{"id":"hanweg-mcp-discord","name":"mcp-discord","homepage":null,"repo_url":"https://github.com/hanweg/mcp-discord","category":"communication","subcategories":[],"tags":["mcp","discord","agents","moderation","messaging","python"],"what_it_does":"Provides an MCP server that exposes Discord bot capabilities (server/channel/member lookup, message read/send, reactions, and basic moderation/role management) to MCP clients such as Claude Desktop.","use_cases":["Let an AI agent inspect Discord servers, channels, members, and users","Enable agents to send messages or add/remove reactions in a controlled Discord bot context","Support agent workflows for moderating messages (delete/timeout) and managing roles","Automate routine community operations by connecting MCP tooling to Discord"],"not_for":["Handling sensitive or regulated workflows without additional safeguards/auditing","Production environments that require strong, documented operational guarantees (SLA, rate-limit contracts, idempotency semantics)","Use-cases where least-privilege and scope-limited permissions can’t be ensured on the Discord bot"],"best_when":"You control the Discord bot permissions and want an agent to use MCP tools to perform Discord actions (read/act) in a specific server.","avoid_when":"You need fully specified API/error/retry semantics for reliable automation, or you cannot limit bot intents/permissions to the minimum required.","alternatives":["Use a custom MCP server wrapping the Discord API directly with your own permission model","Use Discord bots directly (discord.py) and implement agent interaction via function calling without MCP","Other MCP Discord/community integrations (if available) with stronger documented contracts"],"af_score":46.8,"security_score":53.8,"reliability_score":23.8,"package_type":"mcp_server","discovery_source":["github"],"priority":"high","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-03-30T13:41:54.079901+00:00","interface":{"has_rest_api":false,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":null,"has_sdk":false,"sdk_languages":[],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":["Discord bot token via DISCORD_TOKEN environment variable"],"oauth":false,"scopes":false,"notes":"Authentication is implicit via the Discord bot token. The README instructs enabling Discord privileged intents and inviting the bot via OAuth2, but does not describe fine-grained MCP-side scopes."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"Open-source MIT package; no usage-based pricing described in the provided materials."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":46.8,"security_score":53.8,"reliability_score":23.8,"mcp_server_quality":55.0,"documentation_accuracy":55.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":60.0,"rate_limit_clarity":20.0,"tls_enforcement":60.0,"auth_strength":55.0,"scope_granularity":25.0,"dependency_hygiene":60.0,"secret_handling":70.0,"security_notes":"Uses a Discord bot token provided via environment variable (better than hardcoding). However, the provided materials do not describe MCP-side authentication/authorization, fine-grained tool scopes, secure transport guarantees for the MCP process, nor explicit guidance on logging/handling failures. Discord bot permissions/intents must be minimized to reduce blast radius for send/moderate/role actions.","uptime_documented":0.0,"version_stability":35.0,"breaking_changes_history":35.0,"error_recovery":25.0,"idempotency_support":"false","idempotency_notes":null,"pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["Discord operations can be destructive (send/moderate/delete); agents should implement confirmation and safety checks","Privileged intents and permissions may be required; insufficient permissions will cause tool failures","Message history reading is limited to 'recent' messages; agents expecting full history may fail"]}}