mcpField
A
AFAS Software MCP by usefulapi

AFAS Software MCP by usefulapi

Remote
usefulapi.ioBusiness & Marketing1Updated today

About AFAS Software MCP by usefulapi

AFAS Software MCP by usefulapi is a hosted MCP server for accessing AFAS Software from MCP clients. It lets users inspect enabled connectors, their fields, and their records using their own account credentials.

Key features

  1. 01List enabled AFAS connectors
  2. 02Inspect connector fields
  3. 03Read connector records
  4. 04Hosted connection with OAuth sign-in

Use cases

  1. 01Discover connectors enabled in an AFAS app connector
  2. 02Check fields available on a connector
  3. 03Read records from AFAS connectors

MCP support

Exposes AFAS connector metadata and records as read tools for MCP clients. It runs as a hosted remote MCP server.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://afas-software.usefulapi.io/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

AFAS Software MCP by usefulapi

Use your AFAS Software account from Claude, Cursor, or any MCP client. Browse the connectors your AFAS app connector activates, and read their fields and records. Hosted, no local install: connect with your own credentials.

Live endpoint: https://afas-software.usefulapi.io/mcp · Homepage: https://usefulapi.io

Connect

  • Claude (claude.ai, Desktop): open Customize → Connectors, click + Add → Add custom connector, and paste https://afas-software.usefulapi.io/mcp.
  • Claude Code: claude mcp add --transport http afas-software https://afas-software.usefulapi.io/mcp, then run /mcp to log in.
  • VS Code: Add to VS Code.
  • Cursor and other clients: add the URL as a remote MCP server:
{
  "mcpServers": {
    "afas-software": {
      "url": "https://afas-software.usefulapi.io/mcp"
    }
  }
}

Add only the URL. Do not add an Authorization header or an API key to the client config: the server signs you in with OAuth, and the login page asks for your AFAS Software credentials.

Step-by-step setup, where to find your credentials, and FAQ: https://usefulapi.io/afas-software/

On first connect you provide your AFAS environment ID (the number in your AFAS address, for example 12345 from O12345AA), the environment type and an AFAS app connector token (created in Profit under General → Management → App connector). The server validates it and stores it per user. No keys go in config files.

Tools

ToolTypeWhat it does
afas_get_metainforeadList connectors
afas_get_connector_metareadGet connector fields
afas_get_connectorreadRead a connector
afas_usage_statusmetaUsage status (free-tier meter)
afas_request_featuremetaRequest a missing feature
afas_upgrademetaUpgrade to Pro (unlimited*)
afas_cancel_subscriptionmetaCancel the Pro subscription

read tools are read-only; write tools mutate data (clients should confirm them); meta tools report usage, manage your subscription or send a feature request.

Pricing

PlanPriceLimit
Free$050 tool calls / month
Pro (per user)$9/mo or $90/yr (2 months free)Unlimited*

*Pro has a fair use limit of 10,000 tool calls a month on this server. For more, write to [email protected].

Pro covers this server only. Subscribe with afas_upgrade (it returns a Stripe Checkout link). Cancel any time with afas_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running afas_upgrade before then undoes the cancel. Or write to [email protected].

License

MIT — see LICENSE. Documentation only; the server is hosted.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.