# HAI-MCP (pypi · hai-mcp)

Model-agnostic MCP control plane for HAI: bounded missions, owner-gated actions, drift checks.

- Trust score: 71/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-04

## Components

- pypi · `hai-mcp`: 71/100 (this document), [markdown](https://verifymcp.io/servers/smlfg-hai-mcp/hai-mcp.md), [page](https://verifymcp.io/servers/smlfg-hai-mcp/hai-mcp)

## Channel facts

- Registry: `pypi`
- Package: `hai-mcp`
- Version: `0.1.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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 2026-11-04.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 0 of 28 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 32/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Licence could not be checked: the licence is shipped as a file inside the package, not declared as a standard (SPDX) licence identifier, so we cannot tell whether it is OSI-approved.
  - Actively maintained (last published 21 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 53/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 1535 tokens (~63/item across 24 items; 24 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 70/100
  - Stability observed for 21 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 24 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 24 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the HAI-MCP server?

HAI-MCP runs locally as a PyPI package, launched with uvx hai-mcp. 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 smlfg-hai-mcp -- uvx hai-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "smlfg-hai-mcp": {
      "command": "uvx",
      "args": [
        "hai-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "smlfg-hai-mcp": {
      "command": "uvx",
      "args": [
        "hai-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add smlfg-hai-mcp -- uvx hai-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "smlfg-hai-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "hai-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add smlfg-hai-mcp --command uvx --arg hai-mcp
```

### Hermes

```yaml
mcp_servers:
  smlfg-hai-mcp:
    command: "uvx"
    args: ["hai-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "smlfg-hai-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "hai-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add smlfg-hai-mcp -t stdio -c uvx -a hai-mcp
```

### Other

