sharpspring-mcp-server
An open-source MCP server for the SharpSpring API (Constant Contact Lead Gen & CRM) that enables AI clients to read and write Leads, discover custom fields, and call any documented API method.
README
sharpspring-mcp-server
An open-source MCP (Model Context Protocol) server for the SharpSpring API, now branded Constant Contact Lead Gen & CRM. It lets any MCP-compatible AI client (Claude Desktop, Claude Code, Cursor, etc.) read and write Leads, discover custom fields, and call any other documented SharpSpring API method.
This is an independent, community project. It is not affiliated with, endorsed by, or supported by SharpSpring or Constant Contact.
Design goals
- No account-specific configuration baked in. Every credential comes from environment variables at runtime. No hardcoded custom field names, account IDs, or other values belonging to any one SharpSpring account.
- Generic by default. Tools map to SharpSpring's standard, documented API methods and object shapes only — nothing bespoke.
- Custom fields stay dynamic. Since every SharpSpring account has its own custom fields, this server never assumes field names. Use
sharpspring_get_fieldsto discover a given account's fields (system + custom) at runtime, then reference them bysystemName.
Setup
npm install
npm run build
Copy .env.example to .env and fill in your own credentials (generate them in SharpSpring under API Keys):
cp .env.example .env
SHARPSPRING_ACCOUNT_ID=your-account-id
SHARPSPRING_SECRET_KEY=your-secret-key
# Optional: v1 (timezone follows the account's Company Profile) or v1.2 (UTC, default)
SHARPSPRING_API_VERSION=v1.2
Using with an MCP client
Once published to npm, you can run it directly with npx — no local clone needed:
{
"mcpServers": {
"sharpspring": {
"command": "npx",
"args": ["-y", "sharpspring-mcp-server"],
"env": {
"SHARPSPRING_ACCOUNT_ID": "your-account-id",
"SHARPSPRING_SECRET_KEY": "your-secret-key"
}
}
}
}
Or, running from a local clone/build, point at the built entry point instead:
{
"mcpServers": {
"sharpspring": {
"command": "node",
"args": ["/absolute/path/to/sharpspring-mcp-server/build/index.js"],
"env": {
"SHARPSPRING_ACCOUNT_ID": "your-account-id",
"SHARPSPRING_SECRET_KEY": "your-secret-key"
}
}
}
}
Never commit real credentials — pass them as environment variables as shown above.
Tools
| Tool | SharpSpring method | Description |
|---|---|---|
sharpspring_get_fields |
getFields |
Discover lead/account/opportunity/campaign fields, including custom fields and their systemName. |
sharpspring_get_leads |
getLeads |
List/filter leads (by id, emailAddress), up to 500 per call. |
sharpspring_get_lead |
getLead |
Fetch a single lead by id. |
sharpspring_create_leads |
createLeads |
Create up to 500 leads. |
sharpspring_update_leads |
updateLeads / updateLeadsV2 |
Update up to 500 leads by id. |
sharpspring_delete_leads |
deleteLeads |
Delete leads by id. |
sharpspring_call |
any | Generic escape hatch: call any documented SharpSpring method (Accounts, Campaigns, Opportunities, Lists, Notes, Tasks, DealStages, Products, Emails, ...) by name with a raw params object. |
Only Leads have dedicated, ergonomic tools today. Every other standard SharpSpring object (Accounts, Campaigns, Opportunities, Lists/ListMembers, Notes, Tasks, ...) is already reachable through sharpspring_call and is a natural next PR — see Contributing.
API notes
- Endpoint:
https://api.sharpspring.com/pubapi/{version}/, JSON-RPC-style POST requests, auth viaaccountID/secretKeyquery params. - Object-level errors (e.g. "Entry already exists") come back inside a successful response, nested under
result.creates[].error/result.updates[].error/result.deletes[].error— always check these, not just the top-levelerrorfield. - Rate limits: 50,000 requests/day, 10 requests/second, 500 objects per query. This server does not implement client-side throttling or retries — callers are responsible for respecting these limits.
Contributing
Pull requests are welcome, especially dedicated tools for other standard objects (Accounts, Campaigns, Opportunities, Lists, Notes, Tasks). Keep additions generic and account-agnostic: no hardcoded field names, account IDs, or other environment-specific values.
License
MIT — see LICENSE.
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
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.