Which integrations are available for this server?

Provides a set of tools for building AI agents that can autonomously analyze corporate debt structures, evaluate maturity profiles, and perform multi-step credit analysis. Enables natural language credit analysis and portfolio risk assessment by integrating corporate debt data with OpenAI's language models through specialized toolsets.

How do I use DebtStack MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@DebtStack MCP Server Which telecom companies have a net leverage ratio above 5x?" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

DebtStack MCP Server

by debtstack-ai

Overview Schema Related Servers Score Discussions

Python

Remote

DebtStack.ai Python SDK

Corporate credit data for AI agents.

PyPI License

Why DebtStack?

Equity data is everywhere. Credit data isn't.

There's no "Yahoo Finance for bonds." Corporate debt structures, guarantor chains, and covenant details are buried in SEC filings—scattered across 10-Ks, 8-Ks, credit agreements, and indentures. An AI agent trying to answer "which telecom companies have leverage above 5x?" would need to read dozens of filings, extract the right numbers, and compute ratios manually.

DebtStack fixes this. We extract, normalize, and serve corporate credit data through an API built for AI agents.

Three Things You Can't Do Elsewhere

1. Cross-Company Credit Queries

# Find distressed telecom companies
GET /v1/companies?sector=Telecommunications&min_leverage=5&sort=-net_leverage_ratio

Screen ~300 companies by leverage, coverage ratios, or maturity risk in one call. No filing-by-filing analysis.

2. Pre-Built Entity Relationships

# Who guarantees this bond?
POST /v1/entities/traverse
{"start": {"type": "bond", "id": "893830AK8"}, "relationships": ["guarantees"]}

Guarantor chains, parent-subsidiary hierarchies, structural subordination—mapped and queryable. This data exists nowhere else in machine-readable form.

3. Agent-Ready Speed

< 100ms response time

AI agents chain multiple calls. If each took 30 seconds (reading a filing), a portfolio analysis would take hours. DebtStack returns in milliseconds.

Related MCP server: Finance MCP

Installation

pip install debtstack-ai

For LangChain integration:

pip install debtstack-ai[langchain]

Quick Start

from debtstack import DebtStackClient
import asyncio

async def main():
    async with DebtStackClient(api_key="your-api-key") as client:

        # Screen for high-leverage companies
        risky = await client.search_companies(
            sector="Telecommunications",
            min_leverage=4.0,
            fields="ticker,name,net_leverage_ratio,interest_coverage",
            sort="-net_leverage_ratio"
        )

        # Drill into the riskiest one
        ticker = risky["data"][0]["ticker"]
        bonds = await client.search_bonds(ticker=ticker, has_pricing=True)

        # Check guarantor coverage on their notes
        for bond in bonds["data"]:
            guarantors = await client.get_guarantors(bond["cusip"])
            print(f"{bond['name']}: {len(guarantors)} guarantors")

asyncio.run(main())

Synchronous Usage

from debtstack import DebtStackSyncClient

client = DebtStackSyncClient(api_key="your-api-key")
result = client.search_companies(sector="Energy", min_leverage=3.0)

What's In The Data

Coverage	Count
Companies	~300 (S&P 100 + NASDAQ 100 + high-yield issuers)
Entities	~39,000 (subsidiaries, holdcos, JVs, VIEs)
Debt Instruments	~10,000 (bonds, loans, revolvers) with 96% document linkage
Bond Pricing	~4,300 bonds with FINRA TRACE pricing (updated 3x daily)
SEC Filing Sections	~25,000 (searchable full-text)
Covenants	~1,800 structured covenant records

Pre-computed metrics: Leverage ratios, interest coverage, maturity profiles, structural subordination scores.

Relationships: Guarantor chains, issuer-entity links, parent-subsidiary hierarchies.

