finance MCP Server
Your AI agent just burned $200. AgentGuard stops it at $5. Runtime cost guardrails for AI agents — budget enforcement, loop detection, kill switch. Zero dependencies, MIT licensed.
Discovered via github-topic:mcp-server and last synced 2w ago.
1. Install the package
npx -y @agentguard47/mcp-server
2. Add to claude_desktop_config.json
{
"mcpServers": {
"agent47": {
"command": "npx",
"args": [
"-y",
"@agentguard47/mcp-server"
]
}
}
}Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) / %APPDATA%\Claude\claude_desktop_config.json (Windows)
Deep-search for contracts based on bounty, platform, or tags.
Real-time health check of the agency network.
Intelligence on market pricing for agent services.
`LoopDetected`
Stops
AgentGuard
`TimeoutExceeded`
Link
`BudgetExceeded`
`LoopDetected`
`RetryLimitExceeded`
—
hard turns that need a stronger model
What it proves
Competitive notes: - [AgentGuard vs Vercel AI Gateway](docs/competitive/vercel-ai-gateway.md) - [Where AgentGuard fits in the agent security stack](docs/competitive/agent-security-stack.md) ## Decision Traces Capture proposal, human edit, approval, override, and binding events through the same event pipeline: ```python from agentguard import JsonlFileSink, Tracer, decision_flow tracer = Tracer(sink=JsonlFileSink(".agentguard/traces.jsonl")) with tracer.trace("agent.run") as run: with decision_flow( run, workflow_id="deploy-review", object_type="pull_request", object_id="123", actor_type="human", actor_id="pat", ) as decision: decision.proposed({"action": "merge"}) decision.approved(comment="Looks safe") decision.bound(binding_state="merged", outcome="success") ``` Supported event types: - `decision.proposed` - `decision.edited` - `decision.overridden` - `decision.approved` - `decision.bound` Guide: [`docs/guides/decision-tracing.md`](docs/guides/decision-tracing.md) ## MCP Server AgentGuard also ships a read-only MCP server for coding-agent workflows: ```bash npx -y @agentguard47/mcp-server ``` Use the SDK to enforce local safety where the agent runs. Use MCP when a client like Codex, Claude Code, or Cursor needs read access to traces, decisions, costs, usage, and budget health. ## Hosted Dashboard Boundary The SDK is the free local proof path. The hosted dashboard is for retained history, alerts, team visibility, spend trends, hosted decision history, and dashboard-managed remote kill signals.
Guard
`BudgetExceeded`
Connect to Helium's MCP server for news research, media bias analysis, balanced perspectives, stock/options data, and semantic meme search across 3.2M+ articles and 5,000+ sources
Automate account reconciliation by matching transactions, identifying discrepancies, and generating variance reports
Create comprehensive business plans, financial projections, and strategic documents for funding or planning
Calculate cash runway, burn rate, and financial sustainability projections
TradingAgents: Multi-Agents LLM Financial Trading Framework
Build your autonomous hedge fund in minutes. AutoHedge harnesses the power of swarm intelligence and AI agents to automate market analysis, risk management, and trade execution.
💰 Double-entry bookkeeping made easy — plain-text accounting for humans and AI agents. Polished iOS & Android app built with React Native + Expo.
Pizzly, financial market analysis combining technical indicators with LLMs, featuring real-time data processing and AI-powered market insights ⚡️
Learn how to use the Financial Analyst Claude skill. Complete guide with installation instructions and examples.
Learn how to use the helium-mcp Claude skill. Complete guide with installation instructions and examples.
Learn how to use the Runway Calculator Claude skill. Complete guide with installation instructions and examples.