Embedded memory for AI agents with SQLite FTS5, pgvector, and Neo4j graph search.
Connect Memwright to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Embedded memory for AI agents with SQLite FTS5, pgvector, and Neo4j graph search. The memwright mcp server is what makes that connection.
Full-context replay re-reads the whole conversation every turn — input tokens that grow O(n²) and a bill that compounds with every session. Attestor retrieves only what's needed: flat ~200 tokens per call, 21× fewer input tokens by turn 100, 100% recall — measured across six models, open and closed.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
Multi — agent products where many LLMs write to the same memory storeSelf — hosted deployments — your VPC, your Postgres, your Neo4jVersion — 4.1.6 (stable; greenfield rebuild — no v3 migration path)PyPI — attestorImport — attestorRepo — https://github.com/bolnet/attestorTurn — Full-context replayt24 — growingt50 — growingt100 — 8,709 tok/callRegistry — Pull addressGHCR — ghcr.io/bolnet/attestor:latestConfiguration is passed through the environment: OPENROUTER_API_KEY, PINECONE_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.
Plenty of database access servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Memwright's toolset — Multi, Self, Version and 11 more — is a fair guide to whether it matches your workflow. It is maintained by bolnet; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| Multi | agent products where many LLMs write to the same memory store |
| Self | hosted deployments — your VPC, your Postgres, your Neo4j |
| Version | 4.1.6 (stable; greenfield rebuild — no v3 migration path) |
| PyPI | attestor |
| Import | attestor |
| Repo | <https://github.com/bolnet/attestor> |
| Turn | Full-context replay |
| t24 | growing |
| t50 | growing |
| t100 | 8,709 tok/call |
| Registry | Pull address |
| GHCR | ghcr.io/bolnet/attestor:latest |
| Quay | quay.io/bolnet/attestor:latest |
| Container | Role |
{
"mcpServers": {
"memwright": {
"command": "uvx",
"args": ["attestor"],
"env": {
"OPENROUTER_API_KEY": "your-value",
"PINECONE_API_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| OPENROUTER_API_KEY | Credential the server authenticates with. | Yes |
| PINECONE_API_KEY | Credential the server authenticates with. | Yes |
Read-only SQL access to Postgres — let your assistant inspect schemas and answer questions from real data.
Manage your whole Supabase project in conversation — database, auth, storage, Edge Functions and branches.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Official MongoDB server covering data, schemas and Atlas management — from find queries to spinning up clusters.
Serverless Postgres with database branching — point your assistant at Neon and let it work on disposable copies.