# io.github.GetHaki/haki (remote · api.gethaki.space)

Long-term memory for AI agents: bitemporal fact ledger, contradiction detection, explainability.

- Trust score: 33/100 (low)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- remote · `api.gethaki.space`: 33/100 (this document), [markdown](https://verifymcp.io/servers/gethaki-haki/api.md), [page](https://verifymcp.io/servers/gethaki-haki/api)

## Channel facts

- Endpoint: `https://api.gethaki.space/mcp/`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-20.

- **Endpoint Security**: 83/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - The endpoint enforces authorisation, but returns a challenge with no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 0/100
  - Transport blocked by authentication: the endpoint requires auth we don't have to verify streamable-http.
- **Schema Quality & AI Usability**: 0/100
  - Schema blocked by authentication: the endpoint requires auth we don't have to read it.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 0/100
  - Tool coverage blocked by authentication: the endpoint requires auth we don't have to read its tools.
- **Tool Safety**: 0/100
  - Tool safety blocked by authentication: the endpoint requires auth we don't have to read its tools.
- **Capabilities**: 0/100
  - Capabilities blocked by authentication: the endpoint requires auth we don't have to read them.

**Unverified: 6 categories.** Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

### How do I install the io.github.GetHaki/haki MCP server?

io.github.GetHaki/haki is a hosted endpoint at https://api.gethaki.space/mcp/, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http gethaki-haki 'https://api.gethaki.space/mcp/'
```

### Cursor

```json
{
  "mcpServers": {
    "gethaki-haki": {
      "url": "https://api.gethaki.space/mcp/"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "gethaki-haki": {
      "type": "http",
      "url": "https://api.gethaki.space/mcp/"
    }
  }
}
```

### Codex

```toml
[mcp_servers.gethaki-haki]
url = "https://api.gethaki.space/mcp/"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "gethaki-haki": {
      "type": "remote",
      "url": "https://api.gethaki.space/mcp/",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add gethaki-haki --url 'https://api.gethaki.space/mcp/' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  gethaki-haki:
    url: "https://api.gethaki.space/mcp/"
```

### Netclaw

```json
{
  "McpServers": {
    "gethaki-haki": {
      "Transport": "http",
      "Url": "https://api.gethaki.space/mcp/"
    }
  }
}
```

### Vellum

```bash
assistant mcp add gethaki-haki -t streamable-http -u 'https://api.gethaki.space/mcp/'
```

### Other

```json
{
  "mcpServers": {
    "gethaki-haki": {
      "type": "http",
      "url": "https://api.gethaki.space/mcp/"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-10 (score 33, −28)

- [security regression] Endpoint reachability: reachable → behind authorisation
- [security regression] Authorization: unverified → fail
- [security regression] Tool safety: pass → unverified
- [security regression] Transport: pass → unverified
- [security regression] Stability: 0.03 → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-09-09 (score 61, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-09-08 (score 61)

First indexed and scored.

## MCP tools (5)

### `haki_context` (~190 tokens)

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 sources, the trace_id (inspectable
    via haki_inspect), and an explicit `status` ("ok"/"degraded"/"failed") —
    never treat a degraded or failed response as "no known facts".

    If the block does not hold what was needed, call this tool again with
    the SAME query and `exclude_ids` set to the ids already received — it
    serves the next page of the same ranked list. Do NOT rewrite the query
    with what was just read: measured on this project's bench, that finds
    the missing turn less often than asking unchanged.

Input parameters:

- `budget_tokens` (integer)
- `exclude_ids`
- `query` (string, required)

### `haki_capture` (~115 tokens)

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 is synchronous in dev
    (HAKI_MCP_AUTOCONSOLIDATE), so the fact is recallable immediately.
    Content larger than MAX_JSON_BYTES (256 KiB, same bound as POST
    /v1/capture) is rejected with a typed error.

Input parameters:

- `content` (string, required)
- `kind` (string)

### `haki_inspect` (~52 tokens)

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 parameters:

- `trace_id` (string, required)

### `haki_forget` (~78 tokens)

Forget the configured subject's memory in this project.
    mode='disable' (reversible, facts move to disabled) or 'delete' (real
    erasure: facts, embeddings, events, traces). Returns the erasure receipt
    (forget_id) and the counters of what was done.

Input parameters:

- `mode` (string)

### `haki_correct` (~184 tokens)

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='useful'/'irrelevant' logs feedback on a recall
    without changing the fact. Exactly one target required: fact_id (one
    precise fact, usually seen via haki_context/haki_inspect) OR trace_id
    (one whole haki_context call). Same mechanism as POST /v1/feedback
    (app.ledger.submit_feedback): identical effect whatever the call path.
    Scope resolved by API key (see _resolve_scope) or, self-hosted without
    a key, by HAKI_MCP_PROJECT_ID.

Input parameters:

- `comment`
- `fact_id`
- `rating` (string, required)
- `trace_id`

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/gethaki-haki/api#diagnostics

## Score history

- 2026-09-20: 33
- 2026-09-19: 33
- 2026-09-18: 33
- 2026-09-17: 33
- 2026-09-16: 33
- 2026-09-15: 33
- 2026-09-14: 33
- 2026-09-13: 33
- 2026-09-12: 33
- 2026-09-11: 33
- 2026-09-10: 33
- 2026-09-09: 61
- 2026-09-08: 61

## Common questions

### What is the io.github.GetHaki/haki MCP server?

io.github.GetHaki/haki is an MCP server listed in the public MCP registry as io.github.GetHaki/haki. Long-term memory for AI agents: bitemporal fact ledger, contradiction detection, explainability. This page covers its hosted endpoint (https://api.gethaki.space/mcp/).

### Is the io.github.GetHaki/haki MCP server safe to use?

io.github.GetHaki/haki scores 33 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.GetHaki/haki MCP server expose?

io.github.GetHaki/haki exposes 5 tools: haki_context, haki_capture, haki_inspect, haki_forget, haki_correct. Their descriptions and schemas cost roughly 619 tokens of context every time the server is loaded.

### Does the io.github.GetHaki/haki MCP server require authentication?

Yes. io.github.GetHaki/haki asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the io.github.GetHaki/haki MCP server still maintained?

io.github.GetHaki/haki is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://api.gethaki.space/mcp/
- Repository: https://github.com/GetHaki/Haki
- Website: https://gethaki.space/
- Changelog RSS feed: https://verifymcp.io/servers/gethaki-haki/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/gethaki-haki/api.json
- HTML version of this page: https://verifymcp.io/servers/gethaki-haki/api