Anthropic Claude for Financial Services: Open-source agents, skills, and MCP connectors for FSI workflows

Claude for Financial Services is Anthropic's open-source repository of reference agents, skills, and data connectors for FSI workflows—investment banking, equity research, private equity, and wealth management. With 9.5k GitHub stars, it offers 10 named agents (Pitch Agent, GL Reconciler, Market Researcher), vertical skill bundles, partner integrations with LSEG and S&P Global, and 11 MCP data connectors.

Everything is available two ways from one source: install as a Claude Cowork plugin, or deploy via Claude Managed Agents API behind your own workflow engine. Same system prompt, same skills—you choose where it runs.

Primary sources

• Repository: github.com/anthropics/financial-services
• Documentation: CLAUDE.md, README.md
• License: Apache 2.0
• Key contributors: cxyback, manar-ant, mihilmy, tobinsouth, vinitra-ant, viveknair, alexa-perlov

TL;DR

Important: This is not investment advice

Nothing in this repository constitutes investment, legal, tax, or accounting advice. These agents draft analyst work product—models, memos, research notes, reconciliations—for review by a qualified professional. They do not:

• Make investment recommendations
• Execute transactions
• Bind risk
• Post to a ledger
• Approve onboarding

Every output is staged for human sign-off. You are responsible for verifying outputs and for compliance with the laws and regulations that apply to your firm.

Named agents: 10 workflow-specific agents

Each agent is named for the workflow it runs. They're starting points—install the ones that match your work, then tune prompts, skills, and connectors to how your firm does it.

Each agent plugin is self-contained—it bundles the skills it uses, so installing the agent is all you need.

Coverage & advisory

Research & modeling

Fund admin & finance ops

Operations & onboarding

For Managed Agent deployment—agent.yaml, leaf-worker subagents, steering-event examples, and per-agent security notes—see managed-agent-cookbooks/.

Vertical plugins: skills by FSI workflow

Start with financial-analysis—it carries the shared modeling skills and all data connectors. Add verticals for the workflows you need.

MCP integrations: 11 data connectors

All connectors are centralized in the financial-analysis core plugin and shared across the rest.

Note: MCP access may require a subscription or API key from the provider. Check with your data vendor for authentication credentials.

Getting started

Installation in Claude Cowork

In Cowork, open Settings → Plugins → Add plugin and either:

1. Paste this repo URL — https://github.com/anthropics/claude-for-financial-services — then pick the agents and verticals you want from the marketplace list, or
2. Upload a zip — zip any directory under plugins/ (e.g., plugins/agent-plugins/pitch-agent/) and drop it in.

Installation in Claude Code

# Add the marketplace
claude plugin marketplace add anthropics/claude-for-financial-services

# Core skills + connectors (install first)
claude plugin install financial-analysis@claude-for-financial-services

# Named agents — pick the ones you want
claude plugin install pitch-agent@claude-for-financial-services
claude plugin install gl-reconciler@claude-for-financial-services
claude plugin install market-researcher@claude-for-financial-services

# Vertical skill bundles
claude plugin install investment-banking@claude-for-financial-services
claude plugin install equity-research@claude-for-financial-services

Once installed:

• Agents appear in Cowork dispatch
• Skills fire automatically when relevant
• Slash commands are available in your session (/comps, /dcf, /earnings, /ic-memo)

Deploying as Claude Managed Agents

Each template under managed-agent-cookbooks/ references the same system prompt and skills as its plugin counterpart. The deploy script resolves file references, uploads skills, creates leaf-worker subagents, and POSTs the orchestrator to /v1/agents.

Deploy an agent:

export ANTHROPIC_API_KEY=sk-ant-...
scripts/deploy-managed-agent.sh gl-reconciler

Event routing:

See scripts/orchestrate.py for a reference event loop that routes handoff_request events between agents via your own orchestration layer.

Research preview note: Subagent delegation (callable_agents) is a preview capability. See per-agent READMEs for security and handoff guidance.

Repository layout

plugins/
  agent-plugins/               # Named agents — one self-contained plugin each
  vertical-plugins/            # Skill + command bundles by FSI vertical, plus MCP connectors
  partner-built/               # Partner-authored plugins (LSEG, S&P Global)
managed-agent-cookbooks/       # Claude Managed Agent templates — one dir per agent
claude-for-msft-365-install/   # Admin tooling to provision Claude Microsoft 365 add-in
scripts/                       # deploy-managed-agent.sh · check.py · validate.py · orchestrate.py · sync-agent-skills.py

How it fits together

Everything is file-based—markdown and JSON, no build step.