```json
{
  "mcpServers": {
    "smlfg-hai-mcp": {
      "command": "uvx",
      "args": [
        "hai-mcp"
      ]
    }
  }
}
```

## 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.

### 2026-11-03 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 68, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-27 (score 53, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-26 (score 52, −15)

- [security regression] Malware scan: pass → unverified

### 2026-10-25 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-23 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (24)

### `hai_health` (~31 tokens)

Check HAI-MCP server health and optional project path usability. No model calls.

Input parameters:

- `project_path`

Output parameters:

- `result` (string)

### `hai_status` (~30 tokens)

Return ACTIVE lanes, focus, inbox count, and optional project next-step flags.

Input parameters:

- `project_path`

Output parameters:

- `result` (string)

### `hai_get_next_step` (~32 tokens)

Read the canonical NEXT_STEP.md for a project (or report none).

Input parameters:

- `project_path` (string, required)

Output parameters:

- `result` (string)

### `hai_read_artifacts` (~39 tokens)

Read-only summary of HAI Projek-Managment run-contract artifacts.

Input parameters:

- `max_chars` (integer)
- `project_path` (string, required)

Output parameters:

- `result` (string)

### `hai_park` (~35 tokens)

Park a thought/meta item in HAI inbox without changing ACTIVE lanes.

Input parameters:

- `tags`
- `text` (string, required)

Output parameters:

- `result` (string)

### `hai_set_focus` (~49 tokens)

Set focus and register an ACTIVE lane (max 2). Fails if a third ACTIVE is requested.

Input parameters:

- `focus_id` (string, required)
- `label`
- `project_path`

Output parameters:

- `result` (string)

### `hai_propose_next_step` (~43 tokens)

Write NEXT_STEP.proposed.md (not canonical). Promote via hai_accept_next_step.

Input parameters:

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

Output parameters:

- `result` (string)

### `hai_accept_next_step` (~126 tokens)

Promote proposed (or provided) content to canonical NEXT_STEP.md — owner-gated.

Default gate (nonce): call once WITHOUT owner_code; a one-time code is delivered to the
owner (never to this client). Ask the owner for it and call again with owner_code=<code>.
The code is bound to the exact content and is single-use. Legacy gate (ack_legacy):
owner_ack=true + reason.

Input parameters:

- `content`
- `owner_ack` (boolean)
- `owner_code`
- `project_path` (string, required)
- `reason`

Output parameters:

- `result` (string)

### `hai_checkpoint` (~34 tokens)

Snapshot ACTIVE_CONTEXT and optional project artifacts under HAI_HOME/history/checkpoints.

Input parameters:

- `note`
- `project_path`

Output parameters:

- `result` (string)

### `hai_recover` (~31 tokens)

Return the smallest recovery next action from latest or named checkpoint (read-only advice).

Input parameters:

- `checkpoint_id`

Output parameters:

- `result` (string)

### `hai_open_mission` (~68 tokens)

Open a bounded mission with a versioned canonical contract. One active mission globally.

Input parameters:

- `artifact` (string, required)
- `constraints`
- `done_criteria` (array, required)
- `non_goals`
- `objective` (string, required)
- `owner` (string, required)

Output parameters:

- `result` (string)

### `hai_authorize_session` (~105 tokens)

Grant a time-bounded session lease tied to mission ID and exact contract version.

Input parameters:

- `agent_identity` (string, required)
- `capabilities`
- `contract_version` (integer, required)
- `contribution` (string, required)
- `criterion_ids` (array, required)
- `device_id`
- `duration_minutes` (integer, required)
- `expected_result` (string, required)
- `harness_id`
- `mission_id` (string, required)
- `role` (string, required)

Output parameters:

- `result` (string)

### `hai_bind_project` (~69 tokens)

Bind a device-local directory to a logical project_id mount table entry. Requires owner_ack=true + reason.

Input parameters:

- `device_id` (string, required)
- `local_path` (string, required)
- `owner_ack` (boolean, required)
- `project_id` (string, required)
- `reason` (string, required)

Output parameters:

- `result` (string)

### `hai_get_contract` (~33 tokens)

Return the exact canonical mission contract for a valid session lease (not a summary).

Input parameters:

- `session_id` (string, required)

Output parameters:

- `result` (string)

### `hai_check_activity` (~76 tokens)

Deterministically classify planned or observed activity against the mission contract.

Input parameters:

- `activity_kind`
- `activity_step` (string, required)
- `affected_paths`
- `criterion_id`
- `declares_blocker` (boolean)
- `evidence`
- `session_id` (string, required)
- `trace_events`

Output parameters:

- `result` (string)

### `hai_park_item` (~66 tokens)

Park a mission-linked idea with full context. Grants no execution right; contract unchanged.

Input parameters:

- `idea` (string, required)
