io.github.toonight/mnemoscope

MCPattested
v0.2.0io.github.toonightUnknownUpdated 3mo agonpmGitHub

Predict context rot, sign every agent write, tier reads. Markdown-native, 100% local.

MCP server exposing Mnemoscope's context-rot scoring, tiered reading, and signed journal tools to any Model Context Protocol–compatible client (Claude Code, Cursor, ChatGPT desktop, anything that speaks MCP over stdio). 100% local. No cloud. No telemetry. Apache-2.0. Or run via without a global install: Restart Claude Code. The four tools below are discovered automatically. Tool | Input | What it…

Attested build
A verified provenance attestation binds this artifact to the listed repository. Nobody has claimed the listing yet — this proves where the code was built, not who stands behind it.
3mo agoLast update
Package
Authorio.github.toonight
LicenseUnknown
Version0.2.0
Sourcemcp-registry
npm@mnemoscope/mcp-server
GitHubtoonight/Mnemoscope
Trust Status
A
85/100Trusted
✓Listed in Forge index+10/10
✓Identity verified · attested build+20/20
—Ed25519 publish signature+0/5
→ Included automatically when the publisher runs `forge publish`
—Domain verification+0/5
→ Publisher: host /.well-known/forge.json on the package homepage with { "publisher": "<github-login>" }
✓npm Trusted Publishing (Sigstore)+5/5
—npm maintainer match+0/5
→ Publisher: add the verified GitHub login to the npm package's maintainers (npm owner add <login>)
✓CVE scan · clean+30/30
✓Static analysis · clean+20/20
Paste into Claude Code, Cursor, or any AI assistant to fix all gaps
StatusIdentity verified
PublisherUnverified
SignatureUnsigned
Domain—
Provenance✓ Sigstore-verified · a3528fa
Dependencies✓ 60 resolved+ · none vulnerable
Tool surface4 tools · none privileged
Security scan✓ Cleanv0.2.0 · 2mo ago
EvalsNone
IndexedJun 13, 2026

Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts — it cannot prove the absence of malicious code.

About

MCP server exposing Mnemoscope's context-rot scoring, tiered reading, and signed journal tools to any Model Context Protocol–compatible client (Claude Code, Cursor, ChatGPT desktop, anything that speaks MCP over stdio). 100% local. No cloud. No telemetry. Apache-2.0. Or run via without a global install: Restart Claude Code. The four tools below are discovered automatically. Tool | Input | What it returns | | | 0–100 risk score, dominant factor, full factor breakdown, top-5 risk notes, vault…

Keywords
mcp