sovseal — Private AI Memory
https://server.smithery.ai/sovseal/mcp-server/mcpGive Claude, Cursor, and every MCP client one shared memory that never leaves your machine. On-device vector search via LanceDB + Transformers.js (384-dim embeddings), AES-256-GCM client-side encryption, and write-behind ciphertext sync. ### What you can do 🧠 **Store memory** — embed and persist any context fact on-device. Automatic de-duplication, PII redaction, and write-behind encrypted sync. 🔍 **Recall memory** — semantic search over stored context. 10 ms warm recall, 0 RTT reads. Network is never on the read path. 📋 **Briefing context** — auto-summarized, reinforcement-aware briefing of procedural and semantic memories for bootstrapping new conversations. ### Tools - `store_memory` — embed content on-device (384-dim ONNX) → write local LanceDB → return. Ciphertext sync runs write-behind; nothing blocks. - `recall_memory` — embed query (LRU-cached) → vector search local LanceDB → top-K by L2 distance. 0 RTT. ### Resources - `sovseal://context/briefing` — summarized, reinforcement-aware briefing for conversation bootstrap ### How it stays private - **AES-256-GCM** client-side encryption with 96-bit random IV per snapshot - 256-bit key stays in `~/.sovseal/config.json` (mode 0600) — server only sees ciphertext - **Verified Semantic Recall (VSR)** — every load re-derives SHA-256 and fails closed on mismatch - **Packet-Capture Guarantee** — run Wireshark against the server; if you find unencrypted context on the wire, the software is free forever ### Performance | Workload | Operation | p50 | p95 | | --- | --- | --- | --- | | 10K records · 1K queries | recall_memory (warm) | 6.1 ms | 10.4 ms | | Single write | store_memory | 3.8 ms | 7.2 ms | **No API key required.** Zero cloud dependency for local operations. Replaces: Mem0 • Zep • custom SQLite memory • in-context window stuffing
MCP readiness
Readiness is how fully this listing follows its protocol and how it behaved in our probes over 30 days. It is shown for reference and does not move it in search. Search order and leaderboards use the separate quality grade (here B, 79.9/100), which weighs availability, conformance, p95 speed and descriptor. How the two differ
| Valid MCP handshake | 10/10 | initialize and tools/list both answered. |
| Live MCP endpoint | 25/25 | Endpoint answers the MCP initialize handshake (1355 ms). |
| Protocol revision | 5/10 | Speaks MCP 2024-11-05, 4 revision(s) behind 2026-07-28. |
| Signed descriptor | n/a | No MCP standard defines a signed server descriptor. |
| Uptime (30 days) | 15/15 | 30/30 probes succeeded over 30 days (100%). |
| Tool declaration | 5/10 | Lists 2 tool(s) with descriptions. |
| Verified identity | 5/10 | Publisher declared (repository, package or homepage); claim this listing to verify domain control. |
| Freshness + modern flags | 4/5 | seen in a source within 7 days. |
| Auth declaration | 2/5 | Declares credential scheme: smithery_api_key. |
Compared with peers
Against 53,039 reachable MCP servers in our daily snapshot (2026-11-12 06:46 UTC). Display only; it does not change search order.
- Readiness
- Higher than 40% of peers
- This listing 79 · peer median 81
- Latency
- Faster than 48% of peers
- This listing 342 ms · peer median 326 ms
Where it loses the most points, and how to win them back
- Protocol revision −5
— Support the current protocol revision.
Now: Speaks MCP 2024-11-05, 4 revision(s) behind 2026-07-28.
- Tool declaration −5
— Declare every tool with a description and input schema.
Now: Lists 2 tool(s) with descriptions.
- Verified identity −5
— Claim the listing and prove control of its domain.
Now: Publisher declared (repository, package or homepage); claim this listing to verify domain control.
Listed in
Directories this entry was found in.
How to connect
https://server.smithery.ai/sovseal/mcp-server/mcp
curl -X POST https://server.smithery.ai/sovseal/mcp-server/mcp \
-H 'Content-Type: application/json' \
-H 'Accept: application/json, text/event-stream' \
-d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{}}'