MCP.Market

Hypermnesia MCP server

by cdeust·io.github.cdeust/hypermnesia-mcp·v4.23.5·75 stars

Persistent memory for AI agents — 36 cited neuroscience mechanisms, local-first, hybrid retrieval.

A92/100grade A
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Established

75 stars128 downloads/wk

Reviews

Write one

Nobody has reviewed Hypermnesia yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Hypermnesia tools (63, 6 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • add_rule

    Add a neuro-symbolic rule to the memory store.

  • anchor

    Mark a memory as compaction-resistant (heat=1.0).

  • assess_coverage

    Evaluate knowledge coverage completeness.

  • backfill_memories

    Auto-import prior Claude Code conversations into memory.

  • calibration

    Score resolved predictions: Brier score and reliability bands.

  • change_impact

    Report memories affected by a commit's code changes.

  • check_setup

    Verify the local install: Python, PG driver, DB, extensions, FS.

  • checkpoint

    Save or restore working state for hippocampal replay.

  • codebase_analyze

    Analyze codebase and store structure as memories.

  • consolidatewrite action

    Run memory maintenance: decay, compression, CLS, memify.

  • create_triggerwrite action

    Create a prospective memory trigger.

  • curate_distill

    Return distillation dossiers for the in-session LLM to author lessons from.

  • curate_wiki

    Return structured authoring jobs for the in-session LLM to author.

  • detect_domain

    Lightweight domain classification.

  • detect_gaps

    Identify knowledge gaps in the memory store.

  • drill_down

    Navigate into a fractal memory cluster.

  • echo
  • explore_features

    Explore interpretability features.

  • fixture
  • forgetwrite action

    Delete or soft-delete a memory by ID.

  • get_causal_chain

    Trace entity relationships through the knowledge graph.

  • get_grooming_health

    Backlog + staleness for wiki/distillation/promotion grooming.

  • get_project_story

    Generate a period-based autobiographical narrative.

  • get_rules

    List active neuro-symbolic rules.

  • get_telemetry

    Return per-op counters + read/write ratio (Popper C6).

  • import_sessions

    Import conversation history into the memory store.

  • ingest_codebase

    Ingest upstream codebase analysis into Cortex.

  • ingest_document

    Ingest a .docx or Confluence export into Cortex.

  • ingest_findings

    Ingest an AP findings run (runs/<run_id>/) into Cortex.

  • ingest_prd

    Ingest a PRD document into Cortex.

  • lesson_promotion

    Propose promotion jobs for validated lessons — never promotes itself.

  • list_domains

    Overview of all detected cognitive domains.

  • memory_stats

    Memory system diagnostics.

  • narrative

    Generate project narrative from stored memories.

  • navigate_memory

    Navigate memory space using Successor Representation.

  • predict

    Record a falsifiable prediction before its outcome is known.

  • query_methodology

    Returns cognitive profile for the current domain.

  • rate_memory

    Rate a memory as useful or not to update metamemory confidence.

  • rebuild_profiles

    Full rescan of all session data to rebuild methodology profiles.

  • recall

    Retrieve memories using multi-signal fusion.

  • recall_hierarchical

    Retrieve memories using fractal hierarchy.

  • recall_skills

    Retrieve procedural skills for the current situation.

  • record_session_end

    Incremental profile update after a session ends.

  • remember

    Store a memory through the predictive coding write gate.

  • resolve_prediction

    Settle an open prediction against the evidence that decided it.

  • seed_project

    Bootstrap memory from an existing codebase.

  • slow_tool
  • sync_instructions

    Push top memory insights into CLAUDE.md.

  • unified_search

    Fuse Cortex recall with AP code search using reciprocal rank fusion.

  • validate_memory

    Validate memories against current filesystem state.

  • why

    Resolve ⟦rcpt:id⟧ injection receipts into presence-in-context evidence.

  • wiki_adrwrite action

    Create a numbered ADR with auto-incremented sequence.

  • wiki_get_draft

    Fetch a pending draft with its source claims and kind contract.

  • wiki_link

    Add a bidirectional link between two wiki pages (Related section).

  • wiki_list

    List authored wiki pages, optionally filtered by kind.

  • wiki_migrate

    Sync the filesystem wiki into PG and reconcile FS-deleted ghosts.

  • wiki_purge

    Re-evaluate and purge wiki pages that fail the current classifier.

  • wiki_read

    Read a wiki page by relative path.

  • wiki_refine_draftwrite action

    Submit refined prose for a draft and record an audit memo.

  • wiki_reindex

    Regenerate the wiki table of contents at .generated/INDEX.md.

  • wiki_rename

    Move a page and leave a redirect stub at the old path.

