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

io.github.sachinuppal/modelcostsaver

NPM · @WORKSWARM/MODELCOSTSAVER · SCANNED AUG 3

Offline MCP: predict LLM call cost and pick the cheapest capable model. No keys, no network.

+17 this week 68 Trust /100
Trust breakdown (6 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 →

Supply Chain Security87
  • No malware found by supply-chain analysis.Pass
  • Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.Partial
  • No install/post-install scripts declared.Pass
  • Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability74
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1395 tokens (~174/item across 8 items; 7 tools + 1 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management23
  • Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage98
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 92% of tool parameters carry a description.Partial
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

npm · @workswarm/modelcostsaver

# add to Claude Code
claude mcp add sachinuppal-modelcostsaver -- npx -y @workswarm/modelcostsaver
# add to Codex CLI
codex mcp add sachinuppal-modelcostsaver -- npx -y @workswarm/modelcostsaver
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "sachinuppal-modelcostsaver": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@workswarm/modelcostsaver"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add sachinuppal-modelcostsaver --command npx --arg -y --arg @workswarm/modelcostsaver
# ~/.hermes/config.yaml
mcp_servers:
  sachinuppal-modelcostsaver:
    command: "npx"
    args: ["-y", "@workswarm/modelcostsaver"]
// mcp.json
{
  "mcpServers": {
    "sachinuppal-modelcostsaver": {
      "command": "npx",
      "args": [
        "-y",
        "@workswarm/modelcostsaver"
      ]
    }
  }
}
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.

  • 3 Aug 26 +3
    • Stability: unverified → 0.23 functional
  • 2 Aug 26 +60
    • Provenance: unverified → fail security
    • Malware scan: unverified → pass security
    • Install scripts: unverified → pass security
    • Known CVEs: unverified → partial security
    • Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
    • Tool coverage: unverified → 100 functional
    • Schema quality: unverified → 100 functional
    • Dependency health: unverified → partial functional
    • Maintenance: unverified → pass functional
    • MCP protocol: unverified → pass functional
    • Schema quality: unverified → good functional
    • License: unverified → pass functional
    • Licence: Apache-2.0 functional
  • 1 Aug 26 −20
    • Tool coverage: 100 → unverified functional
    • Schema quality: 100 → unverified functional
  • 31 Jul 26 −8
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 30 Jul 26 −18
    • Malware scan: pass → unverified security
  • 27 Jul 26 51

    First indexed and scored.

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 3 Aug 2026 · Analysed npm/@workswarm/[email protected]

Provenance none

Ecosystem: npm · Outcome: none

Dependencies 95 packages

95 packages in the resolved dependency tree · 95 deprecated · 29 stale.

The dependency tree was only partially resolved, so these counts may be incomplete.

MCP tools — 7 exposed · ~1,035 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.

Tool Tokens
compare_models ~120

Compare models side by side for a fixed token shape, cheapest first, with the multiple of the cheapest. Offline.

NameTypeReqDescription
inputTokensintegeryesInput tokens for the comparison.
modelsarrayyesModels to compare (alias or id).
outputTokensintegeryesOutput tokens for the comparison.
providersarrayAxis 1: provider availability allowlist (spec 5.4).
targetstringAxis 2: "self" (default) applies the client scope; "code" considers all providers.
NameTypeReqDescription
asOfstringyes
catalogVersionstringyes
cheaperIfAvailableobject
cheapestyes
mostCapableyes
providerScopearrayyes
rowsarrayyes
scopeSourcestringyes
unknownModelsarrayyes

No examples provided.

estimate_cost ~152

Estimate the cost of a single LLM call for one model from known or estimated token counts. Offline, no keys.

NameTypeReqDescription
charsPerTokennumberOverride the chars-per-token heuristic divisor.
expectedOutputTextstringExpected output text; estimated if outputTokens is absent.
inputTextstringPrompt text; estimated to tokens if inputTokens is absent.
inputTokensintegerExact input tokens; optional if inputText is given.
modelstringyesModel alias or full id, e.g. "sonnet" or "claude-sonnet-4-6".
outputTokensintegerExact output tokens; defaults to the model output cap.
NameTypeReqDescription
asOfstringyes
breakdownobjectyes
catalogVersionstringyes
costobjectyes
inputTokensnumberyes
modelstringyes
outputTokensnumberyes
pricingobjectyes
providerstringyes
tierstringyes
tokensWereEstimatedbooleanyes

No examples provided.

get_pricing ~103

Return the model catalog with pricing, optionally filtered. capabilities are arrays. Offline.