API Methods

Method	What It Does
`search_companies()`	Screen by leverage, sector, coverage, risk flags
`search_bonds()`	Filter by yield, spread, seniority, maturity
`resolve_bond()`	Look up CUSIP, ISIN, or "RIG 8% 2027"
`traverse_entities()`	Follow guarantor chains, map corporate structure
`search_pricing()`	FINRA TRACE bond prices, YTM, spreads
`search_documents()`	Full-text search across credit agreements, indentures
`batch()`	Run multiple queries in parallel
`get_changes()`	Track debt structure changes over time

Examples

Which MAG7 company has the most debt?

result = await client.search_companies(
    ticker="AAPL,MSFT,GOOGL,AMZN,NVDA,META,TSLA",
    fields="ticker,name,total_debt,net_leverage_ratio",
    sort="-total_debt",
    limit=1
)
# Returns structured data in milliseconds, not minutes

Find high-yield bonds trading at a discount

result = await client.search_bonds(
    seniority="senior_unsecured",
    min_ytm=8.0,
    has_pricing=True,
    sort="-pricing.ytm"
)

Who guarantees a specific bond?

guarantors = await client.get_guarantors("893830AK8")
for g in guarantors:
    print(f"{g['name']} ({g['entity_type']}) - {g['jurisdiction']}")

# Output:
# Transocean Ltd. (holdco) - Switzerland
# Transocean Inc. (finco) - Cayman Islands
# Transocean Offshore Deepwater Drilling Inc. (opco) - Delaware
# ... 42 more entities

Search for covenant language

result = await client.search_documents(
    q="maintenance covenant",
    section_type="credit_agreement",
    ticker="CHTR"
)
# Returns matching sections with highlighted snippets

LangChain Integration

Build AI agents that can autonomously analyze corporate credit data.

Installation

pip install debtstack-ai[langchain]

Available Tools

Tool	Description
`debtstack_search_companies`	Screen companies by leverage, sector, coverage ratios, and risk flags
`debtstack_search_bonds`	Filter bonds by yield, spread, seniority, maturity, and pricing
`debtstack_resolve_bond`	Look up bonds by CUSIP, ISIN, or description (e.g., "RIG 8% 2027")
`debtstack_traverse_entities`	Follow guarantor chains, map corporate structure, trace ownership
`debtstack_search_pricing`	Get FINRA TRACE bond prices, YTM, and spreads
`debtstack_search_documents`	Full-text search across credit agreements, indentures, and SEC filings
`debtstack_get_changes`	Track debt structure changes over time (new issuances, maturities, leverage)

Full Example

from debtstack.langchain import DebtStackToolkit
from langchain.agents import AgentExecutor, create_openai_functions_agent
from langchain_openai import ChatOpenAI
from langchain import hub

# Initialize toolkit with your API key
toolkit = DebtStackToolkit(api_key="your-api-key")
tools = toolkit.get_tools()

# Create an agent with GPT-4 (or any LangChain-compatible LLM)
llm = ChatOpenAI(temperature=0, model="gpt-4")
prompt = hub.pull("hwchase17/openai-functions-agent")
agent = create_openai_functions_agent(llm, tools, prompt)
agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)

# Ask natural language questions about corporate credit
result = agent_executor.invoke({
    "input": "Which telecom companies are most at risk of default?"
})
print(result["output"])

Example Queries

The agent can handle complex, multi-step credit analysis:

"Which telecom companies have leverage above 5x and near-term maturities?"
"Find all bonds yielding above 8% with senior secured status"
"Who guarantees Transocean's 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 changed in RIG's debt structure since January 2025?"
"Search for maintenance covenant language in Charter's credit agreements"
"Find distressed bonds trading below 80 cents on the dollar"

MCP Server (Claude Desktop, Claude Code, Cursor)

Give Claude (or any MCP client) direct access to corporate credit data.

Installation

pip install debtstack-ai[mcp]

Available Tools

Tool	Description
`search_companies`	Search companies by ticker, sector, leverage ratio, and risk flags
`search_bonds`	Search bonds by ticker, seniority, yield, spread, and maturity
`resolve_bond`	Look up a bond by CUSIP, ISIN, or description (e.g., "RIG 8% 2027")
`get_guarantors`	Find all entities that guarantee a bond
`get_corporate_structure`	Get full parent-subsidiary hierarchy for a company
`search_pricing`	Get FINRA TRACE bond prices, YTM, and spreads
`search_documents`	Search SEC filing sections (debt footnotes, credit agreements, indentures)
`get_changes`	See what changed in a company's debt structure since a date

Claude Desktop

Add to your Claude Desktop config (~/.config/claude/mcp.json on Mac/Linux, %APPDATA%\Claude\mcp.json on Windows):

