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.

com.ibitlabs.www/ibitlabs-mcp

NPM · IBITLABS-MCP · SCANNED AUG 3

iBitLabs live receipts: real balance, trades, shadow rules & saga from a $1k→$10k AI experiment.

Available components

+23 this week 63 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 Security86
  • No malware found by supply-chain analysis.Pass
  • Only part of the dependency tree could be resolved (94 of 98), 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 (94 of 98), so this covers what we could see, not the whole tree. 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 90 days ago).Pass
  • Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability71
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 497 tokens (~99/item across 5 items; 5 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management27
  • Stability observed for 8 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
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 · ibitlabs-mcp

# add to Claude Code
claude mcp add com-ibitlabs-www-ibitlabs-mcp -- npx -y ibitlabs-mcp
# add to Codex CLI
codex mcp add com-ibitlabs-www-ibitlabs-mcp -- npx -y ibitlabs-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-ibitlabs-www-ibitlabs-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "ibitlabs-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add com-ibitlabs-www-ibitlabs-mcp --command npx --arg -y --arg ibitlabs-mcp
# ~/.hermes/config.yaml
mcp_servers:
  com-ibitlabs-www-ibitlabs-mcp:
    command: "npx"
    args: ["-y", "ibitlabs-mcp"]
// mcp.json
{
  "mcpServers": {
    "com-ibitlabs-www-ibitlabs-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "ibitlabs-mcp"
      ]
    }
  }
}
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 +4
    • Stability: unverified → 0.27 functional
  • 2 Aug 26 +22
    • Provenance: fail → unverified security
    • Install scripts: pass → unverified security
    • Known CVEs: unverified → partial security
    • Malware scan: unverified → pass security
    • Maintenance: pass → unverified functional
    • License: pass → unverified functional
    • Dependency health: unverified → partial functional
    • Licence: MIT functional
  • 31 Jul 26 −5
    • 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 −30
    • Known CVEs: partial → unverified security
    • Malware scan: pass → unverified security
    • Dependency health: partial → unverified functional
  • 29 Jul 26 +32
    • Provenance: unverified → fail security
    • Known CVEs: unverified → partial security
    • Install scripts: unverified → pass security
    • Schema quality: unverified → good functional
    • Maintenance: unverified → pass functional
    • Dependency health: unverified → partial functional
    • License: unverified → pass functional
    • Licence: MIT functional
  • 27 Jul 26 40

    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/[email protected]

Provenance none

Ecosystem: npm · Outcome: none

Dependencies 94 packages

94 packages in the resolved dependency tree · 94 deprecated · 29 stale.

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

MCP tools — 5 exposed · ~497 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
get_latest_saga_chapter ~91

Latest saga chapter narrating the experiment in human prose — pulls from /data/saga_vol2.json and returns the entry for the requested language. Use when you want a human-readable summary of the most recent state, not just numbers. The saga is updated daily (or near-daily) and pairs with the trading data above.

NameTypeReqDescription
langstringSaga language. Default `en`.

No output schema declared.

No examples provided.

get_live_status ~78

Current account snapshot from the live $1k → $10k experiment: balance, total/unrealized PnL, win rate, fees, funding cost, current open position (if any), reconciliation timestamp. Sourced from /api/live-status. Use when you need the actual current state of the bot instead of a backtest figure.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_recent_trades ~89

List the most recent N closed trades with entry/exit/PnL/regime tags. Use this to cite real fills (e.g. for a research post or an example in a strategy doc). Sourced from /data/recent_trades.json, regenerated after each morning/evening sniper check.

NameTypeReqDescription
limitintegerNumber of recent closed trades to return (1-100).

No output schema declared.

No examples provided.

get_rule_status ~126

Per-rule shadow log statistics: number of fires, per-bucket hit rates, distance from the 4-condition promotion bar (≥30/bucket, ≥15pp spread, direction match, no confounding shadow). Use when reviewing whether a contributor's rule is on track to graduate from log-only shadow to a real entry gate. Sourced from /data/rule_status.json, regenerated after each morning/evening sniper check.

NameTypeReqDescription
rule_idstringyesSingle uppercase letter rule id (e.g. 'C', 'D', 'E', 'F', 'G').

No output schema declared.

No examples provided.

list_adopted_rules ~113

List all contributor-proposed shadow rules: adopted (in production observation-only mode, with 30-day promotion windows) and queued_for_review (proposed but not yet wired). Each row carries proposer handle, frame, source post URL, rule_id, code_location, shadow_log path, review window, and current points. Sourced from /data/contributors.json. Use to see who has contributed encodable frames to the bot.

NameTypeReqDescription
statusstringFilter by review_status. Default is `all`.

No output schema declared.

No examples provided.