// SCAN REPORT

Agent Fin

24 tools. 0 can modify or destroy data without limits.

Read-only server. Low risk, but rate limits prevent runaway API costs.

Last updated:

0 can modify or destroy data
24 read-only
24 tools total
// TOOL MAP
Read (24) Write / Execute (0) Destructive / Financial (0)
// WHAT CAN GO WRONG
✕

Even read-only tools carry cost. An agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up bills.

One command. Full control.

Intercept sits between your agent and Agent Fin. Every tool call checked against your policy before it executes — so your agent can do its job without breaking things.

npx -y @policylayer/intercept scan -- npx -y @markchiang/agent-fin
Scans every tool. Generates a policy. Starts enforcing.
Works with Claude Code · Cursor · Claude Desktop · Windsurf · any MCP client
// RECOMMENDED RULES
Cap read operations
equity_calendar_ipo:
  rules:
    - rate_limit: 60/minute

Controls API costs and prevents retry loops from exhausting upstream rate limits.

// ALL 24 AGENT FIN TOOLS
READ 24 tools
Read equity_calendar_ipo Read equity_compare_company_facts Read equity_compare_groups Read equity_discovery_active Read equity_discovery_aggressive_small_caps Read equity_discovery_growth_tech Read equity_discovery_losers Read equity_discovery_undervalued_growth Read equity_discovery_undervalued_large_caps Read equity_estimates_consensus Read equity_fundamental_balance Read equity_fundamental_cash Read equity_fundamental_dividends Read equity_fundamental_income Read equity_fundamental_metrics Read equity_ownership_share_statistics Read equity_price_historical Read equity_price_quote Read equity_profile Read equity_screener Read equity_search Read equity_shorts_fails_to_deliver Read equity_shorts_short_interest Read equity_shorts_short_volume
// FAQ
Is the Agent Fin MCP server safe to use without restrictions? +

The Agent Fin server is primarily read-only with 24 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the Agent Fin MCP server expose? +

24 tools across 1 categories: Read. 24 are read-only. 0 can modify, create, or delete data.

How do I add Intercept to my Agent Fin setup? +

One line change. Instead of running the Agent Fin server directly, prefix it with Intercept: intercept -c markchiang-agent-fin.yaml -- npx -y @markchiang/agent-fin. Download a pre-built policy from policylayer.com/policies/markchiang-agent-fin and adjust the limits to match your use case.

policylayer/intercept

Control every MCP tool call
your agent makes.

Set budgets, approvals, and hard limits across MCP servers.

npx -y @policylayer/intercept init
Protect your agent in 30 seconds. Scans your MCP config and generates enforcement policies for every server.
// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.