{
    "mcpServers": {
        "debtstack-ai": {
            "command": "debtstack-mcp",
            "env": {
                "DEBTSTACK_API_KEY": "your-api-key"
            }
        }
    }
}

Claude Code

Add to your Claude Code config (~/.claude/mcp.json):

{
    "mcpServers": {
        "debtstack-ai": {
            "command": "debtstack-mcp",
            "env": {
                "DEBTSTACK_API_KEY": "your-api-key"
            }
        }
    }
}

Cursor

Add to your Cursor MCP settings (.cursor/mcp.json):

{
    "mcpServers": {
        "debtstack-ai": {
            "command": "debtstack-mcp",
            "env": {
                "DEBTSTACK_API_KEY": "your-api-key"
            }
        }
    }
}

Alternative: Run with Python Module

If you prefer not to install the console script, you can use python -m instead:

{
    "mcpServers": {
        "debtstack-ai": {
            "command": "python",
            "args": ["-m", "debtstack.mcp_server"],
            "env": {
                "DEBTSTACK_API_KEY": "your-api-key"
            }
        }
    }
}

Example Queries

Once configured, ask Claude:

"Which energy companies have near-term maturities and high leverage?"
"Who guarantees the Transocean 8% 2027 notes?"
"Compare Charter's debt structure to Altice"
"Find all senior secured bonds yielding above 8%"
"What are the financial covenants in Charter's credit agreement?"
"Show me RIG's corporate structure - where does the debt sit?"
"What changed in CVS's debt structure since June 2025?"
"Search for change-of-control provisions in Altice's indentures"

Pricing

DebtStack offers usage-based pricing with a free tier to get started.

See debtstack.ai/pricing for details.

License

Apache-2.0

Available Tools

8 tools

get_changesA

See what changed in a company's debt structure since a date. Returns new issuances, matured debt, leverage changes, and pricing movements. Use to monitor companies for material changes.

ParametersJSON Schema

Name	Required	Description	Default
`ticker`	Yes	Company ticker
`since`	Yes	Compare since date (YYYY-MM-DD)

TDQS

A3.8/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description lists what the tool returns (issuances, maturities, leverage changes, pricing) but does not explicitly state that it is read-only or disclose any side effects. With no annotations, the description carries the burden, and missing explicit read-only status reduces transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description consists of two succinct sentences: the first defines purpose and returns, the second states use case. No unnecessary words, and key information is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description adequately covers return types with examples. However, it lacks explicit mention of read-only nature and handling of empty results or date validation. Overall, it is complete for a simple query tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, providing basic descriptions for 'ticker' and 'since'. The tool description adds context by linking the 'since' parameter to a date comparison, but does not add significant meaning beyond the schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: 'See what changed in a company's debt structure since a date,' with specific examples of returns. It distinguishes itself from sibling tools like get_corporate_structure and get_guarantors, which focus on static structure or guarantees.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a use case: 'Use to monitor companies for material changes,' but does not explicitly state when not to use it or compare it with alternatives. This implies usage without clear exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_corporate_structureA

Get the full corporate structure for a company. Shows parent-subsidiary hierarchy, entity types, and debt at each level. Use to understand structural subordination and where debt sits in the org.

ParametersJSON Schema

Name	Required	Description	Default
`ticker`	Yes	Company ticker (e.g., 'RIG', 'CHTR')

TDQS

A4/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description must fully convey behavioral traits. Indicates a read operation returning structural data. Lacks details on potential size, latency, or data freshness, which are important for an agent to decide if the call is appropriate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences: first states purpose and output content, second provides usage guidance. No wasted words, front-loaded effectively.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple single-parameter input and no output schema, the description adequately explains what the tool returns. Could be improved by noting any limits like hierarchy depth or response format, but overall sufficient for an agent to understand the tool's function.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with a clear parameter description for ticker. Description adds no additional semantic information beyond the schema, meeting the baseline expectation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the tool retrieves the full corporate structure including hierarchy, entity types, and debt levels. Distinguishes from sibling tools by specifying the focus on structural subordination and debt location.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit use case: 'Use to understand structural subordination and where debt sits in the org.' Does not exclude alternative tools but context signals list siblings that serve different purposes (e.g., get_guarantors for guarantees).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_guarantorsA

Find all entities that guarantee a bond. Use to understand guarantee coverage and structural subordination risk. Pass a CUSIP or bond description.