Slash commands reference

Once vertical plugins are installed, these slash commands become available:

financial-analysis (core)

• /comps — Comparable company analysis
• /dcf — Discounted cash flow valuation
• /lbo — Leveraged buyout model
• /3-statement — Integrated financial statement model
• /deck-qc — Quality check PowerPoint decks
• /excel-audit — Audit Excel models

investment-banking

• /cim — Confidential information memorandum
• /teaser — Teaser document
• /buyer-list — Generate buyer list
• /merger-model — Merger model
• /process-letter — Process letter

equity-research

• /earnings — Earnings note
• /initiation — Initiation report
• /model-update — Update financial model
• /thesis — Investment thesis
• /catalyst — Catalyst tracking

private-equity

• /ic-memo — Investment committee memo
• /diligence — Diligence checklist
• /sourcing — Sourcing pipeline
• /portfolio — Portfolio monitoring

wealth-management

• /financial-plan — Financial plan
• /rebalance — Portfolio rebalancing
• /client-review — Client review report
• /tlh — Tax-loss harvesting

fund-admin

• /gl-recon — General ledger reconciliation
• /accruals — Accruals analysis
• /variance — Variance commentary
• /nav-tieout — NAV tie-out

Example workflow: Pitch Agent

Let's walk through using the Pitch Agent to generate a branded pitch deck from comps, precedents, and LBO analysis.

1. Install the agent:

claude plugin install pitch-agent@claude-for-financial-services

2. Trigger the agent in Cowork:

In Cowork dispatch, select Pitch Agent and provide:

• Target company (name or ticker)
• Sector or industry
• Deal type (M&A advisory, capital raise, etc.)
• Your firm's branding guidelines (or upload a template)

3. The agent orchestrates:

• Pulls comps via MCP connectors (Daloopa, FactSet, S&P Global)
• Runs precedent transactions analysis
• Builds LBO model with assumptions
• Generates pitch deck following your firm's PowerPoint template
• Runs deck QC skill to check formatting, data consistency, and compliance

4. Review and refine:

The agent stages the deck for human sign-off. You review, tweak assumptions, adjust formatting, and approve.

5. Export:

Final deck is exported as .pptx ready for client delivery.

Example workflow: GL Reconciler

Let's walk through using the GL Reconciler to find breaks, trace root cause, and route for sign-off.

1. Install the agent:

claude plugin install gl-reconciler@claude-for-financial-services

2. Trigger the agent:

Provide:

• GL extract (CSV or Excel)
• Sub-ledger extract
• Prior period reconciliation (if available)

3. The agent orchestrates:

• Identifies breaks between GL and sub-ledger
• Traces root cause (timing differences, posting errors, missing entries)
• Generates variance commentary
• Routes for sign-off (via workflow integration or email)

4. Review and sign-off:

The agent stages the reconciliation for human review. You verify root cause, approve adjustments, and close the period.

Customizing agents for your firm

These are reference templates—they get better when you tune them to how your firm works.

Swap connectors: Point .mcp.json at your data providers and internal systems.

{
  "mcpServers": {
    "your-internal-data": {
      "url": "https://api.yourfirm.com/mcp"
    }
  }
}

Add firm context: Drop your terminology, processes, and formatting standards into skill files.

## Your Firm's Comps Process

1. Pull universe from [internal screening tool]
2. Filter by [your firm's criteria]
3. Apply [your firm's multiples]
4. QC against [your firm's checklist]

Bring your templates: /ppt-template teaches Claude your branded PowerPoint layouts.

Adjust agent scope: Edit agents/<slug>.md to match how your team actually runs the workflow.

Add your own: Copy the structure for workflows we haven't covered.

Claude for Microsoft 365: Install tooling

If your firm runs Claude inside Excel, PowerPoint, Word, and Outlook via the Microsoft 365 add-in, claude-for-msft-365-install/ is the admin tooling to provision it against your own cloud—Vertex AI, Bedrock, or an internal LLM gateway—instead of Anthropic's API.

It's a Claude Code plugin (not a Cowork plugin) that walks an IT admin through:

• Generating customized add-in manifest
• Granting Azure admin consent
• Writing per-user routing config via Microsoft Graph

Install:

claude plugin install claude-for-msft-365-install@claude-for-financial-services
/claude-for-msft-365-install:setup

This is separate from the agents and vertical plugins above—it's the on-ramp that gets the add-in deployed in a tenant, after which the agents and skills here are what runs inside it.

Real-world use cases and integration with other tools

Quantitative trading workflows (integrate with Kronos)

While Claude for Financial Services focuses on qualitative analysis (pitch decks, research notes, reconciliations), quantitative trading requires time series forecasting and backtesting.

