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.

io.github.smigolsmigol/llmkit

NPM · @F3D1/LLMKIT-MCP-SERVER · SCANNED SEP 20

AI cost tracking: 11 tools for spend, budgets, and Claude Code + Cursor + Cline costs

0 this week 96 Trust /100
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 95 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to smigolsmigol/llmkit). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 35 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
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 377 tokens (~34/item across 11 items; 11 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management97
  • Stability observed for 29 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% 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
  • We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 11 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
Install

How do I install the io.github.smigolsmigol/llmkit MCP server?

io.github.smigolsmigol/llmkit runs locally as an npm package, launched with npx -y @f3d1/llmkit-mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @f3d1/llmkit-mcp-server

# add to Claude Code
claude mcp add smigolsmigol-llmkit -- npx -y @f3d1/llmkit-mcp-server
// .cursor/mcp.json
{
  "mcpServers": {
    "smigolsmigol-llmkit": {
      "command": "npx",
      "args": [
        "-y",
        "@f3d1/llmkit-mcp-server"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "smigolsmigol-llmkit": {
      "command": "npx",
      "args": [
        "-y",
        "@f3d1/llmkit-mcp-server"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add smigolsmigol-llmkit -- npx -y @f3d1/llmkit-mcp-server
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "smigolsmigol-llmkit": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@f3d1/llmkit-mcp-server"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add smigolsmigol-llmkit --command npx --arg -y --arg @f3d1/llmkit-mcp-server
# ~/.hermes/config.yaml
mcp_servers:
  smigolsmigol-llmkit:
    command: "npx"
    args: ["-y", "@f3d1/llmkit-mcp-server"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "smigolsmigol-llmkit": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@f3d1/llmkit-mcp-server"
      ]
    }
  }
}
# add to Vellum
assistant mcp add smigolsmigol-llmkit -t stdio -c npx -a -y @f3d1/llmkit-mcp-server
// mcp.json
{
  "mcpServers": {
    "smigolsmigol-llmkit": {
      "command": "npx",
      "args": [
        "-y",
        "@f3d1/llmkit-mcp-server"
      ]
    }
  }
}
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 Sept 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.

  • 16 Sept 26 −2
    • Stability: pass → 0.83 functional
  • 15 Sept 26 +1
    • Stability: 0.97 → pass security
  • 13 Sept 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.

  • 10 Sept 26 −2
    • Stability: pass → 0.83 functional
  • 9 Sept 26 +1
    • Stability: 0.97 → pass security
  • 7 Sept 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.

  • 4 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

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 20 Sept 2026 · Analysed npm/@f3d1/llmkit-mcp-server@0.4.10

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem npm
Reason Verified
Discovered via Registry attestation endpoint
Source repo smigolsmigol/llmkit
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/smigolsmigol/llmkit/.github/workflows/publish.yml@refs/heads/main
Rekor log index 2484081645
Predicate type https://slsa.dev/provenance/v1
Subject digest sha512:47d3e569894193fc364ca26f425a49f998c679c20c4864b671bae9149492f213c734f2919ca9828fb7595f27a5e2a139daed1c4d47d54645908e3ed1b

Background: How many MCP packages publish verified provenance →

Dependencies 95 packages
Packages resolved 95
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 11 exposed · ~377 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
llmkit_budget_status ~34

Check budget limits and remaining balance

NameTypeReqDescription
budgetIdstringSpecific budget ID, or omit for all
NameTypeReqDescription
budgetsarrayyes

No examples provided.

llmkit_cost_query ~72

Query cost breakdown grouped by provider, model, session, or day

NameTypeReqDescription
daysnumberDays to look back (default 30)
groupBystringyesHow to group results
modelstringFilter by model
providerstringFilter by provider
NameTypeReqDescription
breakdownarrayyes
daysnumberyes
groupBystringyes

No examples provided.

llmkit_health ~17

Check proxy health and response time

Input schema present but exposes no named parameters.

NameTypeReqDescription
responseTimeMsnumber
statusstringyes

No examples provided.

llmkit_list_keys ~21

List all API keys with status and creation date

Input schema present but exposes no named parameters.

NameTypeReqDescription
keysarrayyes

No examples provided.

llmkit_local_agents ~29

Subagent cost attribution for the current Claude Code session. Shows which agents cost the most.

Input schema present but exposes no named parameters.

NameTypeReqDescription
agentCountnumberyes
byTypearray
mainConversationCostUsdnumber
sessionIdstringyes
subagentsTotalCostUsdnumber
totalCostUsdnumberyes

No examples provided.

llmkit_local_cache ~28

Cache savings analysis across all detected AI coding tools. Shows how much prompt caching saved.

Input schema present but exposes no named parameters.

NameTypeReqDescription
savingsarray
totalSavedUsdnumberyes

No examples provided.

llmkit_local_forecast ~28

Monthly cost projection based on local AI tool usage. Compares to Max subscription.

Input schema present but exposes no named parameters.

NameTypeReqDescription
dailyAverageUsdnumberyes
maxSubscriptionSavingsUsdnumber
projectedMonthlyUsdnumberyes
totalSessionsnumber
totalTrackedUsdnumber

No examples provided.

llmkit_local_projects ~30

Cumulative cost across all projects and sessions from all detected AI coding tools, ranked by spend.

Input schema present but exposes no named parameters.

NameTypeReqDescription
projectsarrayyes
totalCostUsdnumberyes

No examples provided.

llmkit_local_session ~32

Current session cost across all detected AI coding tools (Claude Code, Cline). No API key needed.

Input schema present but exposes no named parameters.

NameTypeReqDescription
sessionsarray
sourceCountnumberyes
totalCostUsdnumberyes

No examples provided.

llmkit_session_summary ~49

Get recent proxy sessions with cost, duration, and models used

NameTypeReqDescription
limitnumberNumber of sessions (default 10)
sessionIdstringSpecific session ID
NameTypeReqDescription
sessionsarrayyes

No examples provided.

llmkit_usage_stats ~37

Get usage statistics (spend, requests, top models) for a time period

NameTypeReqDescription
periodstringTime period
NameTypeReqDescription
cacheHitRatenumber
cacheReadTokensnumber
inputTokensnumber
outputTokensnumber
periodstringyes
requestsnumberyes
topModelsarray
totalSpendUsdnumberyes

No examples provided.

Common questions

What is the io.github.smigolsmigol/llmkit MCP server?

io.github.smigolsmigol/llmkit is an MCP server listed in the public MCP registry as io.github.smigolsmigol/llmkit. AI cost tracking: 11 tools for spend, budgets, and Claude Code + Cursor + Cline costs. This page covers its npm package (@f3d1/llmkit-mcp-server).

Is the io.github.smigolsmigol/llmkit MCP server safe to use?

io.github.smigolsmigol/llmkit scores 96 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. 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 io.github.smigolsmigol/llmkit MCP server expose?

io.github.smigolsmigol/llmkit exposes 11 tools: llmkit_usage_stats, llmkit_cost_query, llmkit_list_keys, llmkit_budget_status, llmkit_health, and 6 more. Their descriptions and schemas cost roughly 377 tokens of context every time the server is loaded.

Is the io.github.smigolsmigol/llmkit MCP server still maintained?

io.github.smigolsmigol/llmkit is still listed as active in the MCP registry. We last reached this channel on 20 September 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 io.github.smigolsmigol/llmkit MCP server under?

io.github.smigolsmigol/llmkit declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.