MCP Server for Z.AI - A Model Context Protocol server that provides AI capabilities
Nothing to run from here
SkillOS 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.
93/100
trust score
25
downloads a day
local
runs on your machine
909
downloads in 30d
What it does
An open standard and MCP runtime for discovering, activating, and composing reusable AI agent skills with evidence-grounded workflows.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user skillos-mcp '--' npx -y skillos-mcp-server
# 2 — ask your agent for something these tools do
# list_skills, activate_skill, get_skill_info and 5 more
SkillOS costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publisher
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 SkillOS 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 Node.js — the current LTS (24) is the safe choice; npx 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 skillos-mcp '--' npx -y skillos-mcp-serverReconnect, 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 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
8 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.
List all available SkillOS Labs Inc skills in the registry. Filter by tier (0-4) or domain keyword. Shows SDS compliance status for each skill.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tier | integer | no | Filter by tier (0=Foundational, 1=Domain, 2=Technology, 3=Pattern, 4=Orchestration). Omit for all tiers. |
| domain | string | no | Filter by domain keyword (case-insensitive). E.g. 'security', 'mobile', 'database'. |
| include_archived | boolean | no | Include archived (superseded) skill versions. Default: false. |
Activate a SkillOS Labs Inc skill. The model will operate under that skill's full professional identity, decision engine, constraint matrix, failure mode library, and quality gates. SDS compliance is enforced — incomplete skills cannot be activated.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| skill_name | string | yes | The skill_name from list_skills (e.g., 'software_architect', 'mobile_specialist') |
| version | string | no | Specific version to activate (e.g., '1.0.0'). Defaults to the latest stable version. |
| archive | boolean | no | Set to true to activate an archived (older) version. Requires version to also be specified. |
| temperature_override | string | no | Override the skill's default temperature mode. Conservative for high-stakes domains, creative for prototyping. |
| api_key | string | no | SkillOS Labs Inc platform API key (sk-os_...). Required to access premium or enterprise-only skills. Free-tier skills work without a key. |
Get detailed information about a skill including its Collaboration Contract (typed I/O), validation status, and SDS compliance report. Use this to plan workflows before activating skills.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| skill_name | string | yes | The skill_name to inspect (e.g., 'backend_specialist') |
Execute a multi-skill workflow in sequence. Each skill in the chain receives the output of the previous one as additional context, with constraints (regional_context, compliance requirements) propagating automatically through the chain.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workflow | array | yes | Ordered list of skill_names to activate in sequence (minimum 2). E.g. ['software_architect', 'backend_specialist', 'database_specialist'] |
| initial_context | string | yes | The user's request or project description to feed into the first skill in the chain. |
| temperature_override | string | no | Apply the same temperature mode to all skills in the chain. |
| api_key | string | no | SkillOS Labs Inc platform API key (sk-os_...). Required if any skill in the workflow is premium or enterprise-only. |
| permission_scope | array | no | Bounded permission scopes that propagate across all skills in the chain (e.g. ['read:only', 'env:staging']) |
| handoff_constraints | array | no | Mandatory constraints and contracts passed between skill transitions. |
Design an optimal multi-skill workflow for a given task. Returns a recommended skill sequence with rationale, handoff fields, and estimated complexity — without activating any skills.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| task | string | yes | Describe the task or project you need help with. Be as specific as possible about the technology stack, scale, constraints, and deliverables. |
| max_steps | integer | no | Maximum number of skills in the workflow (2-6). Default: 4. |
| prefer_tier | integer | no | Prefer skills at or above this tier level. Omit to let the router decide. |
Route a user request to the single best-matching skill. Returns the recommended skill with confidence score and explanation. Use this when you want one skill, not a full workflow.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| request | string | yes | The user's request or question. The router will match it to the best skill. |
| domain_hint | string | no | Optional domain keyword to narrow the search (e.g. 'security', 'frontend', 'database'). |
List all available and configured external tool connectors in SkillOS Labs Inc (GitHub, PostgreSQL, Slack, Stripe, M-Pesa, etc.). Shows integration status and capabilities.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| category | string | no | Filter by category: 'Developer Tools', 'Data', 'Communication', 'Finance', 'Productivity' |
Test connectivity to a SkillOS Labs Inc tool connector (e.g. 'github', 'slack', 'postgresql'). Verifies credentials and reports connection health.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | The connector slug to test (e.g., 'github', 'slack', 'postgresql') |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under Apache-2.0
- 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 SkillOS 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 93 / 100
Release 3.0.3 · scanned 15 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 score93
Findings2 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digest581217d3fab3d5fd180bf2f88748fbb9e8a3ac2cb687cbce63f1d9cff08f5907
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| 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 (8 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. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| list_skills | no tags | |
| activate_skill | external-sink | external-sink: handler sends an HTTP POST (fetch(${PLATFORM_API_URL}/api/entitlements/check) at dist/index.js:121, handler sends an HTTP POST (fetch(${PLATFORM_API_URL}/api/mcp/activate) at dist/index.js:147 |
| get_skill_info | no tags | |
| chain_skills | external-sink | external-sink: handler sends an HTTP POST (fetch(${PLATFORM_API_URL}/api/entitlements/check) at dist/index.js:121 |
| create_workflow | no tags | |
| get_skill_routing | no tags | |
| list_connectors | no tags | |
| test_connector | 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 digest581217d3fab3d5fd
Scanned2026-10-15
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 3.0.3. Pin a release below and the command asks for exactly that one.
3.0.3
10 Oct 2026
latestNo release note was published with this version.
3.0.2
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
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 SkillOS 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.