ParametersJSON Schema

Name	Required	Description	Default
`bond_id`	Yes	Bond CUSIP or identifier

TDQS

A4/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description bears full burden. It implies a read operation ('Find') but does not disclose error behavior, rate limits, or authentication needs. Basic transparency is present but lacking depth.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences front-load the purpose and immediately follow with usage guidance. No extraneous words; every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with one required parameter and no output schema, the description covers essential purpose and usage. Could mention it is read-only, but annotations would handle that; overall complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with one parameter described as 'Bond CUSIP or identifier'. The description adds 'Pass a CUSIP or bond description' which is nearly identical. No new semantics beyond schema, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it finds entities that guarantee a bond, with verb 'find' and specific resource 'guarantors'. It distinguishes from siblings like search_bonds or get_corporate_structure which target different aspects.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is given ('understand guarantee coverage and structural subordination risk'), providing clear when-to-use. No explicit exclusions or alternatives are mentioned, but the purpose is distinct enough.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

resolve_bondA

Look up a bond by CUSIP, ISIN, or description. Use when you have a partial bond identifier and need full details. Example: 'RIG 8% 2027' or 'CUSIP 893830AK8'

ParametersJSON Schema

Name	Required	Description	Default
`query`	Yes	Bond identifier - CUSIP, ISIN, or description (e.g., 'RIG 8% 2027')

TDQS

A4.2/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so the description carries the full burden. It explains the core function and input but does not disclose any behavioral traits like side effects, authorization needs, or return structure (no output schema). Moderate transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no waste. Includes a clear example. Every word earns its place, making it highly efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with one parameter and no output schema, the description is well-rounded: specifies input types, action, and usage scenario. It could mention whether results are unique or multiple, but overall complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with a clear description of the 'query' parameter. The description adds value by providing examples ('RIG 8% 2027' or 'CUSIP 893830AK8') and clarifying acceptable formats, exceeding the base schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Look up a bond by CUSIP, ISIN, or description', specifying the verb (look up) and resource (bond). It differentiates from sibling tools like search_bonds by focusing on resolving partial identifiers to full details.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says 'Use when you have a partial bond identifier and need full details', providing clear guidance on when to use. It does not mention when not to use or suggest alternatives, but the context is sufficient.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_bondsA

Search bonds by ticker, seniority, yield, spread, and maturity. Use for yield hunting, finding high-yield opportunities, or analyzing maturity walls. Example: 'Find senior unsecured bonds yielding above 8%'

ParametersJSON Schema

Name	Required	Description
`ticker`	No	Company ticker(s)
`seniority`	No	Bond seniority level
`min_ytm`	No	Minimum yield to maturity (%)
`has_pricing`	No	Only bonds with pricing data
`maturity_before`	No	Maturity before date (YYYY-MM-DD)
`limit`	No	Maximum results (default 10)

TDQS

A4/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. The description implies a read-only search operation but does not explicitly state safety, authentication needs, or what happens with no results. It is minimally adequate as 'Search' suggests no side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences: one declarative statement of function and one with use cases and an example. No redundant words, front-loaded with key information. Highly concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 6 optional parameters and no output schema, the description covers purpose, typical use cases, and an example query. It does not describe the return format, but the example implicitly suggests bond results. For a search tool without output schema, this is nearly complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all parameters. The description adds a summary of filters and an example query, but does not provide additional details beyond what the schema offers. Baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Search bonds by ticker, seniority, yield, spread, and maturity.' It uses a specific verb (Search) and resource (bonds), and distinguishes from sibling tools like resolve_bond or search_pricing by focusing on bond screening with multiple filters.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly lists use cases: 'Use for yield hunting, finding high-yield opportunities, or analyzing maturity walls.' It provides an example. However, it does not mention when not to use this tool or suggest alternatives among siblings like search_pricing or search_documents.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_companiesA

Search companies by ticker, sector, leverage ratio, and risk flags. Use to find companies with specific characteristics, compare leverage across peers, or screen for structural subordination risk. Example: 'Find tech companies with leverage above 4x'

