MCP serverio.github.GetHaki/haki
Long-term memory for AI agents: bitemporal fact ledger, contradiction detection, explainability.
Overview
Score?
UNRATED 0.000
of what a free look can see, on 3 looks
Looks
17
last 1 day ago
Tools
5
More info
URL
api.gethaki.space/mcp/
streamable-http
Says it is
haki
protocol 2025-06-18
In the record since
25 days ago
Among servers18,413 with a card
0median 0.606 · this server 0.000 · highest on record 0.8561
Toolsfrom sha256:1fa38c7357…f45dee
| Tool | Schema |
|---|---|
| haki_capture Memorize a durable project fact: technical decision, convention,
resolved error. Call at the END of a task. Never memorize secrets,
tokens or ephemeral data. Consolidation |
input · output |
| haki_context Recall the project's memory (decisions, conventions, preferences)
relevant to a task. Call BEFORE planning or editing code. Returns a
ready-to-inject block with dates and s |
input · output |
| haki_correct Correct the memory from inside the conversation (M10). rating='incorrect'
with a fact_id moves that fact to 'disputed': haki_context will never
recall it again. rating='use |
input · output |
| haki_forget Forget the configured subject's memory in this project.
mode='disable' (reversible, facts move to disabled) or 'delete' (real
erasure: facts, embeddings, events, traces). R |
input · output |
| haki_inspect Inspect the trace of a haki_context call: which facts were included,
excluded or blocked, and why (reason_code). Provenance proof of the
served memory. |
input · output |
Verify it yourself
npx teppi-check https://api.gethaki.space/mcp/curl -s https://api.teppi.xyz/v1/trust/mcp/mcs_01M22BHPCK0EGTR5Y4QXW7AZY1