  • wiki_verify

    Verify wiki-page symbol citations against AP's code graph.

  • wiki_writewrite action

    Author a wiki page using create, append, or replace mode.

Public scan report

scanner v0.1.10 · 2026-10-15 · same rubric, same numbers if you re-run it

no findings
  • Code scan1291 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Hypermnesia compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 95% of 48,255 servers
Tools
63
the typical server has 7
Tools that change things
10%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
75
more than 95% of 28,688 servers
Downloads a week
128
more than 68% of 12,191 servers with a package

What its tools let an agent do: 54 read · 3 create · 6 change

Release history: 6 versions in the registry since 2026-09-15, latest 2026-09-23, typically one every 1 day.

Install Hypermnesia in Claude Code, Cursor or VS Code

claude mcp add hypermnesia-mcp -- uvx hypermnesia-mcp
Add to Cursor

What the publisher says

From the Hypermnesia repository's README, as published. We do not edit it. Read it on GitHub

<!-- mcp-name: io.github.cdeust/hypermnesia-mcp -->

Memory for AI coding agents that you can hold accountable. Keep decisions, fixes and project context between sessions, and inspect what was retrieved. Runs locally by default. No account, no API key, no server to manage.

Sovereign is what it is today. Everything runs on your machine: a local SQLite file by default, or PostgreSQL + pgvector if you prefer. No LLM in the retrieval loop, and nothing leaves localhost unless you configure an integration that does. Your project's memory is a file you own and can delete.

Cross-platform is how it is built. One stdio MCP server and the same 57 tools on Claude Code, in the Claude Desktop bundle, under Claude Cowork, and on every local stdio MCP host listed in the table below. What differs per host is stated there, not discovered after install.

Eco-responsible is what we are aiming at. Work that never reaches a datacenter is work nobody has to power, and an agent that finds the right context first time re-reads fewer files. We hold that intent to the Green Software Foundation's SCI method, and we publish no CO₂ or energy figure, because we have not measured one. What we do and do not claim ↓

36 neuroscience mechanisms · 57 memory tools · 9 lifecycle hooks · a self-curating per-project wiki — all local, all open-source, MIT.

Install

Claude Code — add the marketplace and install the plugin:

claude plugin marketplace add cdeust/Cortex
claude plugin install hypermnesia-mcp

Claude Desktop — download hypermnesia-mcp.mcpb from Releases and open it, or use Settings → Extensions. The bundle carries the tools but no hooks; the MCPB format has none.

Claude Cowork is detected automatically (CLAUDE_ENVIRONMENT=cowork) and uses the local SQLite store. No PostgreSQL required.

Any other stdio MCP host (Codex, Gemini CLI, Cursor, Windsurf, VS Code) launches the same server and gets the same tools. The per-host matrix and launch commands are in Every other MCP host below. Codex has a native package: docs/codex-plugin.md. WSL, TLS client certificates and corporate proxies are covered in docs/deployment-scenarios.md.

The first use creates a local SQLite store under ~/.claude/methodology/. Models are downloaded once when needed and then run offline. The embedding and reranking model files are both fetched on first use. Optional integrations, remote PostgreSQL, and OTLP telemetry use the network only when explicitly configured. PRIVACY.md lists the exact scope.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Grade history

  • 2026-09-19restoreC → Ascore 92
  • 2026-09-19downgradeB → Cscore 66: Whole environment serialized (possible credential exfil); Network call to a raw IP address

Hypermnesia: common questions

Is Hypermnesia MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the Hypermnesia safety report
How do I install Hypermnesia?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Hypermnesia need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Hypermnesia maintained?
The last commit was 20 days ago (2026-10-15). The latest release is v4.23.5.
What can I use instead of Hypermnesia?
Servers from other publishers that do the same job: Memorix MCP server, Nautilus Compass Memory MCP server and State Memory MCP server. Compare all Hypermnesia alternatives.
How does Hypermnesia compare with other MCP servers?
safety score 92/100 (higher than 95% of 48,255 servers); tools 63 (the typical server has 7); tools that change things 10% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Hypermnesia

Same job from other publishers: the closest match first, then the best rated.

All Hypermnesia alternatives →
  • Memorix
    Local-first project memory with legacy MCP and 2026 discovery compatibility.
    B
  • Nautilus Compass Memory
    Local-first long-term memory for AI agents, with byte-recomputable signed verification receipts.
    B
  • State Memory MCP
    Persistent workflow graph server tracking tasks, decisions, spatial entities, and blockers.
    A
  • Knowl
    Persistent memory for AI agents, for code, research and everyday life. Stale facts retire.
    A

More from cdeust →