ParametersJSON Schema

Name	Required	Description
`ticker`	No	Comma-separated tickers (e.g., 'AAPL,MSFT,GOOGL')
`sector`	No	Filter by sector (e.g., 'Technology', 'Energy')
`min_leverage`	No	Minimum leverage ratio
`max_leverage`	No	Maximum leverage ratio
`has_structural_sub`	No	Filter for structural subordination
`limit`	No	Maximum results (default 10)

TDQS

A3.9/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, so the description carries the full burden. It describes the search behavior (filtering) and provides an example, but does not explicitly state that the operation is read-only, what happens on no results, or any rate/pagination details. The example is helpful but limited.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences plus a practical example. The first sentence immediately states the function, the second clarifies use cases, and the example concretely demonstrates usage. No filler words, every sentence serves a purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 6 optional parameters and no output schema, the description covers the search purpose and example usage but omits details about the result format, pagination (limit parameter hints at it), error behavior, or any side effects. For a search tool, the description is minimally adequate but lacks comprehensive detail.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with each parameter having a clear description. The description summarizes the parameters in prose ('by ticker, sector, leverage ratio, and risk flags') and adds an example, but does not add significant meaning beyond the schema. The example illustrates usage but does not explain parameter interactions or value ranges.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the verb 'Search' and specifies the resource 'companies' with clear filtering dimensions (ticker, sector, leverage ratio, risk flags). It differentiates from siblings like 'search_bonds' and search_pricing' which target different entities, and provides an example that reinforces the purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states three usage scenarios: 'find companies with specific characteristics, compare leverage across peers, or screen for structural subordination risk.' It lacks explicit when-not-to-use guidance but the context from siblings implies when other search tools are appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_documentsB

Search SEC filing sections for specific terms. Section types: debt_footnote, credit_agreement, indenture, covenants, mda_liquidity. Use to find covenant language, credit agreement terms, or debt descriptions.

ParametersJSON Schema

Name	Required	Description
`query`	Yes	Search terms
`ticker`	No	Company ticker(s)
`section_type`	No	Section type to search
`limit`	No	Maximum results (default 10)

TDQS

B3.2/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, and the description only states it is a search operation with no additional behavioral traits (e.g., authentication, rate limits, or side effects). The description relies on the tool name and common knowledge.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is concise with two sentences and a list, but the list is incomplete (missing two enum values). Efficient but could be more accurate.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is adequate for a simple search tool but lacks details on behavior like pagination, limits, or output structure. The miss in enum listing and no guidance on which search tool to use among siblings leaves gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers 100% of parameter descriptions, so the baseline is 3. The description adds some usage context for section_type (listing part of the enum) and overall purpose, but does not significantly enhance understanding of each parameter beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it searches SEC filing sections for specific terms, and provides examples of section types. However, the enum in the schema includes two additional types not listed in the description, slightly reducing completeness.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Description mentions 'Use to find covenant language, credit agreement terms, or debt descriptions,' giving context but not explicitly differentiating from sibling tools like search_bonds or search_companies. No when-not-to-use guidance is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_pricingA

Get bond pricing from FINRA TRACE. Returns current price, yield to maturity, and spread to treasury. Use to find distressed bonds or compare relative value.

ParametersJSON Schema

Name	Required	Description
`ticker`	No	Company ticker(s)
`cusip`	No	Bond CUSIP(s)
`min_ytm`	No	Minimum yield to maturity (%)
`limit`	No	Maximum results (default 10)

TDQS

A3.8/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. Only states it returns pricing data; no mention of real-time vs. historical, rate limits, or idempotency. Lacks depth for a read operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences conveying source, return values, and use cases. No redundancy, front-loaded with key action and data source.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Explains return fields despite no output schema. All parameters are documented. Lacks details on sorting, multiple ticker handling, or limitations, but sufficient for a straightforward search tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for all 4 parameters. The description adds context on output fields (price, YTM, spread) which helps interpret min_ytm. Slightly above baseline 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the tool retrieves bond pricing from FINRA TRACE, returns specific fields (price, YTM, spread), and provides use cases. Distinct from sibling tools like search_bonds.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides two use cases ('find distressed bonds' and 'compare relative value') but does not mention when not to use or contrast with alternatives like search_bonds. Relies on implied context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4/5.0