Integration pattern:

1. Use Market Researcher agent to generate sector overview and peer shortlist
2. Feed peer tickers to Kronos foundation model for price forecasting (K-line sequences)
3. Use Model Builder agent to incorporate Kronos forecasts into DCF or LBO models
4. Use Earnings Reviewer agent to update models after earnings calls
5. Use Pitch Agent to generate final investment memo with quantitative + qualitative analysis

Example workflow:

# Step 1: Generate sector overview
claude plugin run market-researcher --sector "semiconductor"

# Step 2: Get peer tickers → feed to Kronos for forecasting
# (Kronos batch prediction on NVDA, AMD, INTC, etc.)

# Step 3: Build DCF with Kronos forecasts
claude plugin run model-builder --type dcf --forecasts kronos_output.csv

# Step 4: After earnings → update models
claude plugin run earnings-reviewer --ticker NVDA --quarter Q1-2026

# Step 5: Generate investment memo
claude plugin run pitch-agent --target NVDA --deal-type "coverage initiation"

See our Kronos blog post for details on using Kronos for financial time series forecasting with Qlib integration.

Portfolio construction (wealth-management workflows)

Wealth-management vertical includes:

• /financial-plan — Generate holistic financial plan
• /rebalance — Portfolio rebalancing recommendations
• /tlh — Tax-loss harvesting opportunities
• /client-review — Client review reports

Integration with portfolio optimization:

1. Use /financial-plan to generate client goals and risk tolerance
2. Feed to portfolio optimization model (mean-variance, Black-Litterman, risk parity)
3. Use /rebalance to generate rebalancing recommendations based on optimizer output
4. Use /tlh to identify tax-loss harvesting opportunities
5. Use /client-review to generate quarterly client reports

Contributing

Everything here is markdown and YAML. Fork, edit, PR. For new content:

New skill: Add it under plugins/vertical-plugins/<vertical>/skills/, then run:

python3 scripts/sync-agent-skills.py

This propagates to any agent that bundles it.

New agent: Create:

• plugins/agent-plugins/<slug>/ (with agents/<slug>.md + skills/)
• Matching managed-agent-cookbooks/<slug>/

Pre-push check:

python3 scripts/check.py

This lints every manifest, verifies all cross-file references resolve, and fails if any bundled skill has drifted from its vertical source.

GitHub stats and community

Key contributors: cxyback, manar-ant, mihilmy, tobinsouth, vinitra-ant, viveknair, alexa-perlov

Related on ExplainX

• Kronos foundation model for financial candlesticks — integrate quantitative forecasting with Claude qualitative analysis
• What are agent skills? Complete guide — structured playbooks for agents
• Claude Code integration guide — terminal-native workflows (if available)
• MCP servers directory — discover MCP integrations
• Agent skills registry — community-curated agent playbooks
• AI tools directory — discover utilities by task

Bottom line

Claude for Financial Services is Anthropic's open-source reference for FSI workflows—10 named agents (Pitch Agent, GL Reconciler, Market Researcher), 9 vertical plugins (investment-banking, equity-research, private-equity, wealth-management, fund-admin, operations), and 11 MCP integrations with Daloopa, FactSet, S&P Global, Moody's, and more.

Available two ways:

1. Claude Cowork plugins — zip upload or marketplace install
2. Claude Managed Agents API — headless deployment with deploy-managed-agent.sh

Use it for:

• Investment banking — pitch decks, CIMs, teasers, merger models
• Equity research — earnings notes, initiations, model updates
• Private equity — IC memos, diligence checklists, portfolio monitoring
• Wealth management — financial plans, rebalancing, client reviews
• Fund admin — GL recon, accruals, variance commentary, NAV tie-out
• Operations — KYC screening, document parsing

The real power: These are starting points. Swap connectors, add firm context, bring your templates, and tune to how your firm works. Everything is markdown + YAML—no build step.

Get started:

# Claude Code
claude plugin marketplace add anthropics/claude-for-financial-services
claude plugin install financial-analysis@claude-for-financial-services
claude plugin install pitch-agent@claude-for-financial-services

# Or browse: https://github.com/anthropics/financial-services

Integrate with quantitative tools: Combine with Kronos for time series forecasting, or your own portfolio optimization models, for end-to-end investment workflows.

Disclaimer

Nothing in this repository constitutes investment, legal, tax, or accounting advice. These agents draft analyst work product for review by qualified professionals. They do not make investment recommendations, execute transactions, bind risk, post to ledgers, or approve onboarding. Every output is staged for human sign-off.

You are responsible for verifying outputs and for compliance with applicable laws and regulations.

This article is an independent summary for developers on explainx.ai and is not sponsored by Anthropic. Features and specifications are based on the public GitHub repository as of May 7, 2026; verify on the official repo before production use.