Skip to content

docs(TSP-1357): add MCP cancellation tools#730

Open
claude[bot] wants to merge 1 commit into
mainfrom
docs/TSP-1357
Open

docs(TSP-1357): add MCP cancellation tools#730
claude[bot] wants to merge 1 commit into
mainfrom
docs/TSP-1357

Conversation

@claude

@claude claude Bot commented Jul 21, 2026

Copy link
Copy Markdown

Summary

  • Adds a new Cancelling executions subsection under "Handling long-running agent executions" documenting three new MCP tools added in PR #16277:
    • relevance_cancel_agent_task — cancels a running agent task; notes that the current step finishes first (no instant hard-stop)
    • relevance_cancel_workforce_task — cancels a running workforce task
    • relevance_cancel_tool_run — cancels a currently-running tool execution

Previously, MCP integrations could start and monitor tasks but had no documented way to stop them. This update fills that gap.

Linear issue: https://linear.app/relevance/issue/TSP-1357/

Document three new cancellation tools added in PR #16277:
relevance_cancel_agent_task, relevance_cancel_workforce_task,
and relevance_cancel_tool_run.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
@claude claude Bot added the docs-drafter Documentation drafted by Claude label Jul 21, 2026
@linear

linear Bot commented Jul 21, 2026

Copy link
Copy Markdown

TSP-1357

@mintlify

mintlify Bot commented Jul 21, 2026

Copy link
Copy Markdown
Contributor

Preview deployment for your docs. Learn more about Mintlify Previews.

Project Status Preview Updated (UTC)
relevanceai 🟢 Ready View Preview Jul 21, 2026, 7:05 AM

💡 Tip: Enable Workflows to automatically generate PRs for you.

@mintlify

mintlify Bot commented Jul 21, 2026

Copy link
Copy Markdown
Contributor

Preview deployment for your docs. Learn more about Mintlify Previews.

Project Status Preview Updated (UTC)
relevanceai 🟡 Building Jul 21, 2026, 7:03 AM

💡 Tip: Enable Workflows to automatically generate PRs for you.

@github-actions

Copy link
Copy Markdown
Contributor

🎯 Vibe check

Reviewed: 1 file (1 with issues, 0 clean)

Scores

Dimension Score What's holding it back
🟡 Consistency 6/10 Systematic product-term capitalization failures throughout (agents, tools, workforces, knowledge all lowercase when referring to Relevance AI platform features); one British spelling ("Cancelling").
🟢 Technical clarity 9/10 Minor: two polling-status values listed on one step (working and in progress) — verify these match actual API response values.
🟢 Non-technical clarity 9/10 FAQ provides a plain-English MCP definition; the early Warning redirecting wrong-page readers is well placed.
🟢 Structure 9/10 One callout type swap: <Note> on a preference/tip → <Tip>.

Score key: 🟢 9–10, 🟡 6–8, 🔴 1–5.

Overall vibe: The page is well-organized and technically accurate — step-by-step instructions are specific, the async execution section is genuinely useful, and the early redirect Warning is a good move. The main thing dragging it down is a consistent pattern of lowercase product terms (agents, tools, workforces, knowledge) throughout the copy; fixing those will bring the page fully in line with the house standard.

🔧 Issues (13)

British spelling

  • integrations/mcp/mcp-server.mdx:278### Cancelling executions → "Canceling executions" (American English: single L)

Product term capitalization — Agent, Tool, Workforce, Knowledge are Relevance AI proper nouns and must be capitalized when referring to the platform features

  • integrations/mcp/mcp-server.mdx:7 — "your agents, tools, and knowledge" → "your Agents, Tools, and Knowledge"
  • integrations/mcp/mcp-server.mdx:50 — "the Relevance AI tools will be available" → "the Relevance AI Tools will be available"
  • integrations/mcp/mcp-server.mdx:228 — "access tools and agents across all your projects" → "access Tools and Agents across all your projects"
  • integrations/mcp/mcp-server.mdx:238 — "agents, tools, workforces, knowledge, and more" → "Agents, Tools, Workforces, Knowledge, and more"
  • integrations/mcp/mcp-server.mdx:242 — heading ## Handling long-running agent executions → "Agent executions"
  • integrations/mcp/mcp-server.mdx:244 — "When triggering agents via MCP" → "When triggering Agents via MCP"
  • integrations/mcp/mcp-server.mdx:254 — "agents with workforce nodes" → "Agents with Workforce nodes"
  • integrations/mcp/mcp-server.mdx:259 — "Agents with workforce nodes should always use async" → "Agents with Workforce nodes"
  • integrations/mcp/mcp-server.mdx:265<Step title="Trigger the agent"> → "Trigger the Agent"
  • integrations/mcp/mcp-server.mdx:309 — "Verify that you have tools configured" → "Tools configured"
  • integrations/mcp/mcp-server.mdx:323 — "Agents with workforce nodes, multi-step chains" → "Agents with Workforce nodes"
  • integrations/mcp/mcp-server.mdx:349 — "exposes the tools and agents available" → "Tools and Agents"
🧩 Component suggestions (1)
  • integrations/mcp/mcp-server.mdx:230–232<Note> wraps a preference ("the multi-connection approach above is preferred for convenience"). That's a tip, not a note. Swap to <Tip>.
⚠️ Contradictions (1)
  • integrations/mcp/mcp-server.mdx:274 — Step 3 lists two possible in-flight statuses: `working` and `in progress`. These are likely the same state with an inconsistency in the documented values (most REST APIs use a single underscore-joined string like in_progress, not a two-word phrase). Verify against actual API response values and align to one canonical string.
🔋 Credit usage
Item Count
Files reviewed 1
Context pages read 2
Total lines processed ~464

Files read: integrations/mcp/mcp-server.mdx (352 lines), integrations/mcp/mcp-client.mdx (103 lines), integrations/mcp/agent-skills.mdx (111 lines)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

docs-drafter Documentation drafted by Claude

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant