"Exploring Memory Persistence in DeepSeek Technology" matching MCP servers:

Persistent encrypted memory for AI agents. E2E encrypted private vaults, shared knowledge commons, topic channels, and agent-to-agent DMs. 23 MCP tools, free, no API key needed.

Enables AI assistants to keep and retrieve private context locally, with verifiable receipts and optional Solana anchoring for public proofs.

Gives AI agents a shared, encrypted memory store accessible over MCP, with per-agent keys, per-namespace permissions, history and revert, attachments, and semantic search that handles Czech as well as English. Memories, agents, network access, and HTTPS can be managed through a self-hosted admin web on the same port, with backups being simply copies of the encrypted data file.

Enables capturing a tamper-evident, hash-chained local record of every AI agent tool call — both the decision before a tool runs and its outcome — so you can review what the agent actually did in order, detect edits, deletions, or reordering at the exact index, and export a signed evidence pack any third party can verify with no installs.

Enables AI tools and agents to share a persistent memory space, so a decision, task, or encrypted secret saved in one client can be searched, recalled, and handed off from another. It also tracks goals day by day, moves unfinished work between sessions, and keeps exports, trash recovery, and per-account isolation under the user's control.

A tool for detecting and cleaning Java memory shells via local or SSH remote execution. It enables AI agents to scan Java processes, analyze suspicious class code, and safely remove memory shells after user confirmation.

Guardrails for AI coding agents that enforces rules via compliance receipts, blocking destructive actions and syncing rules across all AI tools.

Enables security analysts to carry structured investigation state across sessions by storing typed observations, hypotheses, tasks, evidence and versioned decisions in a local SQLite graph with full-text search. It also enforces authorized scope and request controls, redacted and content-hashed evidence, duplicate-test signatures and validation gates that leave findings in draft until reproducibly confirmed, then produces technical and executive reports for Antigravity, Codex and other stdio MCP clients.

Enables agents to store and retrieve hierarchical memory in cryptographically partitioned namespaces, with HMAC-based isolation and Ebbinghaus time-decay so recall fades realistically over time. Runs as a zero-dependency Python STDIO MCP server that returns deterministic JSON results.

Enables authorized web/API security analysis as a stateful, multi-stage workflow with persistent session state, human-controlled validation, candidate versus confirmed finding tracking, and stop conditions.

Enables devices and agents to share a self-hosted memory store over a remote Streamable HTTP MCP endpoint, with hybrid retrieval, scoped access tokens, and encrypted vault references for sensitive data.

Enables MCP-compatible AI agents to save encrypted, DID-signed session checkpoints and resume the latest state across sessions, while keeping secrets and credentials in a local vault.

Enables MCP clients to save, semantically recall, and delete long-term facts and decisions entirely offline, with encrypted storage, automatic secret redaction, and multilingual local embeddings.

AI-powered memory dump analysis using Volatility 3 for digital forensics investigations. Enables process analysis, malware detection, network forensics, timeline generation, and anomaly detection with support for Claude, Llama, and other LLMs.

Blocks AI coding assistants from installing non-existent packages and accessing non-existent files.

Local MCP server for securely storing and sharing identity documents (passports, visas, licenses) with AI agents, requiring per-field user consent for each request.

Enables agents and MCP clients to retain, recall, screen, quarantine, approve, supersede, and verify durable memories with session-level provenance. Every write passes a poisoning gate, so suspicious or secret-bearing entries are held for human review rather than silently trusted in later sessions.

Enables autonomous agents and MCP-compatible clients to enforce policy-approved actions using risk tiers, reversible checkpoints, and token approval bounds.

An MCP authorization server implementing OAuth2/OIDC flows, supporting dynamic client registration, PKCE, consent screens, and client ID metadata documents for MCP authorization.

Lets multiple AI agents and parallel coding sessions share one memory and task ledger, so they can claim work instead of duplicating it, resume each other's handoffs and reasoning, and use credentials without ever seeing the keys. Connects assistants such as Claude Code, Codex, Cursor, Gemini, ChatGPT and custom agents over MCP, backed by a single local SQLite file or a self-hosted Postgres hub.

MCP server for ai-scanner that enables AI agents to scan codebases for LLM usage, AI frameworks, and exposed secrets.

Enables AI agents to query and record SOC analyst reasoning via a knowledge graph, allowing access to institutional memory from Splunk.

Authentik MCP provides seamless integration with Authentik's API, supporting both full-featured and diagnostic modes. These enable secure, automated user, group, and system management through MCP-compatible tools.

Enables agent-neutral MCP clients to inspect native T3 inventory and results, persist signed events, perform explicit bounded delegation, and retain durable auditable receipts.

A scheduled MCP server that monitors Auth0 users by periodically collecting summaries, detecting suspicious admins, and auto-blocking them; it provides instant reports via SQLite and exposes tools for on-demand collection and configuration.

An MCP server that provides tools to read and modify Auth0 configurations via the Auth0 Management API v2, including write instruments for creation and updates but no deletion.

Enables monitoring Auth0 users by collecting summaries, storing reports in SQLite, and auto-blocking suspicious admins, all through MCP tools without an LLM.

MCP server that provides access to Auth0 Management API v2, offering read-only tools grouped by categories for querying Auth0 resources.

Enables secure remote control of Home Assistant and Life Dashboard/DSH via MCP, supporting entity state queries, whitelisted entity/scene control, lifecycle overview reading, DSH workspace summaries, and follow-up sending.

Enables secure, human-approved AI memory from Gmail messages for Claude, with provenance, risk inspection, expiry, and revocation controls.