A
licenseA
qualityB
maintenanceEnables AI agents to record, recall, correct, and forget evidence-backed factual claims with temporal history, while explaining whether remembered information is current, historical, or contested.
5
Apache 2.0
haki
Server Details
Long-term memory for AI agents: bitemporal fact ledger, contradiction detection, explainability.
Glama couldn't complete the latest health check. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
- Status
- Unhealthy
- Uptime
- 6.8% over 21 days
- Last Tested
- Transport
- Streamable HTTP
- URL
- Repository
- GetHaki/Haki
- GitHub Stars
- 2
- Server Listing
- mcp-haki
TDQS
A4.1/5.0
Scored across 5 tools
Disambiguation5/5
Each tool has a clearly distinct purpose: capture stores facts, context retrieves them, correct modifies, forget removes, inspect audits. No overlap in functionality.
Naming Consistency4/5
All tools share the 'haki_' prefix and use imperative verbs (capture, correct, forget, inspect). 'haki_context' is slightly more noun-like but still clearly implies retrieval, maintaining overall consistency.
Tool Count5/5
Five tools cover the essential memory lifecycle (create, read, update, delete, audit) without unnecessary redundancy. This is well-scoped for the domain.
Completeness5/5
The set covers all CRUD operations plus inspection, which is comprehensive for a memory management server. There are no obvious missing operations for the stated purpose.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
5 tool updates
- First observed
haki_capture - First observed
haki_context - First observed
haki_correct - First observed
haki_forget - First observed
haki_inspect
Related MCP Connectors
Attestable memory for AI agents: curated writes, verifiable tenant isolation, bi-temporal facts.
Long-term memory for AI agents: semantic facts, episodic events, and procedural workflows
Long-term memory for AI agents: durable records, observable retrieval, governed context assembly.
Evidence-grounded, graph-connected, correctable memory for agents.
Related MCP Servers
Lians Agent Memoryofficial
AlicenseAqualityBmaintenanceLocal-first bitemporal memory for AI agents with deterministic supersession, point-in-time recall, erasure proofs, and tamper-evident audit history.912Apache 2.0- AlicenseNot gradedqualityAmaintenanceA neuro-inspired long-term memory architecture for AI agents.3MIT
- AlicenseAqualityCmaintenanceLong-term memory for AI agents. Compiles conversations into a structured knowledge base with Claim/Evidence model, source provenance, append-only timeline, and contradiction detection. Multi-path retrieval (Exact + BM25 + Graph + weighted RRF + reranker) — 96.6% R@5 on LongMemEval-S, zero vector dependencies.813 PyPI3MIT
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd
Glama MCP Gateway
Add one secure layer between your agents and this server.