knowmind
A German-hosted memory and knowledge graph backend for AI agents. Exposes hybrid search (knowmind_recall), bi-temporal fact updates, document ingestion with title-based upsert, and typed bidirectional relations through knowmind_link. Runs as stdio MCP or direct HTTP. Data stays in Hetzner datacenters in Germany with GDPR AVV available. The knowmind init command sets up automatic recall hooks before each prompt and post-conversation storage nudges in Claude Code and Cursor. You bring your own API token from knowmind.de. Reach for this when you need persistent context across sessions with explicit relationship modeling and want to keep data in the EU.
- tools
- 15
- auth
- Secret needed
- transport
- STDIO
- env vars
- 2
- last updated
- Nov 1, 2026
Tools
15 toolsPublic tool metadata for what this MCP can expose to an agent.
knowmind_recall_memoriesSearch your memory and get the passages that answer a question, ranked.
Search your memory and get the passages that answer a question, ranked.
No parameter schema in public metadata yet.
knowmind_recall_at_timeThe same search, but as your memory stood on a given date.
The same search, but as your memory stood on a given date.
No parameter schema in public metadata yet.
knowmind_list_recentThe most recently added entries, newest first.
The most recently added entries, newest first.
No parameter schema in public metadata yet.
knowmind_list_relationsAll typed edges attached to one entry, in both directions.
All typed edges attached to one entry, in both directions.
No parameter schema in public metadata yet.
knowmind_get_schemaThe entity classes and relation types this workspace accepts.
The entity classes and relation types this workspace accepts.
No parameter schema in public metadata yet.
knowmind_list_inferredRelations that wait for a human decision: relations knowmind inferred from a text, and relations that start from a document although their type needs a person, organisation or similar.
Relations that wait for a human decision: relations knowmind inferred from a text, and relations that start from a document although their type needs a person, organisation or similar.
No parameter schema in public metadata yet.
knowmind_get_statsSize of the corpus: documents, chunks, entities, edges.
Size of the corpus: documents, chunks, entities, edges.
No parameter schema in public metadata yet.
knowmind_get_healthWhether the service and its stores are reachable.
Whether the service and its stores are reachable.
No parameter schema in public metadata yet.
knowmind_store_memoryStore a short fact, decision or note. Stays as one unit; it is not split.
Store a short fact, decision or note. Stays as one unit; it is not split.
No parameter schema in public metadata yet.
knowmind_upload_documentStore a longer text as a document. It is split into passages, embedded, and becomes searchable through knowmind_recall_memories.
Store a longer text as a document. It is split into passages, embedded, and becomes searchable through knowmind_recall_memories.
No parameter schema in public metadata yet.
knowmind_update_factSupersede a fact that has changed. The old version keeps its validity window and stays auditable; nothing is deleted.
Supersede a fact that has changed. The old version keeps its validity window and stays auditable; nothing is deleted.
No parameter schema in public metadata yet.
knowmind_upsert_entityCreate or update a typed entity (a person, a company, a product) with aliases.
Create or update a typed entity (a person, a company, a product) with aliases.
No parameter schema in public metadata yet.
knowmind_link_entitiesCreate a typed edge between two entries, with a confidence value.
Create a typed edge between two entries, with a confidence value.
No parameter schema in public metadata yet.
knowmind_unlink_entitiesRemove a typed edge.
Remove a typed edge.
No parameter schema in public metadata yet.
knowmind_review_inferredRecord a decision on one relation from knowmind_list_inferred.
Record a decision on one relation from knowmind_list_inferred.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
KNOWMIND_TOKEN*secretBearer API token from the knowmind.de Dashboard -> API-Tokens (https://knowmind.de/dashboard/api-tokens)
KNOWMIND_API_URLdefault: https://knowmind.deKnowmind API base URL
Readme
knowmind
Persistent memory for your AI tools. Store something once, and it is available in Claude Code, Cursor, and any other MCP client that runs a local (stdio) server — as a typed knowledge graph with provenance, confidence, and a bitemporal history for every fact. Hosted in Germany (Hetzner, Nuremberg data center); the CLI and MCP server in this repository are Apache-2.0.
The free tier is permanently free and requires no payment details. The API, CLI, and MCP server are included in every tier.
Connect your AI tool in three steps
- Create a free account at knowmind.de and generate an access token: Dashboard → API tokens.
- Store the token locally:
npx -y knowmind login --token kmt_xxxxxxxx
- Wire up your client:
Claude Code (one command)
claude mcp add knowmind --env KNOWMIND_TOKEN=kmt_xxx -- npx -y knowmind mcp
Details
- Repository
- github.com/schubeler-consulting/knowmind
- Website
- knowmind.de
- Categories
- AI & LLM Tools, Documents & Knowledge
- Package
knowmind- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
Contextateleengco/contexta-mcpPersistent memory and knowledge graph for AI assistants — keyword + vector + graph search.0stars
Skillsindexthomasblc/skillsindex-mcpSearch and score 11,000+ AI agent tools: MCP servers, Claude skills, GPT actions, IDE plugins.0stars
Memoryoracletooloracle/memoryoracleMemoryOracle - 10 agent memory tools: vector store, recall, summarization, redaction.0stars
OrgXuseorgx/orgx-mcpOrgX is coordination infrastructure for AI-native teams. It gives your LLM a persistent organizational layer: initiatives with milestones and tasks, human-in-th0stars