Verbative Memory MCP server
✓ VerifiedProvides an on-device, dual-layer memory system that captures and recalls distilled facts and event ledgers for AI coding agents.
Also known as verbative/verbative-memory
- Stars
- 1
- Tools
- —
- Downloads, 30 days
- 88
- Latest version
- 1.1.3
- Last commit
- Aug 17, 2026
- License
- —
What is Verbative Memory MCP?
Verbative Memory provides an on-device, dual-layer memory system that captures and recalls distilled facts and event ledgers for AI coding agents.
Summary generated from the project's README
About Verbative Memory MCP server
Verbative Memory provides an on-device memory system designed specifically for AI coding agents. It uses a dual-layer engine that combines a lossless event ledger for recording commands and test results with a layer of distilled, atomic facts like decisions and conventions. This system is intended for developers using macOS with Apple silicon or Windows 10/11 environments. It operates locally, storing all information in human-readable files within your repository to ensure no data is sent to a cloud or vendor database.
Users can integrate this server via the Claude Code CLI, pip, or any standard MCP client using stdio. While the engine and models are downloaded during the first run, subsequent recall operations function fully offline. Access requires a Verbative account under the Code Advanced plan. The system offers a wide array of tools including remember, recall, search, ask, and timeline to manage the knowledge graph and event history.
What you can do with it
- 1Reconstruct development historyAsk the agent to explain why a specific test began failing by looking at the exact command and result history.
- 2Maintain coding conventionsProvide the agent with distilled facts about project-specific decisions and architectural patterns.
Written from the project's README. Every use case is checked against a quote from it.
How to install Verbative Memory MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Verbative Memory MCP in Claude Code
$ claude mcp add verbative-memory -- npx -y verbative-memoryInstall Verbative Memory MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"verbative-memory": {
"command": "npx",
"args": [
"-y",
"verbative-memory"
]
}
}
}Install Verbative Memory MCP in VS Code
.vscode/mcp.json
{
"servers": {
"verbative-memory": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"verbative-memory"
]
}
}
}Install Verbative Memory MCP in VS Code CLI
$ code --add-mcp '{"name":"verbative-memory","type":"stdio","command":"npx","args":["-y","verbative-memory"]}'Install Verbative Memory MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"verbative-memory": {
"command": "npx",
"args": [
"-y",
"verbative-memory"
]
}
}
}Install Verbative Memory MCP in Codex
$ codex mcp add verbative-memory -- npx -y verbative-memoryInstall Verbative Memory MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.verbative-memory] command = "npx" args = ["-y", "verbative-memory"]
Install Verbative Memory MCP in Gemini CLI
$ gemini mcp add -s user verbative-memory npx -- -y verbative-memoryInstall Verbative Memory MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"verbative-memory": {
"command": "npx",
"args": [
"-y",
"verbative-memory"
]
}
}
}Automated checks
Ran Nov 15, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work · What to fix for more points
- Source repository linked and reachableverbative/verbative-memory is public and reachablegithub.com/verbative/verbative-memory ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)No licenseFinding
- Commit or release in the last yearLast commit or release 2026-08-17github.com/verbative/verbative-memory ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from verbative-memory, verbative-memoryPass
- No critical advisory in the package or its dependencies1 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubVerbative Memory
On-device memory system for AI coding agents — a dual-layer engine (distilled facts + a lossless event ledger), automatically captured and injected, exposed over MCP. Shared across agents, persistent across sessions; stored as plain, human-readable files in your repo — no memory cloud, no vendor database.
This repository is the public home for docs, install help, and issues. The engine is closed-source and ships as a sealed, compiled package — there is no source code here.
How it works — capture everything, recall selectively
- Complete capture, in two layers. Underneath sits a lossless ledger: a mechanical, no-model record of every command, edit, and test result, so "what did we run" and "when did this test start failing" are exact, replayable facts. On top, an on-device model distills that stream into atomic, typed memories — decisions, conventions, and dead ends.
- Selective recall — the two layers fused. A single recall surfaces only the handful of distilled facts that matter (ranked by semantic search and a reranker) and interleaves them, by time, with the exact ledger record around them: what you decided next to what you actually did. One answer, not a dump of the whole history.
- Self-organizing. New facts reconcile against old ones, importance decays on per-type forgetting curves, frequently-recalled facts strengthen, and recurring specifics distill into higher-level insights.
- Yours, on-device. Memories live in human-readable files in your project. Recall makes zero cloud calls.
Requirements
- macOS (Apple silicon) or Windows 10/11 (x64). (Linux is on the roadmap.)
- A Verbative account — Memory is part of the Code Advanced plan and starts with a 14-day free trial. See the plans and the Terms.
Install
Claude Code CLI — automatic capture and recall:
claude mcp add verbative-memory -- npx -y verbative-memory
pip:
pip install verbative-memory
verbative-memory login # sign in with your Verbative account
Any MCP client (mcp.json / stdio):
{ "mcpServers": { "verbative-memory": { "command": "npx", "args": ["-y", "verbative-memory"] } } }
Automatic capture and injection are built for the Claude Code CLI and Codex; any other Model Context Protocol client can call the tools manually. The first run downloads the on-device engine and models once; after that, recall runs fully offline.
More detail in docs/INSTALL.md and at verbative.de/docs/memory.
Tools
remember · recall · search · ask · list · get · pin · forget · revise ·
edit_core · feedback · related · history · timeline · events — and more. See the
docs.
Privacy
Capture, embeddings, reranking, and the knowledge graph all run locally. Your code and memories are not uploaded; the memory files stay in your project and leave your machine only if you choose to share them.
Links
- Overview — https://verbative.de/memory
- Docs — https://verbative.de/docs/memory
- Plans — https://verbative.de/pricing
- Terms — https://verbative.de/legal/terms
- Impressum — https://verbative.de/legal/impressum
Issues
Bug reports and feature requests are welcome in the issue tracker — the place for anything about the docs or the tool. For your account, licensing, or a trial, email info@verbative.de.
Verbative is a product of Cramer Digital. Not affiliated with, or endorsed by, Anthropic. Verbative works alongside Anthropic's Claude and the Claude Code CLI; those names belong to Anthropic. See LICENSE.
Verbative Memory MCP questions
How do I add Verbative Memory MCP to Claude Code?
Run claude mcp add verbative-memory -- npx -y verbative-memory in your terminal. Add --scope user to make it available in every project.
How do I add Verbative Memory MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Where is the memory data stored?
Memories are stored locally as plain, human-readable files within your project repository.
Does using this server require an internet connection?
After the initial download of the engine and models, the recall process runs fully offline.
What operating systems are supported?
The system currently supports macOS (Apple silicon) and Windows 10/11 (x64), with Linux planned for the future.
Is my code uploaded to the cloud?
No, all processes including capture, embeddings, and reranking run locally on your machine.