Floe Working Capital
About
Gives AI agents (Claude, Cursor, custom) full access to working capital to pay x402 receipts.
Details
- Author
- floe-labs
- Categories
- Finance, Other, AI
Jump to
Setup
Install Floe Working Capital in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/floe-labs/floe-mcp-server
Follow the installation instructions in the repository README, then restart your MCP client.
The unified billing ledger for voice AI, over MCP.Give Claude Desktop, Claude Code, Cursor, CrewAI, or any MCP client one key for every voice tool and model a voice agent uses —STT, TTS, LLM, telephony— plus 2,000+ vendor API services, with budgets the agent can reason about. Walletless. No crypto required.
Website·Docs·Dashboard·𝕏 @FloeLabs
73 tools covering the full agent lifecycle — create agents, mint/rotate keys, set budgets, estimate costs, andexecute x402 payments— with transport-aware auth (remote HTTP uses a Bearer token; local stdio readsFLOE_API_KEYfrom the env) and akeyless tier(get_markets,check_x402_url,search_floe_docswork with no key at all).
Start free.A$3 Welcome Credit (300 API credits)on signup — no card, no wallet.Get an agent key →
One key for your agent's whole vendor bill — LLM, voice, telephony, search, data — metered per call and budget-capped. Let your coding agent set it up, or wire it yourself:
New accounts get a$3 Welcome Credit (300 API credits)— no card.Set up with your AI tools →·Get a key →
Most payment tools let an agentspend. Floe lets an agentreason about spend before it commits— and stops it before it overruns.
- Agent-awareness tools—get_credit_remaining,estimate_x402_cost,get_loan_state: your agent asks "do I have budget? is this call worth it?"beforepaying, not after.
- Context-aware budgets— set a session spend cap; the agent tapers as it nears the limit and replans to finish on budget.
- The Floe agent skill(Floe-Labs/agent-skills) — the playbook that turns those tools into deliberate spending behavior.Jump to it ↓
- Server-side enforcement— the soft signal is the skill; the hard ceiling is the on-chain spend cap + merchant allowlist. The agent cannot overspend regardless of what it decides.
# Universal (any MCP-aware client) npx -y add-mcp https://mcp.floelabs.xyz/mcp # Claude Code claude mcp add --transport http floe https://mcp.floelabs.xyz/mcp --header "Authorization: Bearer YOUR_FLOE_KEY" # Codex (reads the key from $FLOE_API_KEY at connect time) codex mcp add floe --url https://mcp.floelabs.xyz/mcp --bearer-token-env-var FLOE_API_KEY
{ "mcpServers": { "floe": { "url": "https://mcp.floelabs.xyz/mcp", "headers": { "Authorization": "Bearer floe_YOUR_AGENT_KEY" } } } }
Get your agent key:dashboard→ Create agent → copy thefloe_<hex>key (shown once). Or from the CLI:npx @floelabs/cli init— paste your dashboard developer key and it creates (or selects) the agent and mints the key for you. No key yet? The server still works — seeKeyless tier.
Scope params— narrow what a session can do straight from the URL:
https://mcp.floelabs.xyz/mcp?read_only=true # only non-mutating tools https://mcp.floelabs.xyz/mcp?features=spend,pricing # only the named capability groups
Capability groups:lending,spend,pricing,lifecycle,observability,payments,webhooks,docs. Both params combine. The Floe agent skill's decision loop needsspend,pricing.
→Local stdio, global install, and key taxonomy below
Full per-tool reference is inTools (73)below.
Option 1 (remote) is inQuick startabove. For local runs:
Run the server locally. It proxies all requests to the Floe API.
