Which integrations are available for this server?

Provides a wallet backend via Nostr Wallet Connect (Alby) to automatically pay Lightning invoices for AI service calls. Allows reviewing code from GitHub repositories by specifying the URL with the review_code_url tool. Allows reviewing code from GitLab repositories by specifying the URL with the review_code_url tool.

How do I use boltwork-mcp?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@boltwork-mcp trial_summarise: Summarise this text about climate change." That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

boltwork-mcp

by Squidboy30

Overview Schema Source Related Servers Discussions Admin

Python

Remote

mcp-name: io.github.Squidboy30/boltwork-mcp

boltwork-mcp

MCP server for Boltwork — AI services that pay for themselves via Bitcoin Lightning.

Give your AI agent PDF summarisation, code review, translation, web extraction, document comparison, and persistent memory — all paid autonomously in sats. No API keys. No subscriptions. No accounts.

What this is

Boltwork is a pay-per-call AI services API that uses the L402 protocol — your agent makes a request, receives a Lightning invoice, pays it automatically, and gets the result back. No human involved.

This package wraps Boltwork as an MCP server so any MCP-compatible AI (Claude, Cursor, Windsurf, etc.) can use it as a tool — with payments handled transparently in the background.

Related MCP server: Pylon MCP Server

Try it immediately — no wallet required

Two tools work right now with zero setup:

{
  "mcpServers": {
    "boltwork": {
      "command": "uvx",
      "args": ["boltwork-mcp"],
      "env": {}
    }
  }
}

Then ask your AI:

"Use trial_review_code to review this: def add(a, b): return a + b"
"Use trial_summarise to summarise this: <paste any text>"

Real AI results instantly. No Lightning wallet. No setup. Rate limited to 5 calls/hour.

Install

pip install boltwork-mcp

# If using NWC (Alby, Mutiny, Coinos, etc.):
pip install "boltwork-mcp[nwc]"

Or use directly with uvx — no install needed:

uvx boltwork-mcp

Setup — pick a wallet

Four wallet backends are supported. Pick whichever fits your setup:

Option A — NWC / Nostr Wallet Connect (easiest)

Works with Alby, Mutiny Wallet, Coinos, Primal, Cashu.me, and any NWC-compatible wallet.

Get a connection string:
- Alby — go to nwc.getalby.com, create a budget, copy the string
- Mutiny — Settings → Connections → Add connection
- Coinos — coinos.io → Settings → Nostr Wallet Connect
Add to your MCP config:

{
  "mcpServers": {
    "boltwork": {
      "command": "uvx",
      "args": ["boltwork-mcp"],
      "env": {
        "NWC_CONNECTION_STRING": "nostr+walletconnect://your-string-here"
      }
    }
  }
}

Requires: pip install "boltwork-mcp[nwc]"

Option B — LNbits

Works with lnbits.com or any self-hosted LNbits instance. Popular with BTCPay Server users and home node operators.

Create a wallet at lnbits.com or your instance
Go to API info → copy your Invoice/read key

{
  "mcpServers": {
    "boltwork": {
      "command": "uvx",
      "args": ["boltwork-mcp"],
      "env": {
        "LNBITS_URL": "https://lnbits.com",
        "LNBITS_API_KEY": "your-invoice-key-here"
      }
    }
  }
}

For self-hosted: set LNBITS_URL to your instance URL (e.g. https://lnbits.yourdomain.com).

Option C — Strike

Works with a Strike account. Custodial, simple API key setup. Good for US users or anyone who already uses Strike.

Create an account at strike.me
Go to dashboard.strike.me/developers/api-keys → create an API key

{
  "mcpServers": {
    "boltwork": {
      "command": "uvx",
      "args": ["boltwork-mcp"],
      "env": {
        "STRIKE_API_KEY": "your-api-key-here"
      }
    }
  }
}

Option D — Phoenixd

Works with Phoenixd — ACINQ's self-hosted Lightning node. Simple REST API, no channel management.

Install Phoenixd: phoenix.acinq.co/server
Get your HTTP password from the Phoenixd config

{
  "mcpServers": {
    "boltwork": {
      "command": "uvx",
      "args": ["boltwork-mcp"],
      "env": {
        "PHOENIXD_URL": "http://localhost:9740",
        "PHOENIXD_PASSWORD": "your-password-here"
      }
    }
  }
}

MCP config locations

Client	Config file
Claude Desktop (macOS)	`~/Library/Application Support/Claude/claude_desktop_config.json`
Claude Desktop (Windows)	`%APPDATA%\Claude\claude_desktop_config.json`
Cursor	`.cursor/mcp.json` in your project
Windsurf	`~/.codeium/windsurf/mcp_config.json`