Disambiguation5/5

Each tool has a clearly distinct purpose with no overlap: get_changes monitors debt structure changes, get_corporate_structure shows hierarchy, get_guarantors identifies guarantors, resolve_bond looks up specific bonds, search_bonds searches bonds by criteria, search_companies searches companies by characteristics, search_documents finds SEC filing sections, and search_pricing retrieves bond pricing. The descriptions clearly differentiate each tool's function, eliminating ambiguity.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern using snake_case: get_changes, get_corporate_structure, get_guarantors, resolve_bond, search_bonds, search_companies, search_documents, and search_pricing. The verbs 'get', 'resolve', and 'search' are used appropriately and predictably, making the naming highly consistent and readable.

Tool Count5/5

With 8 tools, this server is well-scoped for debt analysis, covering key areas like bond lookup, company screening, structure analysis, and document search. Each tool serves a specific, necessary function without redundancy, and the count is within the ideal 3-15 range for a focused domain.

Completeness4/5

The toolset provides comprehensive coverage for debt analysis, including bond resolution, pricing, corporate structure, and document search. Minor gaps exist, such as no explicit tools for updating or deleting data (e.g., modifying bond entries) or advanced analytics like scenario modeling, but core workflows are well-supported and agents can work around these limitations.

Maintenance

ActivityInactive

ResponsivenessSyncing

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Constellation Credit
ai.constellationfinance
Financial and covenant data for public and private credit: statements, cap stacks, covenants.
Finance Security
2
MetricDuck — Financial Analysis
com.metricduck
SEC filing intelligence for AI agents. Financials, screening, peer comparison for 5,000+ companies.
Finance Search Research & Data
2
arkolith A
io.github.wikatar
Evidence-backed capital-change intelligence and sourced financial data for AI agents
Finance Government Data
2
Drillr — The financial MCP for AI agents A
ai.drillr
The financial MCP for AI agents - 90+ financial tables, SEC filings, signals, alt-data.
Finance Research & Data Data Platforms
836

Related MCP Servers

MCP Yahoo Finance
Finance Search
maxscheijen
A
license
B
quality
B
maintenance
A Model Context Protocol server that enables interaction with Yahoo Finance to retrieve stock pricing, company information, and historical financial data through natural language queries.
Updated 10 days ago (2026-08-24 11:54 UTC)
10
29
MIT
Finance MCP
Finance Search Web Scraping
FlowLLM-AI
A
license
C
quality
C
maintenance
Enables financial research and analysis through AI agents that combine web search, content crawling, entity extraction, and deep research workflows. Supports extracting stock/fund entities with security codes and conducting structured financial investigations.
Updated 7 months ago (2026-02-11 10:14 UTC)
9
24
Apache 2.0
EdgarTools MCP
Finance Search Research & Data
sareegpt
A
license
Not graded
quality
D
maintenance
Enables LLMs to download, parse, and analyze SEC EDGAR filings, including 10-K/Q reports, XBRL financial statements, and insider trading data. It provides structured access to institutional holdings, corporate events, and financial facts for comprehensive investment research.
Updated 7 months ago (2026-02-18 02:01 UTC)
4
MIT
edgar-mcp
Finance Search Open Data
henrysouchien
A
license
A
quality
B
maintenance
Provides access to SEC EDGAR financial data, enabling AI agents to fetch company filings, financial metrics, and narrative sections. It supports natural-language metric searching and extracts structured data from 10-K, 10-Q, and 8-K reports.
Updated 8 days ago (2026-08-26 11:38 UTC)
6
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/debtstack-ai/debtstack-python'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

DebtStack.ai Python SDK

Why DebtStack?

Three Things You Can't Do Elsewhere

Installation

Quick Start

Synchronous Usage

What's In The Data

API Methods

Examples

Which MAG7 company has the most debt?

Find high-yield bonds trading at a discount

Who guarantees a specific bond?

Search for covenant language

LangChain Integration

Installation

Available Tools

Full Example

Example Queries

MCP Server (Claude Desktop, Claude Code, Cursor)

Installation

Available Tools

Claude Desktop

Claude Code

Cursor

Alternative: Run with Python Module

Example Queries

Pricing

Links

License

Available Tools

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API