
Mnemoscope
Exposes four MCP tools to monitor and protect Markdown vaults used as agent memory. Predict_rot scores your corpus on five context degradation factors before you inject it into an LLM. Get_tiered_read splits notes into working, episodic, and semantic tiers based on recency. Record_journal and read_journal maintain an Ed25519-signed, hash-chained audit log of every agent write, which you verify with the CLI to catch tampering. Ships with a Claude Code PostToolUse hook that passively signs writes as they happen. Useful when you're growing a vault with an agent over months and need to know whether the corpus is rotting, what subset to load, and whether anyone has modified the history.
- tools
- 4
- transport
- STDIO
- last updated
- Apr 28, 2026
Tools
4 toolsPublic tool metadata for what this MCP can expose to an agent.
predict_rotScore 0–100, dominant factor, full factor breakdown, top 5 risk notes, vault stats
Score 0–100, dominant factor, full factor breakdown, top 5 risk notes, vault stats
No parameter schema in public metadata yet.
get_tiered_readNote paths grouped into working / episodic / semantic
Note paths grouped into working / episodic / semantic
No parameter schema in public metadata yet.
record_journalThe signed entry, including its sig, keyFingerprint, and prevHash
The signed entry, including its sig, keyFingerprint, and prevHash
No parameter schema in public metadata yet.
read_journalAll journal entries, or a single session's entries
All journal entries, or a single session's entries
No parameter schema in public metadata yet.
Sponsors
Readme
Details
- Repository
- github.com/toonight/mnemoscope
- Website
- github.com/toonight/Mnemoscope
- Categories
- AI & LLM Tools, Documents & Knowledge
- Package
@mnemoscope/mcp-server- Transport
- STDIO
- Registry
- MCP registry, active