Resolves the PR #1189 conflict against its base. Both branches edited
apps/mcp/src/widget/{components/WorkspaceCard.tsx,design/tokens.css};
dalat-v1's dark-mode-readability tweak is superseded by the full widget
redesign, so both are resolved to the redesigned versions (which already
carry the memory/memories wording).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Rebuild the widget's visual system around the console's real language:
cool-neutral surfaces in light and dark, the inset-shadow signature on
form fields, the file dropzone, and the workspace select, one restrained
blue accent, DM Sans. Remove the blue glow blobs, card/graph gradients,
grid backgrounds, and the v1-v4 variant system.
- Picker is a framed, scrollable list; the active row is marked by color
(no tick or rail), so the trailing badge stays aligned across rows.
- Save/Upload use Nova's insideOut near-black pill for the primary action.
- Success/confirmation drop the memory/document id and show the workspace
as a calm accent-dot chip instead of a blue-on-blue badge.
- Graph re-reads its palette whenever the document theme flips, so light
mode no longer renders dark node fills and control chrome.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- Fix CSS specificity order: move .mcp-widget-glow base rule before
override selector to satisfy noDescendingSpecificity
- Remove invalid aria-label from header element
- Add aria-hidden="true" to decorative SVG instead of role="img"
- Format multi-line shadow values on single lines per Biome
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Make the widget fall back to dark tokens when the host does not provide an explicit theme, and expand workspace memory count labels from mem/mems to memory/memories.
Co-authored-by: Ishaan Gupta <ishaankone@gmail.com>
Make the widget fall back to dark tokens when the host does not provide an explicit theme, and expand workspace memory count labels from mem/mems to memory/memories.
Co-authored-by: Ishaan Gupta <ishaankone@gmail.com>
Resolve MCP revamp conflicts by keeping the new server layout, deleting legacy root MCP files, and carrying forward API timeout handling into the new auth/client modules.
Consumers think in "spaces", not "container tags". Renames the tool to
listSpaces and updates its description + text output to say "spaces".
Internal plumbing is unchanged: the client method listContainerTags() and
the structuredContent.containerTags key (widget contract) keep their names.
Functionality unchanged; just the name. The DO class is now SupermemoryMCP, which matches the existing supermemory-mcp worker's v1 migration -> the cutover is a no-op, no DO session reset. Demo/mock 'enterprise buyers' text left as-is.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Replaces the old apps/mcp with the enterprise-mcp code (functionality unchanged). package.json: worker supermemory-mcp, catalog deps pinned to explicit versions, portless dev:app. wrangler: name supermemory-mcp, route mcp.supermemory.ai, DO EnterpriseMCP. Builds + boots + OAuth discovery/401/worker-to-api verified locally.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
## What
Makes the MCP `recall` tool render memories the same way the console **playground** does — rich, scored, relation-aware output — instead of the old flat `### Memory N (NN% match)` list.
The playground pattern is: **profile + rich search → one shared `formatMemories` formatter → feed to the model.** This ports that into the standalone MCP server.
## Changes
- **`format.ts`** (new) — `formatMemories`, lifted verbatim from the playground. Pure, dependency-free. Renders similarity scores, `agg`/`chunk` markers, related-memory arrows (`←` parent, `→` child, `~` related), attached document summaries, and temporal context.
- **`client.ts`** — `SupermemoryClient.search()` now accepts the playground's retrieval knobs (`searchMode` / `rerank` / `rewriteQuery` / `include`) and **stops discarding** the rich response fields (`context`, `documents`, `metadata`, `isAggregated`) during normalization, so the formatter has data to render.
- **`server.ts` (`handleRecall`)** — retrieves memories via `client.search()` with `include: { documents, relatedMemories }`, prepends the user's profile (stable + recent facts) when `includeProfile` is set, and renders memories through `formatMemories`. Output capped at `MAX_RECALL_CHARS`.
## How it maps to the playground
| | Playground | MCP (this PR) |
|---|---|---|
| Profile | injected into its own system prompt (`<user_profile>`) | prepended to `recall` output / exposed via `context` prompt |
| Search | hook pre-fetch **or** tool | `recall` tool (model-triggered) |
| Formatting | `formatMemories` → system prompt | `formatMemories` → `recall` tool result |
## Testing
Verified end-to-end against a local API + local MCP, driven through a real MCP client (and Claude Desktop). `recall` now returns scored memory blocks with `Source:`/`Document:` lines and the legend header. Existing e2e assertions remain compatible (they match `## User Profile` / `## Relevant Memories`, both still emitted).
