agent: @U0AJM7X8FBRCurrent: In our docs, there is nowhere that explains our MCP#79
Open
sweetmantech wants to merge 4 commits intomainfrom
Open
agent: @U0AJM7X8FBRCurrent: In our docs, there is nowhere that explains our MCP#79sweetmantech wants to merge 4 commits intomainfrom
sweetmantech wants to merge 4 commits intomainfrom
Conversation
📝 WalkthroughWalkthroughDocs reorganized: the "MCP" page was renamed "MCP Servers" and split into Docs Search and Recoup API MCP sections; prompt_sandbox/tool schemas were removed and a new mcp-tools reference listing 40+ tools was added. Homepage, quickstart, API reference, and docs navigation were updated. Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 inconclusive)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
- Fix navigation order: authentication now appears before MCP (you need auth before MCP) - Homepage: add integration path cards (REST/MCP/CLI), clearer "what you can build" framing - Quickstart: replace Tasks example (requires existing data) with Spotify search (works immediately); add MCP card in next steps - MCP page: add ready-to-paste config snippets for Claude Desktop, Cursor, and VS Code; move tool reference after connection guides - API reference introduction: remove duplicate auth/base URL content, link to authentication guide instead Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
mcp.mdx (1)
56-104:⚠️ Potential issue | 🟠 MajorSame auth header issue in Cursor, VS Code, and TypeScript examples.
All remaining connection examples also use
Authorization: Bearerformat. Once the correct authentication method is confirmed, update all four config snippets consistently.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@mcp.mdx` around lines 56 - 104, Update the three connection examples (.cursor/mcp.json, ~/.cursor/mcp.json, .vscode/mcp.json, and the TypeScript StreamableHTTPClientTransport requestInit headers) to use the confirmed authentication header format instead of "Authorization: Bearer YOUR_API_KEY": locate the JSON snippets for "mcpServers"/"servers" and the TypeScript transport construction (StreamableHTTPClientTransport and its requestInit.headers) and replace the "Authorization" header value consistently with the agreed scheme (e.g., the exact header name and token prefix provided by the auth spec) across all examples.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@quickstart.mdx`:
- Around line 29-51: Update all Spotify search examples to use the correct query
parameter name `q` instead of `query`: change the curl example URL parameter in
the curl command, update the requests.get params object in the Python snippet
(replace params={"query": "Drake", "type": "artist"} with params={"q": "Drake",
"type": "artist"}), and modify the fetch URL in the JavaScript example to use
?q=Drake&type=artist; ensure every occurrence of "query" in these three examples
is replaced with "q".
---
Outside diff comments:
In `@mcp.mdx`:
- Around line 56-104: Update the three connection examples (.cursor/mcp.json,
~/.cursor/mcp.json, .vscode/mcp.json, and the TypeScript
StreamableHTTPClientTransport requestInit headers) to use the confirmed
authentication header format instead of "Authorization: Bearer YOUR_API_KEY":
locate the JSON snippets for "mcpServers"/"servers" and the TypeScript transport
construction (StreamableHTTPClientTransport and its requestInit.headers) and
replace the "Authorization" header value consistently with the agreed scheme
(e.g., the exact header name and token prefix provided by the auth spec) across
all examples.
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: 65379075-2f88-4c4a-bebf-70d320933bd5
📒 Files selected for processing (5)
api-reference/introduction.mdxdocs.jsonindex.mdxmcp.mdxquickstart.mdx
✅ Files skipped from review due to trivial changes (1)
- docs.json
…rate tool reference - Rewrite mcp.mdx with Tabs, Steps, CardGroup, Info/Warning callouts - Extract tool reference into dedicated mcp-tools.mdx page - Add mcp-tools to navigation in docs.json Made-with: Cursor
The OpenAPI spec defines the parameter as `q`, so the quickstart examples would return 400 errors with `query`. Made-with: Cursor
There was a problem hiding this comment.
🧹 Nitpick comments (1)
mcp-tools.mdx (1)
14-136: Consider adding a quick-jump index at the top for faster navigation.Given the page length, a compact category index (anchor links or Mintlify cards) would improve scan speed on desktop/mobile.
As per coding guidelines: "Keep documentation content concise and scannable."
