# com.skopik/mcp (npm · @skopiklabs/mcp)

Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.

- Trust score: 65/100 (medium)
- Change this week: +47
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-04

## Components

- remote · `api.skopik.com`: 23/100, [markdown](https://verifymcp.io/servers/com-skopik-mcp/api.md), [page](https://verifymcp.io/servers/com-skopik-mcp/api)
- npm · `@skopiklabs/mcp`: 65/100 (this document), [markdown](https://verifymcp.io/servers/com-skopik-mcp/skopiklabs-mcp.md), [page](https://verifymcp.io/servers/com-skopik-mcp/skopiklabs-mcp)

## Channel facts

- Registry: `npm`
- Package: `@skopiklabs/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 2026-08-04.

- **Supply Chain Security**: 83/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known medium-severity CVE affects hono 4.12.33, reached via @modelcontextprotocol/sdk > hono. A fixed version is available.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 19/100
  - Repository check failed: the declared repository URL returned HTTP 404.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 20 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 84/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1228 tokens (~76/item across 16 items; 13 tools + 3 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 99/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 97% of tool parameters carry a description.
  - Structured output schemas are declared (85% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add com-skopik-mcp -- npx -y @skopiklabs/mcp
```

### Codex

```bash
codex mcp add com-skopik-mcp -- npx -y @skopiklabs/mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-skopik-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@skopiklabs/mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-skopik-mcp --command npx --arg -y --arg @skopiklabs/mcp
```

### Hermes

```yaml
mcp_servers:
  com-skopik-mcp:
    command: "npx"
    args: ["-y", "@skopiklabs/mcp"]
```

### Other

```json
{
  "mcpServers": {
    "com-skopik-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@skopiklabs/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.

### 2026-08-04 (score 65, 0)

- [security regression] CVE-2026-69207 affects this package: medium
- [security regression] Known CVEs: partial → fail

### 2026-08-02 (score 65, +39)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional improvement] Stability: unverified → 0.23
- [functional] Licence: MIT

### 2026-08-01 (score 26, +5)

- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] MCP protocol: unverified → pass

### 2026-07-31 (score 21, −26)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 47, +29)

- [functional improvement] Schema quality: unverified → 100
- [functional improvement] Tool coverage: unverified → 100

### 2026-07-28 (score 18, −29)

- [functional regression] Schema quality: 100 → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-07-27 (score 47)

First indexed and scored.

## MCP tools (13)

### `skopik_status` (~50 tokens)

Skopik Status

Return MCP server diagnostics, configured Skopik API base URL, and exposed capabilities.

Input parameters:

- `includeEnvironment` (boolean): Include set/unset diagnostics for supported environment variables. Secret values are never returned.

### `skopik_agents_list` (~49 tokens)

List agents

List the AI agents in the caller's Skopik org: identity, status, model, and capability fields.

Input parameters:

- `user_id` (string): Only agents owned by this user id.

Output parameters:

- `agents` (array)

### `skopik_agent_get` (~36 tokens)

Get agent

Fetch one agent by id, including its full configuration.

Input parameters:

- `agent_id` (string, required): Agent id (agent_...).

Output parameters:

- `agent` (object)

### `skopik_tasks_list` (~87 tokens)

List tasks

List tasks in the caller's org, optionally filtered by status, assigned agent, project, or parent task.

Input parameters:

- `agent_id` (string): Only tasks assigned to this agent.
- `parent` (string): Only subtasks of this parent task id.
- `project_id` (string): Only tasks in this project.
- `status` (string): Only tasks with this status.

Output parameters:

- `tasks` (array)

### `skopik_task_get` (~44 tokens)

Get task

Fetch one task by id, including prompt, status, assignment, and its canonical run id.

Input parameters:

- `task_id` (string, required): Task id (task_...).

Output parameters:

- `task` (object)

### `skopik_run_get` (~44 tokens)

Get run

Fetch one run (a single agent execution) by id: status, messages, cost, and error if any.

Input parameters:

- `run_id` (string, required): Run id.

Output parameters:

- `run` (object)

### `skopik_search` (~82 tokens)

Search platform content

Semantic + lexical search over the org's indexed files, documents, and agent brains. Returns scored text chunks.

