finance MCP Server
Personal research project — multi-agent Nordic stock research on Microsoft Agent Framework + Google Gemini, querying Inderes Premium MCP. Not affiliated with Inderes.
Discovered via github-topic:mcp and last synced 3mo ago.
Install instructions not detected yet
Check the source repository for the latest setup steps.
Numerical analysis: P/E, ROE, target prices, recommendations
Insider trades, forum, calendar
Inderes' analyst content, transcripts, filings
Action
Details
Requests/day
Synthesizes subagent outputs (no tools)
MCP tools
Inderes' own model portfolio
### Programmatic use ```python import asyncio from inderes_agent.cli.repl import ConversationState, handle_query async def main(): state = ConversationState() await handle_query("Mikä on Konecranesin P/E?", state) asyncio.run(main()) ``` See [`examples/`](examples/) for a single-question script and a multi-turn conversation example. --- ## Per-run logs Every query writes a complete forensic record to `~/.inderes_agent/runs/<timestamp>/`: ``` 20260501-205122-776/ ├── query.txt # the user's question ├── routing.json # which subagents the router picked, plus reasoning ├── subagent-01-quant.json ├── subagent-02-research.json ├── subagent-03-sentiment.json ├── synthesis.txt # lead's final synthesized answer ├── meta.json # duration, fallback events, error counts ├── console.log # raw HTTP/MCP/fallback log lines with timestamps └── narrative.md # human-readable timeline (auto-generated) ``` `narrative.md` is the single best file to inspect afterward. It includes: 1. **Routing decision** with the router's reasoning 2. **Tool-call timeline** with offsets and per-call duration, attributed by agent 3. **Each subagent's full output** (the structured response it returned to the lead) 4. **Lead's synthesis** (what the user saw) 5. **Statistics footer** — agents · tool calls · errors · 503 retries · fallbacks · total duration You can regenerate the narrative for any past run via: ```bash python scripts/explain.py # latest run python scripts/explain.py 20260501-205122-776 # specific run ``` In the REPL: `/explain` does the same for the current session's last run. --- ## Architecture at a glance ``` User question │ ▼ ┌─────────────┐ │ Router LLM │ Gemini, structured-output JSON └─────┬───────┘ │ ┌─────────┼─────────┬──────────┬──────────┐ ▼ ▼ ▼ ▼ ▼ aino-quant aino-research aino-sentiment aino-portfolio aino-valuation │ │ │ │ │ └─────────┴─────────┴──────────┴──────────┘ │ ▼ bounded by MAX_CONCURRENT_AGENTS Inderes MCP (16 tools, partitioned) │ ▼ ┌─ valuation/ ──── deterministic engine │ │ (pure Python, Greenwald-Gordon │ │ formulas, no LLM dependency) │ └─ runs after agent emits JSON ▼ ┌──────────────────────┐ │ Conflict detector │ flags disagreements between │ (Gemini, JSON output)│ subagents before synthesis └─────────┬────────────┘ ▼ ┌─────────────┐ │ aino-lead │ reads subagent outputs + └─────┬───────┘ conflict report, synthesizes ▼ Final answer ``` ### Subagent → MCP tool mapping
Configuring Google Cloud Identity-Aware Proxy (IAP) to enforce per-request identity verification for Compute Engine, App Engine, Cloud Run, and GKE services using access levels, context-aware policies, and programmatic access with service accounts.
Implementing and auditing GCP VPC firewall rules to enforce network segmentation, restrict ingress and egress traffic, apply hierarchical firewall policies across the organization, and monitor firewall rule effectiveness using VPC Flow Logs.
Auditing Google Cloud Platform IAM permissions to identify overly permissive bindings, primitive role usage, service account key proliferation, and cross-project access risks using gcloud CLI, Policy Analyzer, and IAM Recommender.
Implement GCP Binary Authorization to enforce deploy-time security controls that ensure only trusted, attested container images are deployed to Google Kubernetes Engine and Cloud Run.
TradingAgents: Multi-Agents LLM Financial Trading Framework
Sample code and notebooks for Generative AI on Google Cloud, with Gemini Enterprise Agent Platform
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.
Learn how to use the Financial Analyst Claude skill. Complete guide with installation instructions and examples.
Learn how to use the cloud-gcp Claude skill. Complete guide with installation instructions and examples.
Learn how to use the implementing-gcp-vpc-firewall-rules Claude skill. Complete guide with installation instructions and examples.