Skip to content

BitCLI MCP server

io.github.BitCLI-io/bitcli-mcp-serverBitCLI-iostreamable-httpv1.0.0Scanned

Real-time crypto futures order flow, BCT-30 matrices, and HFT alerts across 1,650+ contracts.

6 tools: 1 do something that can't be undone and 5 change things.

Tools: 0 delete, 1 irreversible, 5 write, 0 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 1
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here does something that can't be undone. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the BitCLI MCP server can do

The BitCLI MCP server is published by the GitHub account BitCLI-io. It has 6 tools. It can do things that cannot be undone, such as sending, paying or publishing (send_notification) and create or change data (5 tools: system_docs, market_data, calc_engine, alert_manager and 1 more), but cannot delete data. None of its tools only reads.

1 tool can send data out of your system (send_notification).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 12, 2026, version 1.0.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

6 tools

Can't be undone 1Claude Code: ask
  • send_notificationBEHAVIOR: Outbound messaging operation.Can send data outNo findings

    Why it is in this group

    • The name "send_notification" says "send": a word for sending, and what is sent cannot be taken back.

    What it can reach

    • outboundThe name "send_notification" says "send": it sends or publishes something to other people.
    Description, as the server wrote it
    BEHAVIOR: Outbound messaging operation. Routes proactive notifications to the human trader's verified Telegram chat, channel, or Discord webhook. Dispatches discretionary trade ideas, market condition updates, or risk reports to keep the user informed without waiting for prompts. PRICING: $0.001 USD per dispatch. Deducted from daily tariff quota or USD balance. PARAMETER INTERACTIONS: - 'target': Destination identifier string obtained from `user_account.list_destinations`. Prefixes determine transport: 'tg_user:' / 'tg_channel:' for Telegram, 'out_wh:' for Discord webhooks. Must belong to the authenticated account. - 'message': Main message body. For Telegram, supports HTML tags. For Discord, maps to the embed description. - 'title': Optional subject line. For Discord, renders as the embed headline. For Telegram, prepends as a bold header if provided. RETURNS: Structured JSON confirming transmission: 'status' ('dispatched'), 'target', 'message_length', 'timestamp_utc', and '_usage' (cost_usd and remaining quota/balance). USAGE GUIDELINES: Call `user_account` with action='list_destinations' prior to sending to retrieve valid target strings. Use this tool exclusively for informative messaging and human-in-the-loop updates. Do NOT use this tool to monitor market prices or set execution triggers (use `alert_manager` instead). ERRORS: Unauthenticated calls, unverified/foreign destinations, empty messages, or exhausted quotas return an explicit 'isError: true' payload.
Changes things 5Claude Code: ask
  • alert_managerBEHAVIOR: State-mutating operation.No findings

    Why it is in this group

    • The input takes a statement or command to run (input.command), which can change anything it can reach.
    Description, as the server wrote it
    BEHAVIOR: State-mutating operation. Injects or removes in-memory execution triggers in the C++ engine. When triggered, it dispatches asynchronous out-of-band notifications (Telegram/Discord) without requiring the agent to remain awake. PRICING: Targeted coin alerts cost $0.001 USD. Global wildcard scans ('*') cost $0.002 USD. Wildcards require a positive USD balance on Free/Trader plans. ACTIONS & PARAMETER INTERACTIONS: - 'create': Deploys a new trigger. Requires 'command'. Returns the assigned alert_id and expiration time. - 'list': Returns an array of currently active triggers, their IDs, and remaining TTLs. Ignores 'command' and 'alert_id'. - 'cancel': Removes a specific trigger. Requires 'alert_id'. Ignores 'command'. - 'clear_all': Purges all active triggers for the account. Ignores 'command' and 'alert_id'. USAGE GUIDELINES: Use this tool to establish asynchronous monitoring instead of polling `market_data`. Requires an authenticated API key; anonymous guests will receive an authorization error. Enforces plan capacity limits. ERRORS: Authentication failures, capacity limit breaches, or syntax errors return an explicit 'isError: true' payload detailing the rejection reason.
  • calc_engineBEHAVIOR: Deterministic mathematical calculation.No findings

