Intelligence — summarize a busy channel

Intelligence: summarize a busy channel

The intelligence_summarize_channel tool turns “what did I miss in #support?” into a structured summary — without the server holding any LLM API key. It does this through MCP sampling: the tool calls back to the host client’s LLM via the requestSampling capability, then parses the response.

Use case

A support engineer says: “TL;DR what happened in #support over the last 50 messages, then post the summary to #ops.”

Two tool calls. The first asks the host’s own LLM (Claude, GPT, whatever) to do the heavy lifting; the second posts the result. discord-mcp ships zero API keys and never makes outbound LLM requests on your behalf.

Note

Sampling capability is opt-in per client. Claude Desktop, Cursor, ChatGPT, Cline, Continue, and Windsurf currently report “no sampling” during initialization. When the capability is missing the tool falls back to returning the raw messages plus a _meta.fallback: 'host_llm_should_process' hint, telling the host LLM to do the summarization itself in the next turn. Either path produces a usable summary; the difference is who runs the inference.

Tool flow

1. Read the channel (optional).

   intelligence_summarize_channel fetches messages internally, so this step is only needed if you want to inspect the raw stream first or pass a custom subset. For the standard flow, skip straight to step 2.

   {
     "name": "messages_read",
     "arguments": {
       "channel_id": "222233334444555566",
       "limit": 50
     }
   }

2. Summarize.

   The tool returns a structured object with summary, key_topics, and action_items. The style parameter controls tone: bullet (default), paragraph, or executive.

   Input

   {
     "name": "intelligence_summarize_channel",
     "arguments": {
       "channel_id": "222233334444555566",
       "limit": 50,
       "style": "bullet"
     }
   }

   Output (sampling supported)

   {
     "summary": "- Three users hit the new SSO flow with expired refresh tokens.\n- @alice shipped a hotfix at 14:22 UTC; @bob verified.\n- Open: customer #88241 still cannot log in — escalated to on-call.",
     "key_topics": ["sso", "refresh tokens", "hotfix deploy"],
     "action_items": ["follow up with customer #88241"],
     "message_count_used": 50,
     "sampling_used": true
   }

   Output (fallback)

   {
     "summary": "[sampling unavailable — host LLM should summarize from raw_messages]",
     "key_topics": [],
     "action_items": [],
     "message_count_used": 50,
     "sampling_used": false,
     "_meta": {
       "fallback": "host_llm_should_process",
       "intent": "summarize",
       "raw_messages": [
         { "id": "888899990000111101", "author": "alice", "content": "shipping the SSO hotfix now" },
         { "id": "888899990000111102", "author": "bob", "content": "lgtm, will verify on staging" }
       ]
     }
   }

3. Post the summary.

   {
     "name": "messages_send",
     "arguments": {
       "channel_id": "333344445555666677",
       "content": "## Support recap\n\n- Three users hit the new SSO flow with expired refresh tokens.\n- @alice shipped a hotfix at 14:22 UTC; @bob verified.\n- Open: customer #88241 still cannot log in — escalated to on-call."
     }
   }

   When the tool returned the fallback envelope, the host LLM should instead read _meta.raw_messages, generate the summary itself in the next turn, then call messages_send with that content.

Why this design

• Zero API keys to manage. The server has no OPENAI_API_KEY field, no budget telemetry, no key rotation playbook. The agent’s existing model subscription does the work.
• Privacy. Channel content never leaves the path the user already trusts (their MCP client → their LLM). discord-mcp doesn’t proxy text to a third-party inference provider.
• Graceful degradation. Clients without sampling still get a usable result via the fallback envelope — the agent just does the inference one turn later.

Style options

style	Output shape
bullet (default)	Markdown bullet list, scannable
paragraph	Two-to-three sentence paragraph
executive	Single-sentence headline + 3-bullet body, written for skim-readers

See also

• intelligence_summarize_channel — full schema and fallback envelope.
• messages_read — inspect raw messages before summarizing.
• messages_send — post the summary back.
• intelligence_classify_messages, intelligence_moderate_content — sibling sampling-based intelligence tools.
• Architecture: MCP sampling — how the fallback envelope is constructed.