Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

com.skopik/mcp

NPM · @SKOPIKLABS/MCP · 2 COMPONENTS

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

0 this week 81 Trust /100

Last scanned (22 hours ago)

Scores higher than 69% of npm servers

Category AI and Machine Learning

Degraded

One or more channels of this server are currently unreachable; their trust score is decaying and will reach 0 if they stay down.

Trust breakdown (7 categories)

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. How we score → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 31 of 92 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency19
  • Repository check failed: the declared repository URL returned HTTP 404. See how to fix → View diagnostics → Fail
  • Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 129 days ago).Pass
  • Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability86
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 1228 tokens (~76/item across 16 items; 13 tools + 3 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage99
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 97% of tool parameters carry a description.Partial
  • Structured output schemas are declared (85% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (15)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Security disclosure in Provenance & TransparencySecurity-disclosure policy not yet verified: we couldn't inspect the source repository.

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Nov 26 +1
    • Stability: 0.97 → pass security
  • 18 Nov 26 −1
    • Stability: pass → 0.97 functional
  • 12 Nov 26 +1
    • Stability: 0.97 → pass security
  • 10 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Nov 26 −2
    • Stability: pass → 0.90 functional
  • 3 Nov 26 +1
    • Stability: 0.97 → pass security
  • 2 Nov 26 −1
    • Stability: pass → 0.97 functional
  • 21 Oct 26 0
    • Stability: 0.97 → pass security
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Analysed npm/@skopiklabs/mcp@0.1.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 92 packages
Packages resolved 92
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 13 exposed · ~1,025 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
skopik_agent_get ~36

Fetch one agent by id, including its full configuration.

NameTypeReqDescription
agent_idstringyesAgent id (agent_...).
NameTypeReqDescription
agentobjectyes–

No examples provided.

skopik_agent_message ~158

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.

NameTypeReqDescription
agent_idstringyesAgent id (agent_...) to message.
conversation_idstring–Existing conversation id to continue. Omit to start a new DM with the agent.
textstringyesThe message text.
thread_idstring–Optional thread id to continue a specific thread.
wait_secondsnumber–Seconds to wait for the reply (default 25; 0 sends without waiting).
NameTypeReqDescription
conversation_idstringyes–
message_idstring|nullyesId of the message that was sent.
notestring––
repliesarrayyesAll agent/runtime messages observed for this run.
reply–yesThe agent's reply, when it arrived in time.
run_idstring|nullyesThe agent run processing the message; null if no agent was dispatched.
run_statusstring|nullyes–

No examples provided.

skopik_agents_list ~49

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

NameTypeReqDescription
user_idstring–Only agents owned by this user id.
NameTypeReqDescription
agentsarrayyes–

No examples provided.

skopik_api_get ~84

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.

NameTypeReqDescription
pathstringyesA Skopik API path beginning with /api/v1/.
queryobject–Optional query parameters.

No output schema declared.

No examples provided.

skopik_brain_read ~91

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.

NameTypeReqDescription
agent_idstringyesAgent id (agent_...).
pathstring–Brain file path (e.g. "AGENTS.md", "memory/MEMORY.md"). Omit to list files.
NameTypeReqDescription
brain_snapshotobject–Snapshot metadata (when listing).
fileobject–File content (when a path was given).
filesarray–File entries (when listing).

No examples provided.

skopik_run_get ~44

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

NameTypeReqDescription
run_idstringyesRun id.
NameTypeReqDescription
runobjectyes–

No examples provided.

skopik_search ~82

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

NameTypeReqDescription
agent_idstring–Restrict to one agent's content.
limitinteger–Maximum results (default 10).
modestring–Search mode (default hybrid).
querystringyesThe search query.
NameTypeReqDescription
diagnosticsobject––
resultsarrayyes–

No examples provided.

skopik_status ~50

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

NameTypeReqDescription
includeEnvironmentboolean–Include set/unset diagnostics for supported environment variables. Secret values are never returned.

No output schema declared.

No examples provided.

skopik_task_cancel ~58

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

NameTypeReqDescription
task_idstringyesTask id (task_...).
NameTypeReqDescription
taskobjectyes–

No examples provided.

skopik_task_create ~149

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).

NameTypeReqDescription
assigned_tostring–Agent id (agent_...) to assign the task to.
dispatchboolean–Immediately dispatch a run for the assigned agent.
prioritystring–Default medium.
project_idstring–Project to file the task under.
promptstringyesWhat the agent should do.
tagsarray––
titlestring–Short display title; derived from the prompt when omitted.
NameTypeReqDescription
dispatch_errorstring–Set when the task was created but the explicit dispatch failed.
run––The dispatched run, when dispatch=true succeeded.
taskobjectyes–

No examples provided.

skopik_task_get ~44

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

NameTypeReqDescription
task_idstringyesTask id (task_...).
NameTypeReqDescription
taskobjectyes–

No examples provided.

skopik_tasks_list ~87

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

NameTypeReqDescription
agent_idstring–Only tasks assigned to this agent.
parentstring–Only subtasks of this parent task id.
project_idstring–Only tasks in this project.
statusstring–Only tasks with this status.
NameTypeReqDescription
tasksarrayyes–

No examples provided.

skopik_usage_summary ~93

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

NameTypeReqDescription
end_atnumber–Window end (Unix ms).
kindstring–Restrict to one usage kind.
org_idstring–Org id; defaults to the caller's org.
start_atnumber–Window start (Unix ms).
NameTypeReqDescription
usageobjectyes–

No examples provided.

Install

How do I install the com.skopik/mcp server?

com.skopik/mcp runs locally as an npm package, launched with npx -y @skopiklabs/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @skopiklabs/mcp

# add to Claude Code
claude mcp add com-skopik-mcp -- npx -y @skopiklabs/mcp
Common questions

What is the com.skopik/mcp server?

com.skopik/mcp is listed in the public MCP registry as com.skopik/mcp. Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources. This page covers its npm package (@skopiklabs/mcp).

Is the com.skopik/mcp server safe to use?

com.skopik/mcp scores 81 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. 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 com.skopik/mcp server expose?

com.skopik/mcp exposes 13 tools: skopik_status, skopik_agents_list, skopik_agent_get, skopik_tasks_list, skopik_task_get, and 8 more. Their descriptions and schemas cost roughly 1,025 tokens of context every time the server is loaded.

Is the com.skopik/mcp server still maintained?

com.skopik/mcp is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the com.skopik/mcp server under?

com.skopik/mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the com.skopik/mcp server?

VerifyMCP ran 15 checks on com.skopik/mcp, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about com.skopik/mcp: Security disclosure. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.