discord-mcp-server
A Model Context Protocol (MCP) server that lets MCP-compatible clients (e.g., Claude Desktop) interact with Discord via a JSON-RPC 2.0 interface over stdio. It supports Discord bot operations such as sending and retrieving messages, getting channel info, searching messages, and moderation actions, with configurable YAML + environment overrides and options for JWT/API-key authentication.
Score Breakdown
⚙ Agent Friendliness
🔒 Security
README includes security best practices (don’t commit secrets, use env vars, rotate API keys, enable audit logging, use strong JWT secrets, limit bot permissions). However, provided documentation does not clearly describe transport security for MCP stdio, token validation details, or fine-grained authorization/scope model per tool/action.
⚡ Reliability
Best When
You need an MCP tool interface to interact with Discord from local/desktop or agent frameworks that support MCP over stdio, and you can secure bot credentials and authentication appropriately.
Avoid When
You cannot securely manage secrets (bot tokens, JWT secret, API keys) or you require fine-grained, formally documented authorization semantics per action/tenant that are not described in the provided README.
Use Cases
- • Automating Discord workflows from an MCP client
- • Building AI-assisted moderation actions (e.g., delete messages, kick/ban users) through tool calls
- • Searching and summarizing Discord message history
- • Channel-aware assistants that can fetch metadata and recent messages
- • Multi-bot / multi-guild orchestration via a single server
Not For
- • Publicly exposing raw bot control endpoints without strong operational controls (least-privilege, network isolation)
- • Use cases requiring a documented, network-based HTTP API for third-party integrations (it is stdio-based MCP)
- • Production environments that require clearly documented operational reliability guarantees (no SLA/reliability evidence provided here)
Interface
Authentication
README states support for JWT and API keys and an optional audit logging flag, but does not describe scope model/granular permissions or how authorization is enforced per tool/action.
Pricing
No pricing information provided (appears to be a self-hosted open-source project).
Agent Metadata
Known Gotchas
- ⚠ Tooling operates through stdio MCP transport; ensure the MCP client/server process lifecycle is stable
- ⚠ Moderation actions (delete/kick/ban) are high-impact—agents should implement explicit confirmation/guardrails client-side
- ⚠ Auth mechanism details (JWT/API key validation specifics and per-tool authorization) are not fully documented in the provided README
Alternatives
Full Evaluation Report
Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for discord-mcp-server.
AI-powered analysis · PDF + markdown · Delivered within 30 minutes
Package Brief
Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.
Delivered within 10 minutes
Score Monitoring
Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.
Continuous monitoring
Scores are editorial opinions as of 2026-04-04.