅ | Email address of the recipient |
| ❌ | Days until signing link expires (default: 7) |
How It Works
You ask your AI to send a document for signing
The MCP server calls the Signbee API
Signbee converts markdown → PDF, handles the signing ceremony
Both parties receive a SHA-256 certified signed copy via email
Get Your API Key
Go to signb.ee
Create an account
Navigate to the Dashboard
Copy your API key
Links
Website: signb.ee
OpenAPI Spec: signb.ee/openapi.json
llms.txt: signb.ee/llms.txt
License
MIT
Available Tools
2 toolssend_documentA
Send a document for two-party e-signing. Converts markdown to PDF, verifies the sender, emails the recipient a signing link, and delivers a SHA-256 certified signed copy to both parties.
| Name | Required | Description | Default |
|---|---|---|---|
| markdown | Yes | Document content in markdown format. This will be converted to a professional PDF. | |
| title | No | Document title. If omitted, extracted from the first markdown heading. | |
| sender_name | Yes | Full name of the document sender | |
| sender_email | Yes | Email address of the sender | |
| recipient_name | Yes | Full name of the document recipient | |
| recipient_email | Yes | Email address of the recipient | |
| expires_in_days | No | Days until the signing link expires. Default: 7 |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes the multi-step workflow (markdown conversion, sender verification, email delivery, SHA-256 certification) and the outcome (signed copy to both parties), though it doesn't mention error conditions, rate limits, or authentication requirements.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that efficiently communicates the complete workflow. Every clause adds essential information about the tool's functionality with zero wasted words, making it highly front-loaded and easy to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 7 parameters, 100% schema coverage, and no output schema, the description provides strong contextual completeness by explaining the multi-step process and outcome. It could be slightly improved by mentioning error handling or authentication, but covers the core functionality well given the structured data available.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, providing comprehensive parameter documentation. The description adds value by explaining the overall workflow context and that markdown converts to PDF, but doesn't provide additional parameter semantics beyond what the schema already documents effectively.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('Send a document for two-party e-signing') and resource ('document'), distinguishing it from the sibling tool 'send_document_pdf' by specifying e-signing functionality rather than just PDF sending. It provides a comprehensive overview of the multi-step process involved.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context (two-party e-signing with markdown conversion), but doesn't explicitly state when to use this tool versus the sibling 'send_document_pdf' or other alternatives. It provides functional context but lacks comparative guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
send_document_pdfA
Send an existing PDF document for two-party e-signing. Use this when you already have a PDF URL instead of markdown content.
| Name | Required | Description | Default |
|---|---|---|---|
| pdf_url | Yes | Publicly accessible URL to the PDF document | |
| title | Yes | Document title | |
| sender_name | Yes | Full name of the document sender | |
| sender_email | Yes | Email address of the sender | |
| recipient_name | Yes | Full name of the document recipient | |
| recipient_email | Yes | Email address of the recipient | |
| expires_in_days | No | Days until the signing link expires. Default: 7 |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. While it mentions 'two-party e-signing' and 'expires in days' (implied by the parameter), it lacks critical behavioral details such as authentication requirements, rate limits, what happens after sending (e.g., notification process, error handling), or whether this is a read-only or destructive operation. For a tool that initiates a signing process with multiple parameters, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise and front-loaded, consisting of only two sentences that directly address purpose and usage guidelines. Every sentence earns its place with no wasted words, making it easy for an AI agent to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of a 7-parameter tool with no annotations and no output schema, the description is incomplete. It adequately covers purpose and usage but lacks behavioral context (e.g., what the tool returns, error conditions, or side effects). While it compensates somewhat with clear guidelines, the absence of output details and behavioral transparency leaves gaps for an AI agent to fully understand the tool's operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, meaning all parameters are well-documented in the input schema. The description adds minimal value beyond the schema by implying the purpose of 'pdf_url' and 'expires_in_days', but it doesn't provide additional context like parameter interactions or examples. With high schema coverage, the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('Send an existing PDF document for two-party e-signing') and distinguishes it from sibling tools by specifying 'when you already have a PDF URL instead of markdown content.' This explicitly differentiates it from the 'send_document' sibling, which presumably handles markdown content.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit usage guidance: 'Use this when you already have a PDF URL instead of markdown content.' This clearly indicates when to use this tool versus alternatives (like the 'send_document' sibling), making it easy for an AI agent to select the correct tool based on the input type.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
2 tool updates
v1.0.0- First observed
send_document - First observed
send_document_pdf
TDQS
The two tools have clearly distinct purposes: one handles markdown-to-PDF conversion for document creation, while the other works with existing PDF URLs. The descriptions explicitly differentiate them, though both involve sending documents for e-signing, which could cause minor confusion if an agent doesn't carefully read the descriptions.
Both tools follow a consistent verb_noun pattern with 'send_document' as the base, and the second tool adds '_pdf' as a modifier to indicate the specific variant. This naming scheme is predictable and clearly communicates the relationship between the tools.
With only 2 tools, the server feels thin for an e-signing domain, as it lacks operations like document status checking, signature verification, or cancellation. While the tools cover the core sending functionality, the limited count may restrict agent workflows and require workarounds for common scenarios.
The toolset is severely incomplete for an e-signing server. It only provides document sending (in two variants) but lacks essential operations such as retrieving sent documents, checking signing status, managing recipients, or handling post-signing actions. This will likely cause agent failures when trying to implement full e-signing workflows.
Maintenance
Related MCP Connectors
E-signature API for AI agents: send contracts, sign PDF documents, track and download signed files.
Free e-signature for humans and AI agents — zero-document PDF signing from hashes only.
Send AI-created PDFs for signature, track signers, and return verifiable document evidence.
- SignvoyOAuthcom.signvoy
Send documents for e-signature, track signing status, and download signed PDFs. No API key required.
Related MCP Servers
- AlicenseAqualityDmaintenanceSend documents for e-signature from Claude Desktop, Claude Code, Cursor, and other AI agents. Free DocuSign alternative.1557MIT
- AlicenseAqualityDmaintenanceEnables AI agents to certify documents, prove agreements, and verify counterparty claims with on-chain receipts on Hedera Hashgraph. Provides tools for document certification, two-party attestation, and agent registration with zero-config setup.667MIT
- AlicenseNot gradedqualityBmaintenanceE-signature for AI agents. One unauthenticated call returns a sandbox API key (no account, no browser), then the agent can send documents for signature, check status, and download the sealed PDF plus Certificate of Completion.3MIT

layerone-mcpofficial
AlicenseAqualityCmaintenanceEnables AI agents to generate documents (PDF/DOCX/Factur-X) and manage electronic signatures (eIDAS/PAdES) via natural language using LayerOne's DocX and Sign APIs.2064MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/signbee/mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server