Claude for Financial Services

// Overview

Claude for Financial Services is Anthropic's open repository of reference agents, skills and data connectors for the financial-services workflows the company sees most: investment banking, equity research, private equity and wealth management. Everything ships from one source in two forms — install it as a Claude Cowork plugin, or deploy it through the Claude Managed Agents API behind your own workflow engine. Same system prompt, same skills; you choose where it runs.

Ten named agents cover four functions. Coverage and advisory gets the Pitch Agent (comps, precedents and an LBO through to a branded deck) and the Meeting Prep Agent. Research and modelling gets the Market Researcher, the Earnings Reviewer and a Model Builder that works live in Excel. Fund admin and finance ops gets the Valuation Reviewer, GL Reconciler, Month-End Closer and Statement Auditor. Operations and onboarding gets the KYC Screener. Each agent plugin is self-contained — it bundles the skills it uses — and each also ships as a Managed Agent template you deploy via /v1/agents, with agent.yaml, leaf-worker subagents and per-agent security notes in the cookbooks directory.

Underneath the agents sit vertical plugins: the skills, slash commands and MCP data connectors bundled by FSI vertical, installable on their own if you want /comps, /dcf and /earnings without a full agent. Partner-authored plugins from LSEG and S&P Global live alongside them, and there is admin tooling to provision the Claude Microsoft 365 add-in. Anthropic states clearly what the agents do not do: nothing here is investment, legal, tax or accounting advice, and the agents draft analyst work product for review rather than making recommendations, executing transactions, binding risk, posting to a ledger or approving onboarding — every output is staged for human sign-off.

// What it does

• Ten named workflow agents — Pitch, Meeting Prep, Market Researcher, Earnings Reviewer, Model Builder, Valuation Reviewer, GL Reconciler, Month-End Closer, Statement Auditor and KYC Screener
• Each agent ships twice from one definition: as a self-contained Cowork plugin and as a Claude Managed Agent template
• Vertical plugins with standalone skills and slash commands such as /comps, /dcf and /earnings, plus MCP data connectors
• Managed-agent cookbooks with agent.yaml, leaf-worker subagent examples, steering events and per-agent security notes
• Partner-built plugins from LSEG and S&P Global
• Admin tooling to provision the Claude Microsoft 365 add-in across a firm
• Human-in-the-loop by design — outputs are staged analyst work product, never executed transactions or ledger writes

// Getting started

Pick the agents that match your work and install them; each plugin bundles the skills it needs, so nothing else is required.

https://github.com/anthropics/financial-services

claude plugin marketplace add anthropics/financial-services

git clone https://github.com/anthropics/financial-services.git
cd financial-services
./scripts/deploy-managed-agent.sh

Commands and code are distilled from the project's own documentation — always check the official repo for the latest.

// When to use it

• Stand up a pitch, earnings or market-research workflow on Claude without designing the agent from scratch
• Take just the skills and connectors — /comps, /dcf, /earnings — into an agent you already have
• Deploy the same agent definition behind your own workflow engine through the Managed Agents API
• Study how Anthropic structures leaf-worker subagents and per-agent security notes for a regulated domain

// How Claude for Financial Services compares

Claude for Financial Services alongside other open-source agent skills & plugins tools AI/TLDR tracks, ranked by GitHub stars.