FLOE_API_KEY=floe_YOUR_AGENT_KEY npx -y @floelabs/mcp-server --stdio
{ "mcpServers": { "floe": { "command": "npx", "args": ["-y", "@floelabs/mcp-server", "--stdio"], "env": { "FLOE_API_KEY": "floe_YOUR_AGENT_KEY" } } } }
{ "mcpServers": { "floe": { "command": "npx", "args": ["-y", "@floelabs/mcp-server", "--stdio"], "env": { "FLOE_API_KEY": "floe_YOUR_AGENT_KEY" } } } }
npm install -g @floelabs/mcp-server FLOE_API_KEY=floe_YOUR_AGENT_KEY floe-mcp --stdio
--stdioand--httpare explicit overrides. With neither flag, the server picks by what stdin is:a pipe(an MCP client spawning it) → stdio; a terminal or a service manager's/dev/null→ HTTP on127.0.0.1:3100. So a barecommand: npxconfig now works — but keep--stdioin configs anyway so behavior never depends on how the client wires stdio. On startup failure the process logs[floe-mcp] Fatal:to stderr and exits with code 1; in stdio mode all logging goes to stderr, never stdout (which carries the MCP protocol).
The server starts (and the hosted endpoint answers)without any key. Keyless sessions get exactly three tools with live results:get_markets,check_x402_url, andsearch_floe_docs— enough to vet a vendor, price a call, and learn the API before signup. Every other tool returns a structured error:
{ "error": "AUTH_REQUIRED", "status": 401, "message": "…Requires an agent key (floe_...).", "next": "Get a developer key at https://dev-dashboard.floelabs.xyz, then mint agent keys with create_agent_key. …" }
Tool errors always carry the backend's HTTPstatus(so agents can distinguish 401/403/404/429), and 401/403 include a remediation hint that distinguishesmissing keyfromwrong key type.
Two key formats unlock different surfaces — every tool description states which one it needs:
Typical bootstrap: connect with thedeveloper key→create_agent→create_agent_key→ reconnect (or open a second MCP session) with the mintedagent keyto spend.
- Go todev-dashboard.floelabs.xyz
- Connect your wallet andCreate an agent(name + borrow limit + max rate)
- Copy thefloe_<64-hex>key shown at the end of the wizard — it is revealed once
# Platform CLI — interactive: paste your developer key, create or select an # agent, and the minted agent key lands in your OS keychain # (manage agent keys later with floe keys list|create|rotate|revoke, # developer keys with floe devkeys) npx @floelabs/cli init # SDK-level alternatives: # TypeScript SDK npx floe-agent register --name my-agent --borrow-limit 10000 # Python SDK floe-agent register --name my-agent --borrow-limit 10000
The platform CLI and this MCP server cover the same API surface.@floelabs/cliis the full platform from a terminal — agents, keys, budgets, policies, billing, funds, phone, metered calls — with--jsonon every command and stable exit codes for scripts and CI. MCP remains the richer in-context integration: tools your agent discovers, reasons over, and calls mid-session without shelling out.
Get adeveloper key(unlocks the lifecycle tools —create_agent, key minting, budgets, funding, webhooks — and multi-tenant visibility across all your agents):
- Go todev-dashboard.floelabs.xyz/keys
- ClickCreate Key, label it, pickreadorread_writepermissions
- Copy thefloe_live_<base62>key shown once
Developer keys span the whole developer account and have a separate rate limit (100 req/min). Agent-runtime tools (get_credit_remaining,get_spend_limit,x402_pay, etc) return 401 with a developer key because the caller is the developer, not a single agent — the error'snexthint says so and points atcreate_agent_key. See theAPI Keys docsfor the full taxonomy.
Fund with fiat:You can fund your wallet with USDC via Coinbase — credit card, bank transfer, Apple Pay, Google Pay — directly from the dashboard. No crypto on-ramp needed.
One Floe developer can own many agents. To run several MCP sessions side by side (e.g. a research agent and a trading agent), mint one key per agent and configure each MCP client entry with its own key:
{ "mcpServers": { "floe-research": { "url": "https://mcp.floelabs.xyz/mcp", "headers": { "Authorization": "Bearer floe_KEY_FOR_RESEARCH_AGENT" } }, "floe-trading": { "url": "https://mcp.floelabs.xyz/mcp", "headers": { "Authorization": "Bearer floe_KEY_FOR_TRADING_AGENT" } } } }
Each session is scoped to one agent — credit lines, spend limits, and webhooks stay isolated.