    Why it is in this group

    • The input takes a statement or command to run (input.command), which can change anything it can reach.
    Description, as the server wrote it
    BEHAVIOR: Deterministic mathematical calculation. Evaluates crypto futures risk management models using live exchange parameters. PRICING: $0.001 USD per execution. Deducted from daily tariff quota or USD balance. SYNTAX EXAMPLES (Passed in 'command'): - '/pos btc 65k 63.7k 50' (Position Sizing) - '/liq sol 20x short' (True Liquidation with MMR) - '/dca btc 65k:100 64k:200' (DCA Break-Even with exit fees) - '/rr btc 65k 64k 67k 69k' (Multi-Target R:R) - '/fncost btc 10000 long' (Carry Cost) - '/atr btc 1h 2' (Volatility Stops) RETURNS: Output is a structured JSON payload. Depending on the command, keys include: 'ideal_lot_coins', 'notional_usd', 'required_margin', 'liquidation_price', 'true_breakeven_price', 'effective_rr_ratio', or 'stop_distance'. USAGE GUIDELINES: Use this tool exclusively for mathematical risk modeling and lot sizing. For live market scanning, use `market_data`. For setting execution triggers, use `alert_manager`. After calculating risk parameters, it is highly recommended to route the generated stop-loss or liquidation prices into `alert_manager` to automate monitoring. ERRORS: Malformed syntax returns an 'error' JSON key with correction guidance.
  • market_dataBEHAVIOR: Read-only analytical gateway.No findings

    Why it is in this group

    • The input takes a statement or command to run (input.command), which can change anything it can reach.
    Description, as the server wrote it
    BEHAVIOR: Read-only analytical gateway. Fetches real-time derivatives intelligence across Binance, Bybit, and Hyperliquid. PRICING: $0.001 USD per execution. Deducted from daily tariff quota or USD balance. ACTIONS & RETURNS: - 'screener': Scans 1,650+ perpetuals to catch pumps, dumps, whale volume spikes, and short squeezes. Returns a JSON array of matched assets containing fields: symbol, price, rvol, fund, oi, oichg, rsi, bias, natr, cvd. - 'consensus': Returns JSON with Quant TA consensus score, CVD slope, RSI, ATR, and EMA bias for a single coin. - 'bct_matrix': Returns compact historical candlestick matrices with server-side computed indicators to minimize token usage. USAGE GUIDELINES: Use this to analyze market state or find trade setups. Do NOT use this tool to continuously poll for price updates or wait for conditions to be met; instead, invoke `alert_manager` to establish asynchronous monitoring. ERRORS: Malformed filters or unlisted tickers return an explicit JSON error object with syntax correction guidance.
  • system_docsBEHAVIOR: Read-only RAG documentation tool.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    BEHAVIOR: Read-only RAG documentation tool. Reads and returns official BitCLI markdown specifications, indicator formulas, CLI command guides, and webhook setups. Returns a single string containing the requested Markdown document. PRICING: Free ($0.000). Does not consume quotas. USAGE GUIDELINES: Use this tool FIRST to understand BitCLI mechanics, verify command grammar, or check webhook templates before constructing queries. Do NOT use this tool to query live market prices or active triggers (use `market_data` or `alert_manager` instead). TOPICS: - 'syntax': Price targets, percentage corridors, velocity moves. - 'calculators': Position sizing, true MMR liquidation, DCA break-even, multi-target R:R. - 'market_intel': Screener filters, cross-exchange aggregation. - 'indicators': CVD divergence, Z-Scores, 8h normalized funding. - 'webhooks': PineScript relay setup, private chat routing. - 'tariffs': Subscription tiers and limits. - 'partners': Affiliate program rules. - 'ai': AI Copilot features. - 'mcp': Model Context Protocol architecture, API key setup, and Cursor IDE integration. - 'index': System overview. ERRORS: Requesting an invalid topic returns a structured JSON error indicating the file was not found.
  • user_accountBEHAVIOR: Read-only configuration query.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    BEHAVIOR: Read-only configuration query. Inspects user ledger states, subscription tiers, and verified notification endpoints. PRICING: Free ($0.000). Does not consume daily quotas or balance. ACTIONS: - 'get_billing': Returns subscription tier, available daily USD API quota, remaining USD balance, active alert count, and per-key daily spending safety limits. - 'list_destinations': Returns verified external dispatch targets (Telegram chat IDs, Discord Webhooks) that can be supplied to the `alert_manager`. USAGE GUIDELINES: Use this tool at the beginning of a workflow to understand available budget and determine valid delivery destinations. Do NOT use this tool to manage triggers (use `alert_manager`) or query market data (use `market_data`). ERRORS: Unauthenticated requests lacking a valid API key return an HTTP 401 equivalent error with a registration portal link.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 21, 2026, 19:23 UTC, unchanged since Nov 7, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
6
Protocol version
2024-11-05
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
yes
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 6 tools that change things (1 irreversible, 5 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.bitcli.io/mcp: tools/list returned 6 tools to an anonymous client, including send_notification (irreversible), system_docs (write), market_data (write), calc_engine (write), alert_manager (write) and 1 more