- `mission_id` (string, required)
- `origin_session_id` (string, required)
- `rationale` (string, required)
- `trigger_event` (string, required)

Output parameters:

- `result` (string)

### `hai_recontract` (~125 tokens)

Apply a visible field-level contract diff; revokes all leases. Owner-gated.

First call (no owner_code) returns the diff and delivers a one-time code to the owner;
call again with owner_code=<code from the owner>. Legacy gate: owner_ack=true.

Input parameters:

- `break_glass_marker` (boolean)
- `changes` (object, required)
- `contract_version` (integer, required)
- `mission_id` (string, required)
- `mode` (string)
- `owner_ack` (boolean)
- `owner_code`
- `reason` (string, required)

Output parameters:

- `result` (string)

### `hai_close_mission` (~108 tokens)

Complete with verified per-criterion evidence, or abandon (owner-gated).

Abandon: first call delivers a one-time code to the owner; call again with owner_code.
Legacy gate: owner_ack=true.

Input parameters:

- `closure` (string, required)
- `contract_version` (integer, required)
- `device_id`
- `evidence`
- `mission_id` (string, required)
- `outcome_summary` (string, required)
- `owner_ack` (boolean)
- `owner_code`

Output parameters:

- `result` (string)

### `hai_intake` (~38 tokens)

Capture a raw thought immutably. Returns an intake id only — never actionable, never starts an agent.

Input parameters:

- `raw` (string, required)

Output parameters:

- `result` (string)

### `hai_distill` (~57 tokens)

Reduce an intake to EXACTLY one decision + one next step; the server parks everything else.

Input parameters:

- `decision` (string, required)
- `intake_id` (string, required)
- `next_step` (string, required)
- `parklist`

Output parameters:

- `result` (string)

### `hai_mission_start` (~84 tokens)

Fast start: declare problem + artifact + time limit. Thin wrapper over hai_open_mission (one canonical contract).

Input parameters:

- `artifact` (string, required)
- `constraints`
- `done_criteria` (array, required)
- `non_goals`
- `owner` (string, required)
- `problem` (string, required)
- `time_limit_hours` (number)

Output parameters:

- `result` (string)

### `hai_drift_check` (~79 tokens)

Lightweight mismatch check against the mission contract. Thin wrapper over hai_check_activity.

Input parameters:

- `activity_kind`
- `activity_step` (string, required)
- `affected_paths`
- `criterion_id`
- `declares_blocker` (boolean)
- `evidence`
- `session_id` (string, required)
- `trace_events`

Output parameters:

- `result` (string)

### `hai_proof` (~67 tokens)

Close a mission only against verified per-criterion evidence. Thin wrapper over hai_close_mission (completed).

Input parameters:

- `contract_version` (integer, required)
- `device_id`
- `evidence` (object, required)
- `mission_id` (string, required)
- `outcome_summary` (string, required)

Output parameters:

- `result` (string)

### `hai_stop` (~110 tokens)

Hard day terminal: record the three answers, invalidate active leases; no next-day plan. Missions are not closed.

manual_practice: what the owner did BY HAND today (e.g. "read the auth diff",
"ran pytest", "wrote the date regex") — the currency logbook for verification skills.

Input parameters:

- `agency_gained` (string, required)
- `clearer` (string, required)
- `day` (string, required)
- `loop_closed` (boolean, required)
- `manual_practice`

Output parameters:

- `result` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/smlfg-hai-mcp/hai-mcp#diagnostics

## Score history

- 2026-11-04: 71
- 2026-11-03: 71
- 2026-11-02: 70
- 2026-11-01: 70
- 2026-10-31: 70
- 2026-10-30: 69
- 2026-10-29: 69
- 2026-10-28: 68
- 2026-10-27: 53
- 2026-10-26: 52
- 2026-10-25: 67
- 2026-10-24: 66
- 2026-10-23: 66
- 2026-10-22: 65
- 2026-10-21: 65
- 2026-10-20: 62
- 2026-10-19: 62
- 2026-10-18: 62
- 2026-10-17: 62
- 2026-10-16: 62
- 2026-10-15: 47
- 2026-10-14: 47
- 2026-10-13: 36

## Common questions

### What is the HAI-MCP server?

HAI-MCP is listed in the public MCP registry as io.github.smlfg/hai-mcp. Model-agnostic MCP control plane for HAI: bounded missions, owner-gated actions, drift checks. This page covers its PyPI package (hai-mcp).

### Is the HAI-MCP server safe to use?

HAI-MCP scores 71 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 4 November 2026. 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 HAI-MCP server expose?

HAI-MCP exposes 24 tools: hai_health, hai_status, hai_get_next_step, hai_read_artifacts, hai_park, and 19 more. Their descriptions and schemas cost roughly 1,535 tokens of context every time the server is loaded.

### Is the HAI-MCP server still maintained?

HAI-MCP is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- PyPI project: https://pypi.org/project/hai-mcp/
- Socket report: https://socket.dev/pypi/package/hai-mcp
- Repository: https://github.com/smlfg/hai-mcp
- Changelog RSS feed: https://verifymcp.io/servers/smlfg-hai-mcp/hai-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/smlfg-hai-mcp/hai-mcp.json
- HTML version of this page: https://verifymcp.io/servers/smlfg-hai-mcp/hai-mcp