Watchlist tracking
Reviewed for relevance and future tracking value.
MCP100 Assessment
Watchlist / Tracking
Why we’re tracking it
Follow deployment and storage changes because hosted memory handling is central
Reviewed · Documentation review; complete setup workflow not independently tested
Best fit
Self-hosted semantic memory shared across multiple AI tools
What we know
Self-hosted memory layer on Cloudflare Workers/D1/Vectorize that lets multiple MCP-compatible AI tools share persistent personal/team context.
Maintenance / activity evidence
- Observed (UTC)Merge pull request 383 from rahilp/release/4.0.0
Tracking evidence observed Oct 5, 2026. These dated signals do not establish current maintenance. Reviewed enrichment confidence: high.
Verification gaps / watch-outs
- Installation and comprehensive security have not been independently audited.
- Personal/team layer permissions and connected integrations. Writes: Store/update/delete memory depending on tools.
- Deployment-specific.
- Sensitive access: Long-lived personal/team memory, Integration credentials
- Self-hosting improves control, but this is durable centralized memory and should be protected like a knowledge database.
Full authority, access and evidence limits are available in Review context and Access & risk.
Popularity
786 repository stars
Stars observed Sep 25, 2026.
Preserve any already-reviewed adoption metrics in MCP100. Batch 4 did not refresh package downloads because the package-stats provider had insufficient credits.
Preserve any already-reviewed adoption metrics in MCP100. Batch 4 did not refresh package downloads because the package-stats provider had insufficient credits.
All limitations / Review context
What MCP memory operations and data-hosting boundaries are documented?
The bounded assessment reviewed the official README, repository notices, security policy path, and security page for known material public-tracking blockers. No such blocker was identified. This is a public-tracking assessment, not an installation safety certification.
- Self-hosting improves control, but this is durable centralized memory and should be protected like a knowledge database.
- Personal/team layer permissions and connected integrations.
- Deployment-specific.
- Project states data remains in the user's Cloudflare account and is not visible to maintainers.
- Reviewed write actions: Store/update/delete memory depending on tools
- Sensitive access: Long-lived personal/team memory, Integration credentials
- Installation, client compatibility and comprehensive security have not been independently audited. Authentication and access depend on the configured services.
- A project-specific SECURITY.md policy was not available at the fetched official path; the review remains limited to published repository notices.
- No installation, runtime, client matrix, or complete tool-contract audit was performed in this review.
- The fetched official SECURITY.md path returned HTTP 404; it was not treated as positive evidence.
- Cloudflare account/infrastructure required for hosted memory.
- Memories persist in operator-owned Cloudflare resources.
Original activity observations
- 2026-10-03T13:13:25Z: Merge pull request 383 from rahilp/release/4.0.0
Technical identity
github.com/rahilp/second-brain-cloudflare- Exact implementation source
- https://github.com/rahilp/second-brain-cloudflare ↗
- Reviewed resource type
- MCP Server
- Repository identity
- rahilp/second-brain-cloudflare
Evidence & Sources
- Evidence basis
- Recorded source evidence
- Setup runtime verification
- Not independently runtime-tested by MCP100 for this setup workflow.
Reviewed · Latest source observation
- GitHub repository ↗
rahilp/second-brain-cloudflare
Recorded repository material and project history.
Setup · Watchlist
Install & Agents
Publisher instructions.
Source evidence observed .
Additional setup details required — see the specific gaps below.
Install / connect
Publisher instructionsSecond Brain deploys a Cloudflare Worker with MCP access; official desktop app sets it up.
Configure / authenticate
MCP100 setup guideDownload official Second Brain desktop release for macOS/Windows, authorize Cloudflare and follow guided Worker deployment plus MCP client connection. Advanced self-host route: `npm install`, `npm run deploy` with Cloudflare resources configured as in publisher Setup Guide; do not conflate with one-click desktop route.
Check connection
Suggested checkVerify deployment in Second Brain dashboard and use `list_teams` / read-only tool after OAuth; Worker HTTP health alone does not prove authenticated MCP access.
Remove / uninstall / revoke
Suggested checkIn the MCP client remove the deployed Cloudflare Worker endpoint or disconnect its OAuth connector. For self-hosted deployments disable/remove the Worker route in Cloudflare separately; deleting a client registration does not delete D1/R2/Vectorize data.
Client unregistration, program uninstall, persistent-data deletion, and credential revocation must be treated separately.
Official Documentation & Sources
What it does
Self-hosted memory layer on Cloudflare Workers/D1/Vectorize that lets multiple MCP-compatible AI tools share persistent personal/team context.
- Capability
- Files & Knowledge
- Resource type
- MCP Server
- Best fit
- Self-hosted semantic memory shared across multiple AI tools
Representative uses
- Store and semantically recall memories
- Share team memory layers
- Connect Claude/ChatGPT/Cursor/Codex
- Use desktop-assisted deployment
Limitations
- Cloudflare account/infrastructure required for hosted memory.
- Memories persist in operator-owned Cloudflare resources.
Reviewed access
Access & risk
Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.
- Authentication
- Deployment-specific.
- Permissions
- Personal/team layer permissions and connected integrations.
- Data handling
- Project states data remains in the user's Cloudflare account and is not visible to maintainers.
- Cost
- free
- Risk and cautions
- Self-hosting improves control, but this is durable centralized memory and should be protected like a knowledge database.
Access scope and cautions
- Write actions
- Store/update/delete memory depending on tools
- Sensitive access
- Long-lived personal/team memory Integration credentials
- Risk level
- moderate
FAQ
Based on reviewed evidence as of 2026-10-06. Watchlist tracking is not a recommendation or a security certification.
Which tasks are documented for this implementation?
What authentication is documented?
Can it modify data or perform write operations?
What data-handling boundary should I consider?
What limitations and risks should I check before use?
Is this an official MCP?
Rahil P is listed as Community implementation in MCP100’s current evidence.