    What this check looks for

Posture changes

  1. Nov 7, 2026
    • RFC 9728 protected resource metadata: https://mcp.bitcli.io/.well-known/oauth-protected-resource/mcp to none
    • Authorization servers: https://my.bitcli.io to none
    • Dynamic client registration: yes to not observed
    • Client ID metadata documents: no to not observed

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools2 changed.~2 changedView diff
  2. PostureRemote posture changed. RFC 9728 protected resource metadata: https://mcp.bitcli.io/.well-known/oauth-protected-resource/mcp -> none; Authorization servers: https://my.bitcli.io -> none; Dynamic client registration: yes -> not observed (and…View diff
    • RFC 9728 protected resource metadata: https://mcp.bitcli.io/.well-known/oauth-protected-resource/mcp to none
    • Authorization servers: https://my.bitcli.io to none
    • Dynamic client registration: yes to not observed
    • Client ID metadata documents: no to not observed

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http bitcli https://mcp.bitcli.io/mcp
claude mcp add --transport http bitcli https://mcp.bitcli.io/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__bitcli__system_docs",
      "mcp__bitcli__market_data",
      "mcp__bitcli__calc_engine",
      "mcp__bitcli__alert_manager",
      "mcp__bitcli__user_account",
      "mcp__bitcli__send_notification"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as bitcli. Review it before you use it.

Capability tags behind 1 rule
  • mcp__bitcli__send_notification outbound

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.BitCLI-io/bitcli-mcp-server/verify?hash=8af47c10cccbb01a0ab69e9ae9f7811fee774d91538a84238dc5874f365f9787" | jq -e '.changed == false'

Pinned hash 8af47c10cccb, from Nov 12, 2026, 00:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.BitCLI-io/bitcli-mcp-server/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.BitCLI-io/bitcli-mcp-server
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.BitCLI-io/bitcli-mcp-server.svg)](https://radar.anlyon.com/servers/io.github.BitCLI-io/bitcli-mcp-server)

Source: MCP Registry · repository. Synced Oct 30, 2026, 08:17 UTC.

BitCLI MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the BitCLI MCP server safe?

No scan can promise that. What its definitions show: 6 tools, 6 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the BitCLI MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the BitCLI MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: send_notification.

What tools does the BitCLI MCP server have?

6 tools: 1 irreversible, 5 write. send_notification, system_docs, market_data, calc_engine, alert_manager and user_account.

Does the BitCLI MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the BitCLI MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): send_notification.

Has the BitCLI MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 12, 2026. Every change is on this page and in its Atom feed.