Discover +21 AI Finance apps & tools

Pros: Exposes live Polymarket trading quotes through MCP queries. Returns order-book depth and historical trading series for analysis. Open-source implementation enables community auditing. Integrates with MCP hosts such as Claude Desktop and Zed.

Cons: Does not perform trade execution, only data retrieval. Requires an MCP host and Node.js runtime to operate. Output accuracy depends on Polymarket public endpoints.

Pros: Standardized MCP implementation enables rapid deployment across MCP tools. Direct access to Luno's moderation models and automated safety scoring. Recognized in the developer community as a practical MCP implementation. Installs via npm and configures inside MCP client settings.

Cons: Requires hosting a Node.js service and operational maintenance. Needs a valid Luno API key for authenticated moderation calls. Depends on external moderation calls, which may affect latency. Limited to clients that support the Model Context Protocol.

Pros: Integrates with the Model Context Protocol for MCP-compatible clients. Provides a callable formatting endpoint for explicit text transformations. Runs on Node.js and supports local or container deployment. Open-source codebase enables customization and community contributions.

Cons: Requires an MCP host such as Claude Desktop to operate. Formatting depends on the connected model’s responses and prompts. Needs a Node.js runtime, aimed at developer workflows. Not aimed at non-technical users without integration effort.

Pros: Implements the MCP standard for programmatic model-to-tool calls. Go backend provides low-latency moderation checks. Open-source codebase allows inspection of moderation logic.

Cons: Moderation accuracy depends on the configured backend provider. Requires an MCP-compliant host such as Claude Desktop.

Pros: MCP-native server enables plug-in moderation for MCP-compatible clients. Uses Google Perspective API for industry-standard toxicity and sentiment scoring. Lightweight implementation intended for low-latency AI workflows. Open-source code lets developers inspect and customize moderation logic.

Cons: Requires a Google Perspective API key, creating an external dependency. Node.js runtime required, which may deter non-JavaScript teams. Outputs are likelihood scores, needing threshold tuning and monitoring.

Pros: MCP-compliant interface removes custom adapter development. Direct access to Blofin market data and order endpoints. Supports placing and canceling limit and market orders via AI. Requires standard Blofin API credentials for authenticated access.

Cons: Needs an MCP host and Node.js runtime to run. Operator must manage API key security and permissions. Execution behavior depends on Blofin API latency and matching.

Pros: Native MCP server for easy integration with MCP hosts. Configurable safety thresholds to adjust detection sensitivity. Supports tool-calling so agents can pre-check content. Lightweight Node.js server, deployable locally or remotely.

Cons: Depends on external Vaultpilot API and requires an API key. Functionality limited to MCP-compatible clients and hosts. Automated classifications need human review for edge cases.

Pros: Native MCP integration avoids custom API adapters. Adjustable sensitivity per moderation label. Lightweight design for low-latency checks. Standardized JSON-RPC communication for machine-readable results.

Cons: Requires a Node.js runtime for server execution. Integration limited to MCP-compatible clients. Category-based outputs need human review for nuanced cases.

Pros: Implements MCP toolset for structured AI function calls to MT5. Open-source codebase allows audits and custom extensions. Operates with both demo and live accounts when MT5 is logged in. Requires standard Python environments (3.10+) for host deployment.

Cons: Current release focuses on data retrieval, not built-in trade execution. Depends on a running MT5 terminal, creating an operational dependency. Targeted at technical users rather than non-developer traders.

Pros: Local operation limits data exposure to external services. Provides 14 read and 17 write tools for granular control. Supports investment monitoring and budget adjustments via language queries. Open-source GitHub project, praised for stability by early adopters.

Cons: Requires an MCP host and Node.js environment to run. Needs a valid Copilot Money API key and account. Write tools modify records, so verification is necessary before applying changes.

Pros: Acts as an MCP server so models can query portfolio data directly. Supports equities, crypto, bonds, and forex in one interface. CSV import/export for broker and spreadsheet compatibility. Persistent local storage keeps data on the user's machine.

Cons: LLM-generated insights require independent verification against market data. Full AI features need an MCP-compatible client to interact with the server. Requires running and maintaining Go binaries, favoring technical users.

Pros: Single API entry point for diverse financial endpoints. Three-tool separation helps partition discovery, streams, and queries. SQLite caching yields faster, locally traceable query responses. Open-source design supports local hosting and customization.

Cons: Requires Massive.com API credentials for live data. Needs an MCP-compatible host and Python runtime to run. Intended for developer users rather than nontechnical analysts. Analytic outputs require financial expertise to validate.