Your AI assistant now knows
how to assist with
Brick APIs.
Connect Claude, GitHub Copilot, or Cursor directly to Brick’s live API documentation. No more hallucinated endpoints. No more malformed payloads. Integrate in hours, not days.
Compatible with:
HOW IT WORKS
AI-assisted across every phase
of integration.
Without context, AI tools guess at API behavior based on training data. Brick MCP provides live, structured access to Brick's full API context — so every suggestion is accurate, not hallucinated.
Discovery & API Understanding
Which API do I need? Ask your AI — get the right answer.
Should you use BI-FAST or Regular Transfer? Bulk disbursement or single? Without structured guidance, teams waste time reviewing docs manually or relying on incorrect assumptions. With Brick MCP, AI clients retrieve structured API descriptions and clarify functional differences between products on the spot.
Endpoint Selection & Payload Preparation
Generate correct payloads. Zero 400 errors on the first call.
Incorrect request body formats, missing required fields, inconsistent field naming — these cause repeated 400 errors during sandbox testing. Brick MCP gives AI tools access to real endpoint schemas so generated payloads align with Brick's actual API format, not outdated training data.
Sandbox Testing & Validation
Validate expected parameters and edge cases before you hit them.
Repeated failures from misunderstood constraints or edge cases slow down sandbox cycles. AI can assist developers in validating expected parameters and interpreting integration behaviors — catching issues before they become blockers in production.
Error Handling & Troubleshooting
Get an error you don't recognize? Ask. Get a contextual answer.
Teams often struggle to interpret error responses or distinguish between validation issues and downstream bank behavior. Brick MCP lets AI contextualize error patterns and guide engineers toward likely causes — without opening a support ticket.
CAPABILITIES
What Brick MCP Can Do
for Your AI Assistant
Live API Context Access
Your AI assistant queries Brick's structured API registry. Endpoints, schemas, auth flows, and rate limits — always current, never stale. No more hallucinated training data.
Correct Payload Generation
Request bodies are generated from actual API schemas with proper field types, required parameters, and validation constraints. No guessing.
Error Contextualization
When calls fail, your AI maps error codes to Brick-specific causes. HTTP 422 isn't generic — it's INVALID_BANK_CODE with a clear resolution path.
Product Decision Support
Not sure whether to use QRIS dynamic or Regular Transfer for this use case? Your AI assistant understands product differences, use cases, and trade-offs — not a guess.
Multi-Editor Support
Works across Claude Code, Cursor, GitHub Copilot, and OpenAI Codex. One protocol, consistent context delivery regardless of your tooling choice.
Onboarding Acceleration
New engineers get structured API understanding from day one. No tribal knowledge required — the context layer serves as living documentation.
QUICK SETUP
Connect once.
Context everywhere.
Brick MCP installs in minutes. Connect it to your AI editor and start integrating with full API context from your very first session. See the full setup guide for configuration details for each supported editor.
Install Brick MCP from the Brick docs. Compatible with any MCP-enabled editor.
Configure your editor to connect to the Brick MCP server — takes under 2 minutes. Setup guide covers Codex, Claude Code, and Copilot.
Start coding. Ask your AI anything about Brick APIs and get structured, accurate answers with no hallucination.
BRICK SKILLS · LOCAL PACKAGE
Prefer local?
Install Skills for your AI editor.
Beyond the remote MCP Server, Brick also distributes a locally installed Skills Package as a reference. Little or no setup is all you'll have: guidance for Claude Code, Codex, and GitHub Copilot.
Claude Code
Skills are packaged as .zip files and uploaded directly via Claude's UI under Customize → Skills.
Upload via Claude › Customize › Skills OpenAI Codex
Skills are distributed as .zip files. Extract each skill package and copy the Codex target directory to ~/.codex/skills/.
Install to ~/.codex/skills/ GitHub Copilot
Skills are distributed as .zip files. Extract and copy to your repo's .github/ directory — installs instructions, prompts, and agent skill folders for Copilot and VS Code agent mode.
Install to .github/ in your repo Powerful context, with clear boundaries.
Brick MCP is a context layer. It's a live knowledge engine. It helps AI assistants be architecturally sound, but it doesn't act — it only informs. A clear line that MCP acts as your client for or speaks your account code.
Review the Capability Constraints page in the docs to understand exactly what Brick MCP can and cannot do before starting.
What Brick MCP does
- Provides live Brick API context to AI assistants
- Delivers correct request/response schemas with validation rules
- Maps error codes to specific causes and resolution steps
- Provides endpoint selection and product comparison context for architectural decisions
- Supports integration decision-making
What Brick MCP does not do
- Execute API calls on your behalf
- Access your Brick account or transaction data
- Modify your codebase
- Replace testing in Brick's sandbox environment
Ready to integrate?
Start building with full API context today.
Brick MCP is available now. Connect your AI assistant and reduce integration time from days to hours.