ENDPOINT 1
https://api.wellapp.ai/v1/mcp
MCP server metadata
- Name
- well-financial-mcp
- Version
- 1.0.0
Known tools 18
well_update_personUpdate an existing person (contact) in the current workspace.
Potential side effectswell_delete_personDelete a person (contact) from the current workspace (soft delete).
Potential side effectswell_invoke_connector_toolRun one tool on a connected provider's own MCP server (e.
Inferred read-onlywell_create_invoice_from_dataCreate an invoice in Well from data you extracted by reading an invoice (your own OCR) — you send the structured fields, not the file.
Potential side effectswell_list_connectorsList the connectors a workspace can install, each with a one-click install deep link.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.well-financial-mcp]
url = "https://api.wellapp.ai/v1/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"well-financial-mcp": {
"type": "http",
"url": "https://api.wellapp.ai/v1/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: well-financial-mcp
Remote MCP URL: https://api.wellapp.ai/v1/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"well-financial-mcp": {
"url": "https://api.wellapp.ai/v1/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"well-financial-mcp": {
"type": "http",
"url": "https://api.wellapp.ai/v1/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "well-financial-mcp",
"transport": "streamable-http",
"url": "https://api.wellapp.ai/v1/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.