The DebtStack.ai Python SDK is designed to solve the problem of fragmented enterprise credit data. Stock data is readily available, but credit data (such as corporate debt structures, guarantee chains, and covenant details) is often buried in SEC 10-Ks, 8-Ks, credit agreements, and bond indentures. If an AI agent wants to answer questions like "which telecom companies have a leverage ratio above 5x," it needs to read dozens of documents and calculate manually. DebtStack solves this pain point by extracting, standardizing, and providing enterprise credit data through an API designed specifically for AI agents.
[Main Capabilities]
- Cross-company credit queries: Filter approximately 300 companies by leverage ratio, coverage ratio, or maturity risk in a single call, without analyzing documents one by one.
- Pre-built entity relationships: Guarantee chains, parent-subsidiary hierarchies, and structural subordination relationships are all mapped and queryable; this type of data has no machine-readable form elsewhere.
- Agent-ready speed: AI agents usually chain multiple calls together. If each call takes 30 seconds (reading documents), portfolio analysis will take hours; DebtStack can return results in milliseconds.
[Data Content]
- Precomputed metrics: leverage ratio, interest coverage, maturity profile, structural subordination score.
- Relationships: guarantee chains, issuer-entity links, parent-subsidiary hierarchies.
[Usage]
- Python SDK: Supports synchronous usage (the documentation describes synchronous usage; specific code snippets are not provided).
- LangChain integration: Provides a usable LangChain tool for building AI agents that can autonomously analyze enterprise credit data.
- MCP server: Can be integrated with MCP clients such as Claude Desktop, Claude Code, and Cursor. Configuration methods:
- Claude Desktop: Add the configuration in ~/.config/claude/mcp.json (Mac/Linux) or %APPDATA%\Claude\mcp.json (Windows).
- Claude Code: Add the configuration in ~/.claude/mcp.json.
- Cursor: Add the configuration in .cursor/mcp.json.
- Alternative: If you do not want to install a console script, you can run the Python module with python -m. (The specific configuration content is not provided in the materials; please refer to the official documentation docs.debtstack.ai)
[Example Queries]
- Which MAG7 company has the most debt?
- Find high-yield bonds trading at a discount
- Who guarantees a specific bond?
- Search indenture language
- Which telecom companies have leverage above 5x and near-term maturities?
- Find all senior secured bonds with yields above 8%
- Who guarantees the Transocean 8.75% 2030 notes? How many entities are in the guarantee chain?
- Compare Charter and Altice's corporate structures—which has more structural subordination risk?
- What changes have occurred in RIG's debt structure since January 2025?
- Search for maintenance covenant language in Charter's credit agreement
- Find distressed bonds trading below 80 cents
- Which energy companies have near-term maturities and high leverage?
- Who guarantees the Transocean 8% 2027 notes?
- Compare Charter and Altice's debt structures
- Find all senior secured bonds with yields above 8%
- What are the financial covenants in Charter's credit agreement?
- Show RIG's corporate structure—where is the debt located?
- What changes have occurred in CVS's debt structure since June 2025?
- Search for change of control provisions in Altice's bond indentures
[Use Cases] Suitable for investment research, portfolio monitoring, risk assessment, and other scenarios that require automated corporate credit analysis, and especially suitable for building AI agents capable of autonomously performing multi-step credit analysis.
[Limitations and Notes]
- Pricing: Uses a usage-based pricing model and offers a free tier. See debtstack.ai/pricing for details.
- Specific installation commands, code examples, API endpoints, etc. are not provided in the materials; please consult the official documentation at docs.debtstack.ai.
- Discord community: discord.gg/debtstack-ai.
- Project address:https://github.com/debtstack-ai/debtstack-python