Below the tools are listed by request type. The summary is inTools at a glanceabove. Every description also names the key it needs:agent key(floe_...),developer key(floe_live_...), any key, or none. The feature-group tag in each heading is what?features=filters on.
Payment execution (payments,pricing) ⭐
The reason the rest exists: estimate → forecast →pay.x402_payneeds an agent key;check_x402_urlis keyless.
Agent lifecycle (lifecycle) — developer key
Bootstrap and manage the fleet without touching the dashboard.
Funding & observability (observability) — developer key
Write tools (lending, return unsigned transactions)
Lets an agent answer "do I have credit?", "is this call worth it?", and "where am I in the loan lifecycle?" before committing capital. All require an agent API key (floe_). The calling identity is taken from the Bearer header in HTTP mode, or fromFLOE_API_KEYin stdio mode.
Opt-in, default-deny restriction onwhich destinationsthe agent may pay. An allowlist entry is an ordinary capped policy row that doubles as "allowed AND capped". Default modeoff= allow any vendor (zero onboarding friction). All require an agent API key (floe_).
Floe's agent skills live in their own repo:Floe-Labs/agent-skills.
Soft signal, not the guardrail.The skill helps a cooperative agent spend wisely. The real ceiling is enforcedserver-side— the on-chain credit line, the session spend cap, and (if configured) the merchant allowlist refuse calls past the limit regardless of what the agent decides.
npx skills add floe-labs/agent-skills # skills.sh CLI # or manually: git clone https://github.com/floe-labs/agent-skills cp -r agent-skills/skills/floe ~/.claude/skills/ # or .claude/skills/ per-project
All write tools returnunsigned transactions— the server never holds private keys.
1. Call a write tool (e.g., create_counter_intent) → Returns { transactions: [...], summary, warnings, expiresAt } 2. (Optional) Call simulate_transaction to dry-run 3. Sign each transaction locally with your wallet 4. Call broadcast_transaction with the signed hex → Returns { transactionHash, status, blockNumber }
Agent: "I need 9,950 USDC working capital" 1. get_open_lend_intents → browse USDC/USDC offers 2. create_counter_intent(offer_hash, wallet) → unsigned txs 3. simulate_transaction(from, to, data) → { success: true, gasEstimate } 4. Sign locally → signed hex 5. broadcast_transaction(signed_hex) → confirmed
import { createWalletClient, http } from "viem"; import { privateKeyToAccount } from "viem/accounts"; import { base } from "viem/chains"; const wallet = createWalletClient({ account: privateKeyToAccount(PRIVATE_KEY), chain: base, transport: http(), }); // Sign and send each transaction in order for (const { transaction: tx } of response.transactions) { const hash = await wallet.sendTransaction({ to: tx.to, data: tx.data, value: BigInt(tx.value), }); // Wait for confirmation before next step }
import { Client } from "@modelcontextprotocol/sdk/client"; import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js"; const client = new Client({ name: "my-agent" }); await client.connect(new StreamableHTTPClientTransport( new URL("https://mcp.floelabs.xyz/mcp"), { requestInit: { headers: { "Authorization": "Bearer floe_..." } } } )); const markets = await client.callTool("get_markets", {}); const counter = await client.callTool("create_counter_intent", { offer_hash: "0x...", wallet_address: "0x...", });
from langchain_mcp_adapters import MultiServerMCPClient async with MultiServerMCPClient({ "floe": {"url": "https://mcp.floelabs.xyz/mcp", "headers": {"Authorization": "Bearer floe_..."}} }) as client: tools = client.get_tools() # Use tools in your agent
CrewAI agents can consume the Floe MCP tools vialangchain-mcp-adapters. A runnable crew is available infloe-cookbook/crewai-demo.