## Notes
- One deliberate gap vs the playground: `aggregate` — the public SDK's `search.memories` doesn't expose it, so no `agg` synthesis blocks. Relation arrows render only when memories actually have linked parent/child versions.
- Possible follow-up: expose the `include` / `rerank` knobs as `recall` tool params so callers can toggle relations/documents per call.
- Pre-existing `tsc` errors in `server.ts` (dual `@modelcontextprotocol/sdk` install) and `mcp-app.ts` (DOM `lib`) are unrelated to this change — confirmed by an unchanged baseline.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
---
**Session Details**
- Session: [View Session](https://supermemory.us1.vorflux.com/agent-sessions/c616fc88-a725-4961-9011-712bce740601)
- Requested by: Sreeram Sreedhar (sreeram@supermemory.com)
- Address comments on this PR. Add `(aside)` to your comment to have me ignore it.
End-to-end tests that drive the deployed Supermemory MCP over streamable HTTP (no mocks):
- discovery: handshake + tool/resource/prompt listing
- identity: whoAmI, listProjects
- memory: save -> recall round-trip, profile variants, forget, container scoping
- graph/resources/prompts: memory-graph, fetch-graph-data, profile/projects, context
- oauth: protected-resource discovery chain, dynamic client registration,
token-endpoint negatives, and a real refresh -> access token round-trip
- auth: GET / info, 401 on missing/invalid token
- root-scope: x-sm-project scoping behavior
Tests skip without SUPERMEMORY_API_KEY (OAuth tier-D skips without its token env vars) so CI is safe without secrets. Adds vitest + a test:e2e script and documents running + the OAuth flow in apps/mcp/README.md.
## Summary
Fixes MCP OAuth discovery so the client-server handshake actually validates against the **MCP 2025-06-18 authorization spec** (which adopts RFC 9728 Protected Resource Metadata + RFC 8707 Resource Indicators).
Previously, a client connecting to `https://mcp.dev.supermemory.ai/mcp` would receive `resource: "https://mcp.supermemory.ai"` (bare host, prod fallback) and reject the connection:
> Protected resource https://mcp.supermemory.ai does not match expected https://mcp.dev.supermemory.ai/mcp (or origin)
## Changes
- **`resource` now includes the `/mcp` endpoint path** — the spec wants the canonical MCP server URI, and the bundled `@modelcontextprotocol/sdk` reference implementation emits the same shape (`new URL(rsPath, base).href`). Bare-host worked with lenient clients that fell back to origin-matching; strict clients rejected it.
- **Path-suffixed metadata route** added at `/.well-known/oauth-protected-resource/mcp` alongside the bare path. The SDK's `metadataHandler` mounts under the resource path, so this matches what spec-strict clients probe first.
- **`WWW-Authenticate`'s `resource_metadata` URL** points to the canonical full URL (`https://host/.well-known/oauth-protected-resource/mcp`).
- **Centralized base-URL derivation** in a new `mcpBaseUrl()` helper, with priority:
1. `MCP_URL` env var — set by portless dev script so dev requests resolve to the tunneled host, not whatever the local proxy sticks in `Host`
2. `x-forwarded-host` / `host` request headers
3. `https://mcp.supermemory.ai` last-resort fallback (only hit when the worker can't see the inbound host at all)
## Production impact
`MCP_URL` is dev-only (not in `wrangler.jsonc` vars), so prod falls through to the `Host` header → `https://mcp.supermemory.ai/mcp`. The wire change in prod is that `resource` now ends with `/mcp` instead of being bare — spec-correct, what strict clients require, and tolerated by lenient ones.
## Contributor DX
Added `apps/mcp/.dev.vars.example` documenting `API_URL`, `MCP_URL`, and `POSTHOG_API_KEY` for contributors running plain `wrangler dev` without portless.
## Test plan
- [x] `curl https://mcp.dev.supermemory.ai/.well-known/oauth-protected-resource` returns `resource: https://mcp.dev.supermemory.ai/mcp`
- [x] `curl https://mcp.dev.supermemory.ai/.well-known/oauth-protected-resource/mcp` returns the same payload
- [x] 401 from `/mcp` carries `WWW-Authenticate: Bearer resource_metadata="…/oauth-protected-resource/mcp"`
- [x] MCP client (vscode extension) connects successfully — previously failed with the resource-mismatch error
- [ ] Verify in prod that bare-host clients continue to work after deploy
