feat(mcp): add get_profile and use snake_case for public tools

[Dhravya]

search_memory was fetching and dumping the full space profile on every recall. That burns tokens even when the model only needed matching memories.

This splits the two:

• search_memory returns matching memories only. includeProfile is gone.
• New get_profile returns stable and recent profile facts for the active (or named) space.
• Tool descriptions tell the model to search first, then call get_profile if it still needs who-the-user-is / preferences / recent context.

Public model tools are snake_case so Claude/Codex server prefixes stay readable:

search_memory, get_profile, add_memory, list_documents, get_document, list_memories, list_spaces, who_am_i

Widget tools stay kebab-case (select-space, guided-save).

who_am_i stays account identity and access. The supermemory://profile resource is unchanged.

[mintlify]

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

Project	Status	Preview	Updated
supermemory	🟢 Ready	View Preview	Sep 12, 2026, 11:36 PM

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

[claude]

Claude finished @Dhravya's task in 1m 22s —— View job

---

Reviewing PR #1665

• Fetch PR diff and existing review comments
• Analyze changes for bugs, security issues, and logic errors
• Review the new get_profile tool implementation
• Check tool renaming consistency (snake_case)
• Submit review findings

---

Overview: Splits profile retrieval from search_memory into a dedicated get_profile tool to reduce token usage when profile context isn't needed, and renames public model tools to snake_case.

Issues found: None — this looks good to ship.

The implementation is clean:

• get_profile correctly reuses the existing getProfile() client method (called without a query) that's already used in resources/profile.ts and prompts/context.ts
• Tool renames to snake_case are consistently applied across all 27 changed files with no lingering references to old camelCase names
• The searchMemoryOutputSchema keeps profile as optional for backward-compatible output validation
• Tests cover both the happy path and empty profile edge case ("No profile facts are available")
• E2E tests, discovery tests, and docs are all updated consistently
• Error handling follows the existing pattern with try/catch + deps.errorResult()

Score: 10/10

---

[cloudflare-workers-and-pages]

Deploying with    Cloudflare Workers

The latest updates on your project. Learn more about integrating Git with Workers.

Status	Name	Latest Commit	Updated (UTC)
✅ Deployment successful! View logs	supermemory-mcp	b9bfa7f	Sep 13 2026, 11:45 PM

[cloudflare-workers-and-pages]

Deploying with    Cloudflare Workers

The latest updates on your project. Learn more about integrating Git with Workers.

Status	Name	Latest Commit	Preview URL	Updated (UTC)
✅ Deployment successful! View logs	supermemory-app	b9bfa7f	Commit Preview URL Branch Preview URL	Sep 13 2026, 11:45 PM

[claude]

Overview: Splits profile retrieval from search_memory into a dedicated get_profile tool to reduce token usage when profile context isn't needed.

Issues found: None — this looks good to ship.

The implementation is clean:

• get_profile correctly reuses the existing getProfile() client method that's already called without a query in resources/profile.ts and prompts/context.ts
• The searchMemoryOutputSchema keeps profile as optional for backward-compatible output validation
• Tests cover both the happy path and empty profile edge case
• E2e tests, discovery tests, and docs are all updated consistently
• Error handling follows the existing pattern with try/catch + deps.errorResult()

Score: 10/10

[claude]

Overview: Splits profile retrieval from searchMemory into a dedicated getProfile tool to reduce token usage when profile context isn't needed.

Issues found: None — this looks good to ship.

The implementation is clean:

• getProfile correctly reuses the existing getProfile() client method (called without a query) that's already used in resources/profile.ts and prompts/context.ts
• Tool renames (search_memory → searchMemory, add_memory → addMemory) are breaking changes but appear intentional per PR description to align with Cursor/Hermes naming
• The searchMemoryOutputSchema keeps profile as optional for backward-compatible output validation
• Tests cover both the happy path and empty profile edge case
• E2e tests, discovery tests, and docs are all updated consistently
• Error handling follows the existing pattern with try/catch + deps.errorResult()

Score: 10/10

[claude]

Overview: Splits profile retrieval from search_memory into a dedicated get_profile tool to reduce token usage when profile context isn't needed.

Issues found: None — this looks good to ship.

The implementation is clean:

• get_profile correctly reuses the existing getProfile() client method (called without a query) that's already used in resources/profile.ts and prompts/context.ts
• Tool renames to snake_case (listSpaces → list_spaces, whoAmI → who_am_i, etc.) are breaking changes but appear intentional per the commit history
• The searchMemoryOutputSchema keeps profile as optional for backward-compatible output validation
• Tests cover both the happy path and empty profile edge case
• E2e tests, discovery tests, and docs are all updated consistently
• Error handling follows the existing pattern with try/catch + deps.errorResult()

Minor note: The PR description mentions camelCase (searchMemory, getProfile) but the final code uses snake_case (search_memory, get_profile). The commit history shows this was intentional (commit 37ce918 → 7616c85), so the description is just outdated.

Score: 10/10