MCP Server for Z.AI - A Model Context Protocol server that provides AI capabilities
Nothing to run from here
HAI is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
98/100
trust score
24
tools declared
local
runs on your machine
—
downloads a day
What it does
Model-agnostic MCP control plane for HAI: bounded missions, owner-gated actions, drift checks.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user hai-mcp '--' uvx hai-mcp
# 2 — ask your agent for something these tools do
# hai_health, hai_status, hai_get_next_step and 21 more
HAI costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
SMAll 1 server
smlfg1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts HAI as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user hai-mcp '--' uvx hai-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
Nothing is required, but it can take HAI_HOME (Directory for the global HAI state (missions, leases, proofs). Default: ~/.hai), HAI_OWNER_HOME (Directory for the owner out-of-band channel (one-time nonces). Deliberately outside HAI_HOME. Default: ~/.hai-owner), HAI_TRANSPORT (Transport selection: 'stdio' (default) or 'streamable-http'.), HAI_HTTP_HOST (Host for streamable-http transport. Refused unless loopback or HAI_HTTP_TOKEN is set.), HAI_HTTP_PORT (Port for streamable-http transport.), HAI_HTTP_TOKEN (Bearer token required to accept non-loopback streamable-http connections. Loopback binds without a token.) if you want to set them.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
24 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Check HAI-MCP server health and optional project path usability. No model calls.
No parameter schema on file.
Return ACTIVE lanes, focus, inbox count, and optional project next-step flags.
No parameter schema on file.
Read the canonical NEXT_STEP.md for a project (or report none).
No parameter schema on file.
Read-only summary of HAI Projek-Managment run-contract artifacts.
No parameter schema on file.
Park a thought/meta item in HAI inbox without changing ACTIVE lanes.
No parameter schema on file.
Set focus and register an ACTIVE lane (max 2). Fails if a third ACTIVE is requested.
No parameter schema on file.
Write NEXT_STEP.proposed.md (not canonical). Promote via hai_accept_next_step.
No parameter schema on file.
Promote proposed (or provided) content to canonical NEXT_STEP.md — owner-gated.
No parameter schema on file.
Snapshot ACTIVE_CONTEXT and optional project artifacts under HAI_HOME/history/checkpoints.
No parameter schema on file.
Return the smallest recovery next action from latest or named checkpoint (read-only advice).
No parameter schema on file.
Open a bounded mission with a versioned canonical contract. One active mission globally.
No parameter schema on file.
Grant a time-bounded session lease tied to mission ID and exact contract version.
No parameter schema on file.
Bind a device-local directory to a logical project_id mount table entry. Requires owner_ack=true + reason.
No parameter schema on file.
Return the exact canonical mission contract for a valid session lease (not a summary).
No parameter schema on file.
Deterministically classify planned or observed activity against the mission contract.
No parameter schema on file.
Park a mission-linked idea with full context. Grants no execution right; contract unchanged.
No parameter schema on file.
Apply a visible field-level contract diff; revokes all leases. Owner-gated.
No parameter schema on file.
Complete with verified per-criterion evidence, or abandon (owner-gated).
No parameter schema on file.
Capture a raw thought immutably. Returns an intake id only — never actionable, never starts an agent.
No parameter schema on file.
Reduce an intake to EXACTLY one decision + one next step; the server parks everything else.
No parameter schema on file.
Fast start: declare problem + artifact + time limit. Thin wrapper over hai_open_mission (one canonical contract).
No parameter schema on file.
Lightweight mismatch check against the mission contract. Thin wrapper over hai_check_activity.
No parameter schema on file.
Close a mission only against verified per-criterion evidence. Thin wrapper over hai_close_mission (completed).
No parameter schema on file.
Hard day terminal: record the three answers, invalidate active leases; no next-day plan. Missions are not closed.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install HAI or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 98 / 100
Release 0.1.0 · scanned 14 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score98
Findings3 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationnone
Surface digest379543be2a8ad42960974b81f8134fdc3279eef631b72d6732b17efc72472213
Score vectorthreat 100 → client 98
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | none | publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read | −2 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (24 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| hai_health | no tags | |
| hai_status | no tags | |
| hai_get_next_step | no tags | |
| hai_read_artifacts | no tags | |
| hai_park | no tags | |
| hai_set_focus | no tags | |
| hai_propose_next_step | no tags | |
| hai_accept_next_step | no tags | |
| hai_checkpoint | no tags | |
| hai_recover | no tags | |
| hai_open_mission | no tags | |
| hai_authorize_session | no tags | |
| hai_bind_project | no tags | |
| hai_get_contract | no tags | |
| hai_check_activity | no tags | |
| hai_park_item | no tags | |
| hai_recontract | no tags | |
| hai_close_mission | no tags | |
| hai_intake | no tags | |
| hai_distill | no tags | |
| hai_mission_start | no tags | |
| hai_drift_check | no tags | |
| hai_proof | no tags | |
| hai_stop | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest379543be2a8ad429
Scanned2026-10-14
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.1.0. Pin a release below and the command asks for exactly that one.
0.1.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish HAI can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.