mcp-usage

mcp-usage is a cursor rule for coding agents from PostOakLabs/ainumbers-mcp-apps. It costs 17 tokens per session (383 once invoked), scanned A, original, MIT.

A set of rules for using AINumbers, a remote server with read-only fintech compliance tools and workflows. It helps an agent find tools, connect them into workflows, run them, and verify the results.

In plain words
What is it for?
It is for finding tools for areas such as anti-money-laundering checks, crypto tax, liquidity, and agent payments. It can also run named or custom multi-step workflows and produce execution records.
Why use it?
It removes the need to search a large catalogue manually or connect each finance-related step yourself. It also provides a way to check that a returned result has not changed.

Cursor rule

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 rules/postoaklabs/ainumbers-mcp-apps/mcp-usage
Clone the repo
git clone --depth 1 https://github.com/PostOakLabs/ainumbers-mcp-apps

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 mcp-usage

README.md
[![agentmods](https://agentmods.dev/badge/rules/postoaklabs/ainumbers-mcp-apps/mcp-usage.svg)](https://agentmods.dev/rules/postoaklabs/ainumbers-mcp-apps/mcp-usage)
Your own site
<a href="https://agentmods.dev/rules/postoaklabs/ainumbers-mcp-apps/mcp-usage"><img src="https://agentmods.dev/badge/rules/postoaklabs/ainumbers-mcp-apps/mcp-usage.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 383 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 $0.00017 $0.00383
Opus 5 $0.00009 $0.00192
Sonnet 5 $0.00003 $0.00077
Haiku 4.5 $0.00002 $0.00038

Measured 3d ago against content hash 384d724a0cd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-usage 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 3d ago.

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.

rules/mcp-usage.mdc · 23 lines

What it actually says

AINumbers MCP server

Remote server at https://mcp.ainumbers.co/mcp (streamable HTTP, no auth, zero PII, all tools read-only).

Discovery flow

  1. find_tool or list_ainumbers_tools — search the catalog (532 client-side fintech tools) by keyword. Returns deep-links; prefill-enabled tools accept a #in=… hash parameter for one-click invocation with values already filled in.
  2. find_chain or build_workflow_links — look up a named multi-tool workflow (266 chains covering AML, crypto tax, capital/liquidity, agentic payments, etc.) and get ordered, prefill-ready deep-links with handoff notes between steps.
  3. run_chain — execute a named ChainGraph workflow end-to-end server-side and get back the composite artifact.
  4. verify_execution_hash — independently re-verify a returned artifact's execution_hash (WebCrypto SHA-256 over RFC 8785/JCS-canonical {policy_parameters, output_payload}).
  5. build_chaingraph / emit_chaingraph_artifact / build_session_receipt — compose ad-hoc multi-tool chains and receipts outside the named-chain catalog.

Notes

  • 327 MCP tools total: 15 flagship tools render as interactive widgets, the rest are ChainGraph compute nodes plus the discovery/utility tools above.
  • Every tool declares readOnlyHint: true — nothing on the server or in your environment is modified by any call.
  • Full docs: https://ainumbers.co/mcp.html
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. 3d ago First seen · 23 lines · 17 tokens per session scan A 384d724a0cd6

Subscribe to this mod's changes

mcp-usage is a cursor rule published in the GitHub repository PostOakLabs/ainumbers-mcp-apps (2 stars, last pushed 4d ago), licensed MIT. It adds 17 tokens to every session and 383 once invoked, about $0.0001 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.