@bitcoinbenji/mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BITCOIN_BENJI_API_KEY | No | Pre-funded API key to skip manual payment loop. Get one from https://api.bitcoinbenji.com or /api/key/create |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_feesB | Bitcoin fee estimates with trend analysis (next-block, 30-min, 1-hour) from a full node mempool. [10 sats per call] |
| get_whalesB | Recent whale alerts: large transfers, consolidations, distributions in the mempool. [40 sats per call] |
| get_mempool_stateB | Live Bitcoin mempool state: tx count, byte size, fee histogram. [5 sats per call] |
| get_mempool_historyA | Rolling 24h snapshots of mempool size and fees. [50 sats per call] |
| predict_feesB | EMA-based fee prediction with confidence + direction (rising/falling). [50 sats per call] |
| get_recent_blocksC | Recent Bitcoin block data: heights, tx counts, timestamps. [10 sats per call] |
| tx_statusA | Lookup a Bitcoin transaction by txid: confirmations, fee, block height, mempool ETA. [15 sats per call] |
| fee_quoteA | Exact fee quote for a planned tx: {inputs, outputs, target_blocks, input_type}. [15 sats per call] |
| ai_summarizeB | Summarize text (short/medium/long). [20 sats per call] |
| ai_sentimentC | Sentiment analysis with confidence score. [10 sats per call] |
| ai_translateB | Translate between 100+ languages. [20 sats per call] |
| ai_grammarC | Fix grammar, spelling, and punctuation. [15 sats per call] |
| ai_code_reviewB | Code review for bugs, security, and performance issues. [50 sats per call] |
| ai_extractB | Extract structured data from text (entities/contacts/dates/custom schema). [25 sats per call] |
| ai_scrapeB | Scrape & extract clean readable text from any URL. [15 sats per call] |
| ai_agentB | General-purpose AI agent — handles any text task. [30 sats per call] |
| ai_classifyC | Classify text into your provided categories. [10 sats per call] |
| ai_rewriteB | Rewrite text in a different style/tone. [15 sats per call] |
| ai_explainC | Explain any topic at the requested level. [25 sats per call] |
| ai_embedB | 768-dim embedding vector for RAG (single text or batch). [2 sats per call] |
| ai_visionC | Vision QA over an image URL (Qwen3-VL, sovereign). [40 sats per call] |
| ai_ocrA | Extract all visible text from an image URL. [25 sats per call] |
| ai_code_generateC | Generate code from a natural-language spec. [40 sats per call] |
| ai_longformB | Summarize huge documents (~50K words) in one flat-fee call. [75 sats per call] |
| ai_transcribe_tableB | Convert a table image into JSON rows. [35 sats per call] |
| ai_researchB | Multi-step web research + cited synthesis. [100 sats per call] |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 26 tools
All AI tools have distinct purposes (e.g., classify, summarize, translate) and are clearly delineated by the 'ai_' prefix. The Bitcoin tools are also distinct from each other and from the AI tools, leaving no ambiguity.
The AI tools consistently use 'ai_' prefix, but the Bitcoin tools mix 'get_' (get_fees, get_mempool_state) with other patterns (fee_quote, predict_fees), creating an inconsistent overall naming convention.
26 tools is on the high side but reasonable given the dual domain (18 AI + 8 Bitcoin). Each tool appears justified, and the count is not excessive for the scope.
The AI toolset covers many common tasks (generation, review, embedding, OCR, research, etc.). The Bitcoin toolset covers mempool, fees, and transaction status, though it lacks some operations like broadcasting.