Skip to contentinkvault MCP Server — Install for Claude, Cursor & VS Code | MCPpediainkvault MCP Server
Local-first AI memory: search your Claude Code, Codex, Claude desktop, Pieces and browser history.
Trust scoreTrust score 55 of 100, Fair Fair trust
55 of 100 from six public signals. Nobody can buy a point.
- Listed in the official MCP registry.
- No license recorded.
How we score trust Trust breakdown
Where the 55 comes from
22 + 20 + 0 + 0 + 10 + 3 = 55. Each factor is capped, so no single signal can carry a listing.
Registry22 / 30
Active in the official MCP registry, plus a known vendor namespace.
Registry: 22 of 30 points.Maintenance20 / 20
How recently the repository saw a commit or release.
Maintenance: 20 of 20 points.Popularity0 / 20
GitHub stars and weekly downloads, on a log scale.
Popularity: 0 of 20 points.License0 / 10
A clear, OSI-style open-source license.
License: 0 of 10 points.Security10 / 10
Not archived, a secure install path, a pinned version.
Install
Pick your client, copy the config, paste it in.
~/Library/Application Support/Claude/claude_desktop_config.json
{ "mcpServers": { "sandoreclegane-inkvault": { "command": "uvx", "args": [ "inkvault" ] } }}
Security: 10 of 10 points.
Docs3 / 10
A real summary, a README with depth, listed tools.
Docs: 3 of 10 points.This server does not declare environment variables.
Tools show up when the registry metadata or the repository README lists them. GitHub enrichment fills this in when a token is configured.
About
Local-first AI memory: search your Claude Code, Codex, Claude desktop, Pieces and browser history.
FAQ
- ?What is inkvault?
- Local-first AI memory: search your Claude Code, Codex, Claude desktop, Pieces and browser history.
- ?How do I install inkvault?
- Pick a client above and copy the generated config. Cursor and VS Code also have a deep link when the server can run locally or remotely.
- ?Is inkvault official?
- No. Registry-listed is not the same as vendor-official. Read the methodology for the difference.
- ?How is the trust score calculated?
- This listing scores 55 (Fair). The formula is published on the methodology page.
Reviews
No average · 0 publishedNo reviews yet. Used it? Tell the next person how it went.
Sign into review this server.
Fi77Trust score 77 of 100, Good
Firecrawl, the context API for AI agents: search, scrape, interact with the web, plus paper search.
7.6K stars—/wk weekly downloads— tools
HR74Trust score 74 of 100, Good
Local-first agentic RAG with citations - hybrid search, reranking, multimodal document retrieval
629 stars—/wk weekly downloads— tools
MM74Trust score 74 of 100, Good
Hosted agent memory that learns from outcomes, with shared rooms. No key: mcp.mnemoverse.com/mcp
27 stars290/wk weekly downloads— tools
KS73Trust score 73 of 100, Good
Shared project memory for Claude Code, Codex and Cursor: decisions and corrections through MCP.
10 stars1.9K/wk weekly downloads— tools