Protocol MCP Documentation
Tools, resources, prompts, events, JSON-RPC, stdio, and SSE concepts for MCP builders.
Quick Answer / TL;DR
MCP uses JSON-RPC messages over local stdio or remote HTTP streaming, with tools for actions, resources for context, and prompts for reusable instructions.
Key Takeaways
- Every page includes India-first deployment and compliance context.
- Internal links connect pricing, performance, compliance, and deployment decisions.
- Use the hub as the cluster index for search engines and AI answer engines.
Protocol documentation map
Tools, resources, prompts, events, JSON-RPC, stdio, and SSE concepts for MCP builders.
Each guide in this cluster is written for teams building AI agent workflows in India, with practical routing, security, pricing, and deployment decisions called out explicitly.
Use the table below to choose the correct page, then follow the related links at the bottom of every guide to continue through the knowledge graph.
| Guide | Primary use |
|---|---|
| protocol / tools | Implementation guide |
| protocol / resources | Implementation guide |
| protocol / prompts | Implementation guide |
| protocol / events | Implementation guide |
Recommended implementation sequence
Start with a narrow use case, define the exact data the agent may access, and choose a transport that fits the user environment.
For desktop-only workflows, stdio is usually enough. For shared teams, remote SSE or streamable HTTP endpoints are easier to monitor and govern.
Before production, add request validation, secret isolation, structured logs, and a rollback path for each deployed MCP server.
{
"mcpServers": {
"india-edge-api": {
"url": "https://mcpserver.in/v1/mcp",
"headers": {
"Authorization": "Bearer ${MCP_API_KEY}",
"X-Data-Region": "in"
}
}
}
}Protocol MCP Documentation FAQs
Direct answers for developers, operators, and Indian teams evaluating MCP.