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@mcp-tools.mdx` around lines 14 - 136, Add a compact "quick-jump" index at the top that links to each major category heading (e.g., Artists, Chats, Tasks, Pulses, Catalogs & Songs, Spotify, YouTube, Search & Research, Images, Video, Audio, Files & Knowledge, Communication, Segments, Sandboxes, Utilities) using anchor links that target the existing markdown headings (e.g., "## Artists") so users can jump directly to the tool tables like `create_new_artist`, `get_chats`, `get_tasks`, `select_catalogs`, `get_spotify_search`, `youtube_login`, `search_web`, `generate_image`, `generate_sora_2_video`, `transcribe_audio`, `create_knowledge_base`, etc.; keep the index compact and responsive (single-line pills or a collapsible mobile summary) so it remains scannable on desktop and mobile.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Nitpick comments:
In `@mcp-tools.mdx`:
- Around line 14-136: Add a compact "quick-jump" index at the top that links to
each major category heading (e.g., Artists, Chats, Tasks, Pulses, Catalogs &
Songs, Spotify, YouTube, Search & Research, Images, Video, Audio, Files &
Knowledge, Communication, Segments, Sandboxes, Utilities) using anchor links
that target the existing markdown headings (e.g., "## Artists") so users can
jump directly to the tool tables like `create_new_artist`, `get_chats`,
`get_tasks`, `select_catalogs`, `get_spotify_search`, `youtube_login`,
`search_web`, `generate_image`, `generate_sora_2_video`, `transcribe_audio`,
`create_knowledge_base`, etc.; keep the index compact and responsive
(single-line pills or a collapsible mobile summary) so it remains scannable on
desktop and mobile.
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: 1d963e8a-b388-4e31-89f6-fbaabcd71899
📒 Files selected for processing (3)
docs.jsonmcp-tools.mdxmcp.mdx
✅ Files skipped from review due to trivial changes (2)
- docs.json
- mcp.mdx
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@quickstart.mdx`:
- Around line 57-71: The example JSON includes an extra "status" field that is
not part of the OpenAPI schema for SpotifySearchResponse; remove the "status":
"success" entry and ensure the example only contains the allowed top-level
properties (e.g., "artists", "albums", "tracks", "playlists") and valid artist
object fields (id, name, followers, popularity, genres, image) so the example
matches the SpotifySearchResponse schema.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
Comment on lines
57
to
71
| ```json | ||
| { | ||
| "status": "success", | ||
| "tasks": [ | ||
| "artists": [ | ||
| { | ||
| "id": "550e8400-e29b-41d4-a716-446655440000", | ||
| "title": "Daily Fan Report", | ||
| "prompt": "Generate a summary of new fans from the past 24 hours", | ||
| "schedule": "0 9 * * *", | ||
| "account_id": "123e4567-e89b-12d3-a456-426614174000", | ||
| "artist_account_id": "987fcdeb-51a2-3b4c-d5e6-789012345678", | ||
| "enabled": true | ||
| "id": "3TVXtAsR1Inumwj472S9r4", | ||
| "name": "Drake", | ||
| "followers": 88000000, | ||
| "popularity": 96, | ||
| "genres": ["canadian hip hop", "rap"], | ||
| "image": "https://i.scdn.co/image/..." | ||
| } | ||
| ] | ||
| } | ||
| ``` |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
# Check the OpenAPI spec for the actual Spotify search response schema
cat api-reference/openapi.json | jq '.paths["/api/spotify/search"].get.responses["200"].content["application/json"].schema'Repository: recoupable/docs
Length of output: 117
🏁 Script executed:
cat api-reference/openapi.json | jq '.components.schemas.SpotifySearchResponse'Repository: recoupable/docs
Length of output: 637
Remove the "status" field from the example response.
The "status": "success" field in the example (line 60) does not exist in the actual OpenAPI schema for SpotifySearchResponse. The schema only defines artists, albums, tracks, and playlists properties. Update the example to match the actual API response structure.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@quickstart.mdx` around lines 57 - 71, The example JSON includes an extra
"status" field that is not part of the OpenAPI schema for SpotifySearchResponse;
remove the "status": "success" entry and ensure the example only contains the
allowed top-level properties (e.g., "artists", "albums", "tracks", "playlists")
and valid artist object fields (id, name, followers, popularity, genres, image)
so the example matches the SpotifySearchResponse schema.
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
2 participants
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.
Automated PR from coding agent.
Prompt: @U0AJM7X8FBRCurrent: In our docs, there is nowhere that explains our MCP server or tool list. Expected: Our docs should clearly explain our MCP server and our tools. Note: there IS a MCP tab but it links to the code for the mintify search_recoup server - which is helpful, but a different server. We should explain both, the server to search our docs, and our actual MCP server that calls our tools.
Summary by CodeRabbit