Available tools

Tool	What it does	Cost
`trial_summarise`	Summarise text — free trial	Free
`trial_review_code`	Review code — free trial	Free
`summarise_pdf`	Summarise a PDF from URL	500 sats
`summarise_webpage`	Summarise any web page	100 sats
`review_code`	Full code review with bugs, security, quality	2000 sats
`review_code_url`	Review code from GitHub/GitLab URL	2000 sats
`extract_data`	Extract structured data from PDF	200 sats
`translate`	Translate text or document (24 languages)	150 sats
`extract_tables`	Extract all tables from a PDF	300 sats
`compare_documents`	Diff two PDFs	500 sats
`explain_code`	Explain code in plain English	500 sats
`memory_store`	Store persistent agent memory	10 sats
`memory_retrieve`	Retrieve agent memory	5 sats
`memory_delete`	Delete a memory key	Free
`run_workflow`	Chain multiple services in one call	1000 sats

Payment flow

When your agent calls a paid tool:

boltwork-mcp calls the Boltwork API
Receives HTTP 402 with a Lightning invoice
Pays the invoice automatically using your configured wallet
Retries the request with the payment proof
Returns the result to your agent

Your agent never sees this — it just gets the result.

Available Tools

18 tools

analyse_contractA

Analyse a contract PDF and return structured intelligence. Returns risk score, key clauses, obligations, termination triggers, red flags, and recommended actions in plain English. Costs 1000 sats via Lightning. Use for: NDAs, SaaS agreements, employment contracts, leases, any legal document.

Inputs: url (required), max_pages.

analyse_imageA

Analyse an image from a URL. Returns structured description including content type, objects detected, any visible text (OCR), dominant colors, sentiment, and tags. Costs 200 sats via Lightning. Supported formats: JPEG, PNG, GIF, WebP.

Inputs: url (required), detail.

compare_documentsA

Compare two PDF documents and return a structured diff. Identifies additions, removals, modifications, and overall similarity. Costs 500 sats via Lightning. Use for: contract versions, policy updates, paper revisions.

Inputs: url_a (required), url_b (required), max_pages.

explain_codeA

Explain what code does in plain English. Unlike code review (which finds problems), this explains purpose and behaviour to a non-programmer. Costs 500 sats via Lightning. Use for: understanding inherited code, due diligence, onboarding docs.

Inputs: code, url, language.

extract_dataA

Extract structured data from a PDF document. Returns document type, dates, parties, amounts, line items, and reference numbers. Costs 200 sats via Lightning. Use for: invoices, contracts, receipts, forms.

Inputs: url (required), max_pages.

extract_tablesA

Extract all tables from a PDF as structured JSON. Returns table count, headers, rows, and a summary. Costs 300 sats via Lightning. Use for: financial reports, research data, invoices with line items.

Inputs: url (required), max_pages.

memory_deleteA

Delete a single key from your agent's memory store. Free.

Inputs: agent_id (required), key (required).

memory_listA

List all keys stored for your agent, optionally filtered by prefix. Useful for discovering stored context without fetching values. Free — no Lightning payment required.

Inputs: agent_id (required), prefix.

memory_retrieveA

Retrieve stored memory for your agent. Returns all keys or a specific subset. Costs 5 sats via Lightning.

Inputs: agent_id (required), keys.

memory_storeA

Store persistent key-value memory for your agent. Data persists across sessions, keyed by agent_id. Up to 100 keys per agent, 10 keys per write call. Costs 10 sats via Lightning.

Inputs: agent_id (required), entries (required), ttl_seconds.

review_codeA

Review source code and return a structured analysis covering bugs, security issues, code quality, strengths, and recommended actions. Returns an overall score 1-10. Costs 2000 sats via Lightning. Supports: Python, JavaScript, TypeScript, Go, Rust, Java, C/C++, C#, Ruby, PHP, Swift, Kotlin, Scala, Shell, SQL, Terraform, and more.

Inputs: code (required), language, filename.

review_code_urlA

Review code fetched from a URL. Supports GitHub and GitLab blob URLs (auto-converted to raw). Costs 2000 sats via Lightning.

Inputs: url (required), language.

run_workflowA

Chain multiple Boltwork services in a single call. Pay once, describe a pipeline of up to 5 steps, get the final result plus all intermediate outputs. Use {"$from": N} in any input value to pass the primary output of step N into the current step. Costs 1000 sats via Lightning. Supported services: webpage, pdf, summarise, translate, data, tables, explain, review, compare. Example: fetch a webpage, translate the summary to French — steps: [{service: webpage, input: {url: ...}}, {service: translate, input: {text: {$from: 0}, target_language: french}}]

Inputs: steps (required), label.

summarise_pdfA

Summarise a PDF document from a URL. Returns a structured summary including title, key points, sentiment, topics, and word count. Costs 500 sats via Lightning. Use for: research papers, reports, contracts, any PDF.

Inputs: url (required), max_pages.

summarise_webpageA

Summarise any web page by URL. Returns title, summary, key points, content type, sentiment, and topics. Costs 100 sats via Lightning. Use for: articles, blogs, documentation, product pages, news.

Inputs: url (required).

translateA

Translate text or a document URL to any of 24 supported languages. Detects source language automatically. Costs 150 sats via Lightning. Supported languages: Spanish, French, German, Italian, Portuguese, Dutch, Russian, Japanese, Chinese, Korean, Arabic, Hindi, Turkish, Polish, Swedish, Danish, Norwegian, Finnish, Czech, Romanian, Hungarian, Greek, Hebrew, Thai.