Input parameters:

- `agent_id` (string): Restrict to one agent's content.
- `limit` (integer): Maximum results (default 10).
- `mode` (string): Search mode (default hybrid).
- `query` (string, required): The search query.

Output parameters:

- `diagnostics` (object)
- `results` (array)

### `skopik_brain_read` (~91 tokens)

Read agent brain

Read an agent's active brain snapshot (its versioned memory and identity files). Without a path: lists all files. With a path: returns that file's content.

Input parameters:

- `agent_id` (string, required): Agent id (agent_...).
- `path` (string): Brain file path (e.g. "AGENTS.md", "memory/MEMORY.md"). Omit to list files.

Output parameters:

- `brain_snapshot` (object): Snapshot metadata (when listing).
- `file` (object): File content (when a path was given).
- `files` (array): File entries (when listing).

### `skopik_usage_summary` (~93 tokens)

Usage summary

Aggregate usage and cost for the caller's org: total cost in USD, tokens, and call counts. Fields are camelCase.

Input parameters:

- `end_at` (number): Window end (Unix ms).
- `kind` (string): Restrict to one usage kind.
- `org_id` (string): Org id; defaults to the caller's org.
- `start_at` (number): Window start (Unix ms).

Output parameters:

- `usage` (object)

### `skopik_agent_message` (~158 tokens)

Message an agent

Send a chat message to a Skopik agent and wait for its reply. Starts a new DM conversation unless conversation_id (from a previous call) is given. Returns the reply when it arrives within wait_seconds; otherwise returns the run id to poll with skopik_run_get.

Input parameters:

- `agent_id` (string, required): Agent id (agent_...) to message.
- `conversation_id` (string): Existing conversation id to continue. Omit to start a new DM with the agent.
- `text` (string, required): The message text.
- `thread_id` (string): Optional thread id to continue a specific thread.
- `wait_seconds` (number): Seconds to wait for the reply (default 25; 0 sends without waiting).

Output parameters:

- `conversation_id` (string)
- `message_id`: Id of the message that was sent.
- `note` (string)
- `replies` (array): All agent/runtime messages observed for this run.
- `reply`: The agent's reply, when it arrived in time.
- `run_id`: The agent run processing the message; null if no agent was dispatched.
- `run_status`

### `skopik_task_create` (~149 tokens)

Create task

Create a task in the caller's org, optionally assigned to an agent. Assignment normally auto-dispatches a run; set dispatch=true to force an immediate run and get its id back (requires the agents:run scope).

Input parameters:

- `assigned_to` (string): Agent id (agent_...) to assign the task to.
- `dispatch` (boolean): Immediately dispatch a run for the assigned agent.
- `priority` (string): Default medium.
- `project_id` (string): Project to file the task under.
- `prompt` (string, required): What the agent should do.
- `tags` (array)
- `title` (string): Short display title; derived from the prompt when omitted.

Output parameters:

- `dispatch_error` (string): Set when the task was created but the explicit dispatch failed.
- `run`: The dispatched run, when dispatch=true succeeded.
- `task` (object)

### `skopik_task_cancel` (~58 tokens)

Cancel task

Cancel a task (and cascade to its open subtasks). Only unassigned, assigned, in_progress, or blocked tasks can be cancelled; terminal tasks are rejected.

Input parameters:

- `task_id` (string, required): Task id (task_...).

Output parameters:

- `task` (object)

### `skopik_api_get` (~84 tokens)

Skopik API GET

Escape hatch: call any read-only Skopik API endpoint under /api/v1. Prefer the skopik_* domain tools when one covers the need. Use skopik_api_describe to discover available paths.

Input parameters:

- `path` (string, required): A Skopik API path beginning with /api/v1/.
- `query` (object): Optional query parameters.

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/com-skopik-mcp/skopiklabs-mcp#diagnostics

## Score history

- 2026-08-04: 65
- 2026-08-03: 65
- 2026-08-02: 65
- 2026-08-01: 26
- 2026-07-31: 21
- 2026-07-30: 47
- 2026-07-28: 18
- 2026-07-27: 47

## Links

- npm package: https://www.npmjs.com/package/@skopiklabs/mcp
- Socket report: https://socket.dev/npm/package/@skopiklabs/mcp
- Website: https://skopik.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-skopik-mcp/skopiklabs-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-skopik-mcp/skopiklabs-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/com-skopik-mcp/skopiklabs-mcp