Skip to main content
Glama
Sign In
Discord MCP - Discord server management MCP for AI agents

Discord MCP - Discord server management MCP for AI agents

by OrygnsCode
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Bulk delete messages

bulk_delete_messages
Destructive

Delete multiple recent Discord messages at once, optionally filtered by author or text, with a preview and confirmation token to prevent accidental removal.

Instructions

Delete many recent messages at once (2 to 100), optionally filtered by author or text. Discord cannot bulk delete messages older than 14 days. Safe to call directly: the first call returns how many it would remove, with a sample of them, plus a confirm_token; repeating the call with the token deletes them.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "channel": "<channel>"
    },
    "name": "bulk_delete_messages"
  }
}

Input Schema

NameRequiredDescriptionDefault
countNoHow many recent messages to scan. Default 50.
guildNoGuild (server) name or ID. Omit to use the default guild.
channelYesChannel name or ID.
dry_runNo
containsNoOnly delete messages containing this text.
from_authorNoOnly delete messages whose author name matches this.
confirm_tokenNoThe token from this exact action's preview. Where the app can show a confirmation dialog, calling with it asks the user there, and it happens only if they agree.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.4.2
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • addedInput schema / properties / confirm_token / description
      Added value: +"The token from this exact action's preview. Where the app can show a confirmation dialog, calling with it asks the user there, and it happens only if they agree."
  2. Changed1 schema field changedv1.3.0
    • removedInput schema / additionalProperties
      Removed value: -false
  3. First observedv1.0.2

TDQS

A4.1/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds substantial behavior beyond the destructiveHint=true annotation: the hard 14-day platform limit, the two-phase preview/confirm flow, what the first call returns (count, sample, confirm_token), and the guarantee that nothing is removed until the token is supplied. This is exactly the operational context an agent needs before invoking a destructive tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, no waste, and the most decision-relevant facts (scope, platform limit, safety/confirm flow) are front-loaded in that order. Every clause carries information the agent would otherwise have to guess.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive bulk tool with no output schema, it covers the crucial ground: safety model, confirmation mechanism, platform constraint, and filter intent. The remaining gap is dry_run, which is left unexplained in both schema and description, plus the count-range mismatch.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 86%, so the baseline is 3; the description reinforces that filters are by author or text, mapping to from_author and contains. However, its stated range of "2 to 100" conflicts with the schema's count minimum of 1, and dry_run (undocumented in the schema) is never explained in the description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource with scope: "Delete many recent messages at once (2 to 100), optionally filtered by author or text." The plural "many ... at once" implicitly separates it from the singular delete_message sibling, but no sibling is named explicitly, so it stops short of full differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear operating context: the 14-day Discord limit and the instruction that it is "safe to call directly" because the first call previews and a second call with confirm_token commits. It does not state when to prefer delete_message (single) or search_messages instead, so no explicit exclusions or named alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools