docs(mcp): consolidated MCP server, skills, slide builder, and evals docs#608
Draft
jordanc-relevanceai wants to merge 1 commit intomainfrom
Draft
docs(mcp): consolidated MCP server, skills, slide builder, and evals docs#608jordanc-relevanceai wants to merge 1 commit intomainfrom
jordanc-relevanceai wants to merge 1 commit intomainfrom
Conversation
Combines four drafter PRs that overlap on mcp-server.mdx and agent-skills.mdx within the Programmatic GTM section: - TSP-1091 (#535): document the relevance_trigger_agent breaking change (now async by default; use _sync suffix for synchronous behaviour) - TSP-1092 (#548): document Slide Builder via MCP — new dedicated page, cross-references from mcp-server, codex, programmatic-gtm overview, and the Chat slide-builder page - TSP-1107 (#557): document Skills API structured fields including when_to_use, with a Python code example - TSP-1164 (#598): document 19 new MCP evaluation tools — new programmatic-evals page, link from evals.mdx, expanded Evals card description, and SKILL.md tool count update (46 -> 65) Reconciled overlapping edits to agent-skills.mdx (Topics covered card group) and mcp-server.mdx (sync/async tool naming + new Slide Builder section). The original #548 targeted the old programmatic-gtm introduction.mdx path; rerouted those edits to the renamed get-started/core-concepts/programmatic-gtm.mdx file. Adds nav entries for the new slide-builder page and groups evals into its own subgroup with programmatic-evals.
Contributor
|
Preview deployment for your docs. Learn more about Mintlify Previews.
💡 Tip: Enable Workflows to automatically generate PRs for you. |
This was referenced May 5, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR consolidates 4 drafter PRs that all touch the Programmatic GTM section. Each section below is the original description from a source PR. Opening as draft for review before closing the source PRs.
Source PRs (kept open until confirmed)
relevance_trigger_agentbreaking change (async by default)when_to_useReconciliation note
Three of the four PRs edit
agent-skills.mdxand two editmcp-server.mdx. Shipping separately would force conflicts and produce a fragmented Topics covered list. Reconciled the changes in one pass so the section reads coherently.Important rerouting: #548 originally edited
integrations/mcp/programmatic-gtm/introduction.mdx, but that file was renamed toget-started/core-concepts/programmatic-gtm.mdxon main. I redirected those edits (Slide Builder card and tab) to the renamed file.PR #591 (mcp-client.mdx) stays separate — different file, no overlap.
#535 — docs(TSP-1091): update MCP server docs for relevance_trigger_agent breaking change
Summary
relevance_trigger_agentis now asynchronous (returnsconversation_idimmediately) — breaking change from previous synchronous behaviorrelevance_trigger_agent_synctool added for synchronous/blocking executionrelevance_trigger_agent_asyncis replaced byrelevance_trigger_agentChanges made
relevance_trigger_agent_syncrelevance_trigger_agent(previouslyrelevance_trigger_agent_async)relevance_trigger_agentrelevance_trigger_agent_syncfor synchronous behaviorLinear issue: https://linear.app/relevance/issue/TSP-1091/
#548 — docs(TSP-1092): document MCP Slide Builder capabilities
Summary
integrations/mcp/programmatic-gtm/slide-builder.mdxdocumenting all Slide Builder capabilities available via MCPdocs.jsonto include the new page in the Programmatic GTM navigation groupThe new page covers: quick start, all available capabilities (BrandKits, Templates, export formats, incremental building, version history), practical example prompts, working with BrandKits and Templates via MCP, exporting in PDF/Images/PPTX/JSON, troubleshooting, and what's next links.
Closes https://linear.app/relevance/issue/TSP-1092/
#557 — docs(TSP-1107): document Skills API structured fields including when_to_use
Summary
Linear issue: https://linear.app/relevance/issue/TSP-1107/
#598 — docs(TSP-1164): Add documentation for 19 new MCP evaluation tools
Summary
build/agents/build-your-agent/evals/programmatic-evals.mdx— documents the 19 new MCP tools covering the full evaluation lifecycle: managing test sets and test cases, configuring evaluator rules and tool simulations, running evaluations, and monitoring batch resultsbuild/agents/build-your-agent/evals.mdx— added a Programmatic Access section near the top linking to the new pageintegrations/mcp/programmatic-gtm/agent-skills.mdx— bumped tool count from 46 → 65, expanded the Evals card description to reflect the comprehensive new capabilitiesdocs.json— converted the flatevalsnav entry into an Evals group containing both the main page and the new programmatic-evals sub-pageContext
These docs cover the 19 new MCP tools added in RelevanceAI/relevance-api-node#13459. The new tools fill a major gap by enabling programmatic access to evals, supporting CI/CD integration and automated testing frameworks.
Linear issue: https://linear.app/relevance/issue/TSP-1164/
Test plan
/build/agents/build-your-agent/evals/programmatic-evalsLinear