Inputs: target_language (required), text, url.

trial_review_codeA

FREE trial code review — no Lightning wallet required. Reviews up to 500 characters of code for bugs, security issues, and quality. Returns the same structured JSON as the full review_code tool. Rate limited to 5 calls per hour per IP. Use this to try Boltwork before setting up a wallet. For full code review with no limits, use review_code (2000 sats).

Inputs: code (required).

trial_summariseA

FREE trial text summarisation — no Lightning wallet required. Summarises up to 1000 characters of text. Returns title, summary, key points, sentiment, and topics. Rate limited to 5 calls per hour per IP. Use this to try Boltwork before setting up a wallet. For full PDF/webpage summarisation, use summarise_pdf or summarise_webpage.

Inputs: text (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4/5.0

Scored 2026-05-28 08:05 across 18 tools

Disambiguation4/5

Most tools have distinct purposes, but some PDF-related tools (analyse_contract, extract_data, summarise_pdf) could cause confusion if the agent misinterprets the task. The trial tools are clearly separate as limited versions.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern in snake_case (e.g., analyse_contract, compare_documents). The memory tools share a common prefix, and trial tools are prefixed with 'trial_'. No naming conflicts or style mixing.

Tool Count4/5

18 tools cover a broad range of services (PDF, image, code, translation, memory, workflow). While slightly above the typical 3-15 range, the tools are well-scoped and justified by the platform's breadth.

Completeness4/5

The tool surface covers core operations for the domain: analysis, extraction, comparison, translation, summarisation, memory, and code review. Missing potentially useful tools (e.g., image generation) but no critical gaps for the advertised functionality.

Maintenance

ActivityInactive

ResponsivenessNo recent community issues

Resources

Related MCP Connectors

Task402 Agent Evidence ToolsB
xyz.task402
Paid evidence tools for PDFs, public webpages, OpenAPI contracts, and Base chain data for AI agents.
Browser Automation Blockchain RAG Systems
1
https://task402.xyz/mcp
intelligence
app.tinkrr
Bitcoin and YouTube video intelligence for AI agents. Pay-per-call via x402 USDC on Base.
Cryptocurrency Blockchain Entertainment & Media
2
https://tinkrr-api.tinkrr.workers.dev/mcp
Lightning WalletB
io.github.lightningfaucet
Give AI agents a Bitcoin wallet with Lightning Network payments and L402 support.
Blockchain Cryptocurrency Payments & Billing
86111
https://lightningfaucet.com/mcp
WingmanProtocol Agent GatewayB
com.wingmanprotocol.agent
Durable memory, headless browser and research for agents. Pay per call: x402 USDC on Base or credits
Agent Orchestration Blockchain
6123
https://agent.wingmanprotocol.com/mcp

Related MCP Servers

giskard-memory
Knowledge & Memory Vector Databases Autonomous Agents
giskard09
A
license
Not graded
quality
C
maintenance
Pay-per-use semantic memory for AI agents with cryptographic attestation. Vector embeddings with SHA256 commitment, secp256k1 signature, and Lightning invoice.
Updated a month ago (2026-10-07 12:51 UTC)
Apache 2.0
Pylon MCP Serverofficial
Web Scraping Browser Automation Image & Video Processing
pylonapi
A
license
Not graded
quality
D
maintenance
Provides 20+ AI agent capabilities like web scraping, PDF parsing, OCR, and more, with pay-per-use micropayments via x402.
Updated 9 months ago (2026-02-19 15:44 UTC)
1
MIT
DocImprint Documentofficial
RAG Systems Search AI & Machine Learning
sawftware-apps
A
license
A
quality
D
maintenance
Verifiable document intelligence for AI agents. Extract text, tables, and structured data from PDFs and URLs. Summarize, answer questions, check claims, and translate — all with cited evidence. Store tamper-evident evidence bundles with cryptographic signatures and on-chain attestation via Base L2. Cross-document semantic search and Q&A across named collections. Pay per call with USDC
Updated 4 months ago (2026-07-26 09:02 UTC)
22
8 npm
1
MIT
PayAgents MCP Serverofficial
Payments & Billing Cryptocurrency Autonomous Agents
Payagents
A
license
A
quality
D
maintenance
Enables AI agents to autonomously make policy-controlled payments for APIs and tools via Bitcoin Lightning (L402) and Base USDC (x402), including paying paywalled endpoints, checking balances, and reviewing transactions.
Updated 3 months ago (2026-08-22 16:43 UTC)
3
12 npm
1
MIT

boltwork-mcp

What this is

Try it immediately — no wallet required

Install

Setup — pick a wallet

Option A — NWC / Nostr Wallet Connect (easiest)

Option B — LNbits

Option C — Strike

Option D — Phoenixd

MCP config locations

Available tools

Payment flow

Links

Available Tools

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

giskard-memory

Pylon MCP Serverofficial

DocImprint Documentofficial

PayAgents MCP Serverofficial