tychi-agent-finance-mcp

tychi-agent-finance-mcp is a skill for Claude Code, Codex from TychiWallet/agent-finance. It costs 90 tokens per session (2,417 once invoked), scanned A, original, Apache-2.0.

A guide for operating Tychi Agent Finance, a service that gives AI agents self-custody wallets and policy-controlled blockchain actions. It covers setup, connection, onboarding, and the service’s financial tools.

In plain words
What is it for?
Use it when working with agent wallets, balances, portfolios, transfers, minting, blockchain spending, x402 paywalls, or Tychi identity. It also explains the required Node.js package, MCP host configuration, and environment variables.
Why use it?
It provides the required order for installing and connecting the service and explains its trust boundaries. This prevents attempting financial actions before the wallet service and permissions are ready.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/tychiwallet/agent-finance/model-context-protocol
Any agent
npx skills add TychiWallet/agent-finance --skill model-context-protocol
Clone the repo
git clone --depth 1 https://github.com/TychiWallet/agent-finance

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for tychi-agent-finance-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/tychiwallet/agent-finance/model-context-protocol.svg)](https://agentmods.dev/skills/tychiwallet/agent-finance/model-context-protocol)
Your own site
<a href="https://agentmods.dev/skills/tychiwallet/agent-finance/model-context-protocol"><img src="https://agentmods.dev/badge/skills/tychiwallet/agent-finance/model-context-protocol.svg" alt="Measured on agentmods" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,417 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00090 $0.02417
Opus 5 $0.00045 $0.01208
Sonnet 5 $0.00018 $0.00483
Haiku 4.5 $0.00009 $0.00242

Measured 4d ago against content hash 280ae37ac9d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tychi-agent-finance-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

The scan reads SKILL.md. This mod also ships 10 executable files (src/config/env.ts, src/context.ts, src/index.ts, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

framework-extensions/model-context-protocol/SKILL.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tychi Agent Finance MCP

Tychi is the financial home for AI agents: self-custody wallets in ~/.tyi, policy on every spend, local signing for transactions and x402.

This skill governs how you use the five MCP tools. Install and host config live in README.md.

Canonical machine index (read first if unfamiliar): llms.txt — category definition, install commands, MCP tool order, trust boundary, FAQ. On GitHub: https://github.com/TychiWallet/agent-finance/blob/main/llms.txt

Install → connect → onboard → use

Follow this sequence when the user wants agent banking but MCP is not ready yet:

1. Install (user action — you guide, you do not run npm)

Tell the user to install the MCP server globally:

npm install -g @tychilabs/agent-finance-mcp

Binary: agent-finance-mcp. Requires Node.js >= 20. Full install + env table: README.md · llms.txt (Install section).

2. Connect (user action — MCP host config)

User adds server tychi-agent-finance to Cursor / Claude Desktop / OpenClaw / Hermes MCP config with TYI_* env vars. Example configs: README.md. You cannot connect MCP yourself — confirm tychi-agent-finance is connected before any tool call.

3. Onboard (your tools — once per MCP process)

After connect: tyi_discovertyi_onboard. Never skip. Catalog-driven chainId, provider, actions. See Mandatory tool order below.

4. Use (your tools — every task)

tyi_run for tasks. tyi_resume_tx / tyi_resume_x402 only when tyi_run returns pending. State machine detail: llms.txt (MCP — V1 tools).


Before you call any tool

Confirm the MCP server tychi-agent-finance is connected. Required host env (never put these in chat or tool args):

Variable Required
TYI_API_BASE_URL yes
TYI_VAULT_PASSWORD yes
TYI_SESSION_PASSWORD yes
TYI_LLM_API_KEY yes
TYI_LLM_PROVIDER no (e.g. openai)
TYI_CHAIN_ID no*

Read the full file on GitHub · 237 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 237 lines · 90 tokens per session scan A 280ae37ac9d8

Subscribe to this mod's changes

tychi-agent-finance-mcp is a skill published in the GitHub repository TychiWallet/agent-finance (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 90 tokens to every session and 2,417 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.