Your Agent → MCP Server → credit-api.floelabs.xyz → Envio Indexer / Base RPC ↑ ↑ This package Private backend (open source) (holds secrets)
The MCP server is a thin HTTP client. All protocol logic, indexer queries, and RPC calls happen in the private Floe API backend. This package contains only tool definitions andfetch()calls.
Floe is thespend layerfor AI agents — one key that pays any vendor API under programmable budgets (everything above). Italsoexposes an advanced, crypto-nativeintent-based lending layeron Base, for agents that want working capital against deposits:
- Primary market (USDC/USDC):Deposit USDC as collateral, borrow up to 99.5% as a credit line. No price-volatility risk — same-token market.
- Volatile markets:Also supports WETH and cbBTC collateral for crypto-native use cases.
- Solversautomatically match compatible intent pairs on-chain.
- Loansare created with matched terms, collateral locked in per-loan isolated escrow.
- Gas-free— Floe sponsors all transaction costs.
- Fixed rates— no variable-rate surprises.
- Intent: An on-chain offer to lend or borrow
- Counter-Intent: An intent created to match an existing offer
- Health Factor: Ratio of collateral value to debt — below threshold triggers liquidation
- LTV (Loan-to-Value): Borrower's debt as % of collateral value
- Website
- Dashboard
- Documentation
- Platform CLI (@floelabs/cli)
- TypeScript SDK (floe-agent)
- Python SDK (floe-agentkit-actions)
- End-to-end examples
akta.pro MCP connects Claude, ChatGPT, Cursor, VS Code, and other MCP clients to enterprise-grade private company data and real-time news signals. 20M+ entity-resolved companies, 70+ data points each, 30K+ sub-sectors monitored, and ~80% news noise filtered — pay-as-you-go.
A serverless Monzo → Claude connector on Cloudflare Workers
There are already a few Monzo MCP servers (partymola, BfdCampos, an npm one), and they're good — but they're all local stdio servers you run on your own machine. This is the first remote/serverless one I've found: it lives on a Cloudflare Worker, so you authenticate once and it follows you to every Claude surface, with nothing to keep running.
Read-only bank access for your AI agent. Hosted MCP server giving Claude, ChatGPT, Cursor, Gemini, and Codex access to bank accounts, transactions, and investment holdings via Plaid. 12 tools. $5/mo per bank.
I built an MCP server/connector to fetch financial data for all listed stocks on NSE and BSE. It can pull things like QoQ profit/revenue growth for any stock, price trends, promoter holdings, institutional investors, new company declarations, and more. I’ve also built 25 tools within the MCP to support different financial-data use cases. Today, if you ask Claude for personal finance or stock-related advice, it usually relies on web searches or stale training data. The reasoning might still be sound, but the underlying data sources can be outdated or unreliable. With this MCP/connector, Claude can use a more reliable source of truth for financial data, which should help: Improve the quality of results Reduce the token usage spent on web searches
Send invoices from inside Claude and ChatGPT: one sentence becomes a ready-to-send invoice with PDF and payment link.
Free MCP server for SaaS founders. Ask Claude how many months of cash you have left, factoring in MRR growth and churn, and it calls this tool instead of guessing. No signup, no API key, no backend. Just add the connector and ask.
Tenant-bound MCP tools for agent spend authorization, evidence, receipts, and settlement in Cursor, Codex, and Claude Code.
Connect Claude or ChatGPT to your live trading account — check quotes and positions, and place, modify or close trades with a two-step confirm (trading scope only, never withdrawals).
Free MCP server for founders. Ask Claude how many months of runway you have left, and it calls this tool instead of guessing off vibes. No signup, no API key, no backend. Just add the connector and ask.
The Schwab Model Context Protocol (MCP) Server connects your Schwab account to LLM-based applications (like Claude Desktop or other MCP clients), allowing them to retrieve market data, check account status, and (optionally) place orders under your supervision.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
