Heaventree WHMCS MCP
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Heaventree WHMCS MCP
Original, MIT-licensed WHMCS addon exposing documented local API tools, operational BI reports and guarded administration over Model Context Protocol. Upload one addon folder to WHMCS; no Docker, remote database login or WHMCS remote API IP allowlist.
Release candidate 0.1.0. Local protocol/security tests are provided. Production WHMCS staging acceptance and Maxer provider verification are separate gates. Exact parity with the encrypted paid addon is not yet verified; see coverage. The existing commercial addon and JOSH bridges are not modified by this build.
Default access is read-only. Write execution requires a write-scoped token, the addon write switch, and a five-minute administrator-approved request bound to the exact tool, parameters and token. Approvals are single-use; unknown execution outcomes require independent verification, not automatic retries. An administrator can mark one token for instant ticket writes (reply, note, update, block sender only), and can set a signed webhook that tells a mirror which ticket changed; see docs/USAGE.md.
Business data remains on the WHMCS server until an authorized MCP client reads it. That client's model provider may receive returned data: self-hosting the addon does not guarantee data stays on-server when using a cloud AI client. Responses redact credential-like fields; token/audit tables do not store raw customer response bodies. Deployers must handle customer data lawfully and restrict access appropriately.
Development
PHP8.1+; no runtime Composer dependencies. Run php tests/run.php, node --test tests/bridge.test.mjs, and syntax-check every PHP file. Build an immutable ZIP with pwsh -NoProfile -File scripts/package.ps1. ZIP entries use / separators and include no secrets or vendor code.
Catalog regeneration: node scripts/generate-catalog.mjs /PATH/TO/OFFICIAL/WHMCS/developer-docs. The initial catalog uses documentation commit 2e75f454aa248b791948e14ad7b33fa9f0ded761. Regeneration is a reviewed build step, not runtime endpoint discovery; newly added operations default to write scope unless explicitly classified read-only.
Related MCP server: Clinical MCP Server
License and independence
Copyright2026 Heaventree. All original code and documentation in this repository are MIT-licensed. WHMCS is separately licensed and not included. API names and parameter types are interoperability facts from WHMCS's official documentation. No paid plugin source, ionCube decoder, license bypass, copied assets, production database or credential is distributed.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Read-only MCP access to a documented IT fleet: state, changes, posture. 15 tools.
One governed MCP endpoint for 40+ business systems. Read-only, source-cited answers.
Securely query and analyze business data, dashboards, projections, alerts, and knowledge.
Your whole business as one MCP server: analytics, CRM, SEO, ads, revenue. Scoped per data class.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA read-only Model Context Protocol server that exposes over 60 AWS tools across services like EC2, S3, and IAM for AI agent interaction. It features multi-region support, resource caching, and audit logging to provide secure, AI-ready access to AWS infrastructure data.ISC
- AlicenseNot gradedqualityDmaintenanceA governed, audited Model Context Protocol server that provides AI agents with secure, read-only access to a clinical knowledge base through least-privilege tools, policy validation, and append-only audit logging.MIT
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that exposes a versioned brand package (tokens, rules, recipes, media rights, and audit gates) as resources, tools, and prompts for AI agents. It enables agents to plan and audit on-brand UI, image, motion, and video outputs while remaining read-only and credential-free.MIT
- AlicenseNot gradedqualityCmaintenanceRead-only Model Context Protocol server exposing LCP tools to an AI agent — verify before pay, compute an atrHash, extract and place references across ten commerce protocols.Apache 2.0