NameTypeReqDescription
capabilitystringRequire a capability.
includeLocalbooleanInclude local / self-hosted $0 models (off by default).
maxInputPerMillionnumberOnly models at or below this input price per 1M tokens.
providerstringFilter to a single provider.
tierstringFilter to a single tier.
NameTypeReqDescription
asOfstringyes
catalogVersionstringyes
countnumberyes
modelsarrayyes
sourcestringyes

No examples provided.

list_models ~102

Return the model catalog with pricing, optionally filtered. capabilities are arrays. Offline.

NameTypeReqDescription
capabilitystringRequire a capability.
includeLocalbooleanInclude local / self-hosted $0 models (off by default).
maxInputPerMillionnumberOnly models at or below this input price per 1M tokens.
providerstringFilter to a single provider.
tierstringFilter to a single tier.
NameTypeReqDescription
asOfstringyes
catalogVersionstringyes
countnumberyes
modelsarrayyes
sourcestringyes

No examples provided.

optimize_request ~172

Check whether a cheaper capable model exists for a call you plan to make, and report the savings. Offline.

NameTypeReqDescription
crossProviderbooleanConsider other providers too (may need a different API key). Default false.
currentModelstringyesThe model you plan to call (alias or id).
includeLocalboolean
inputTokensintegeryesInput tokens for the call.
outputTokensintegeryesOutput tokens for the call.
providersarrayAxis 1: provider availability allowlist (spec 5.4).
targetstringAxis 2: "self" (default) applies the client scope; "code" considers all providers.
taskClassstringTask class; sets the tier the recommendation must still meet.
NameTypeReqDescription
alreadyOptimalbooleanyes
asOfstringyes
catalogVersionstringyes
currentyes
providerScopearrayyes
reasoningarrayyes
recommendedyes
savingsPctnumberyes
savingsUsdnumberyes
scopeSourcestringyes

No examples provided.

predict_cost ~197

Forecast the cost of a prompt across candidate models before the call. Returns a cheapest-first ranking with assumptions. Offline.

NameTypeReqDescription
candidatesarrayCandidate models (alias or id); defaults to all chat-capable.
charsPerTokennumber
contextTokensintegerKnown context tokens already loaded.
expectedOutputTokensintegerExact output tokens; else inferred from taskClass/model.
includeLocalboolean
inputTokensintegerExact input tokens (skips prompt estimation).
promptstringThe prompt to forecast; estimated to tokens if inputTokens absent.
providersarrayAxis 1: provider availability allowlist (spec 5.4).
targetstringAxis 2: "self" (default) applies the client scope; "code" considers all providers.
taskClassstringDrives the default output cap.
NameTypeReqDescription
asOfstringyes
catalogVersionstringyes
cheaperIfAvailableobject
cheapestyes
forecastsarrayyes
notesarrayyes
providerScopearrayyes
scopeSourcestringyes

No examples provided.

select_optimal_model ~189

Pick the single cheapest model that meets the task tier, capabilities, and budget, with full reasoning and a fallbackChain. Offline.

NameTypeReqDescription
estimatedInputTokensintegeryesEstimated input tokens for the forecast.
estimatedOutputTokensintegeryesEstimated output tokens for the forecast.
includeLocalboolean
maxCostUsdnumberBudget ceiling for the predicted call cost.
providersarrayAxis 1: provider availability allowlist (spec 5.4).
requiredCapabilitiesarrayCapabilities the model must support.
targetstringAxis 2: "self" (default) applies the client scope; "code" considers all providers.
taskstringFree-text task; used for the tier heuristic when taskClass is absent.
taskClassstringExplicit task class; overrides the heuristic.
NameTypeReqDescription
asOfstringyes
budgetExceededboolean
catalogVersionstringyes
cheaperIfAvailableobject
fallbackChainarrayyes
providerScopearray
reasoningarrayyes
rejectedarrayyes
runnerUpobject
scopeSourcestring
selectedyes
shortfallUsdnumber

No examples provided.